alirezarezvani/claude-skills.

a11y-audit

Use for any accessibility audit or a11y fix (WCAG 2.2 A/AA, color contrast, compliance report, CI check) in React, Next.js, Vue, Angular, Svelte or HTML. Scans with a11y_scanner.py and checks contrast with contrast_checker.py, then fixes and re-verifies.

ab-test-setup

Use before planning or launching any A/B, split or multivariate test, or when asked if a result is significant. Sizes the test with sample_size_calculator.py and writes the hypothesis, metric and stop rule first, so it is not called early on noise.

access-lifecycle

Use when preparing or running a user access review, checking that leavers lost their access, finding orphaned or ownerless service accounts, answering an auditor's access-control request for SOC 2, ISO 27001, PCI DSS, HIPAA or NIST 800-53, or checking whether a finished review campaign will hold up. Diffs the HR roster against account exports, tests the campaign for coverage, self-review, unremoved revokes and rubber-stamping, and maps every exception to the controls it breaks.

ad-creative

Use for any ad copy request (RSA headlines, Meta, LinkedIn or TikTok ads, bulk variations), before writing. Checks every line against platform character limits and policy with ad_copy_validator.py. Campaign strategy and budgets: paid-ads.

adversarial-reviewer

Tough, critical review of a diff or PR before merge, through hostile reviewer personas that catch shared blind spots. Use whenever the user wants a change torn apart, a harsh second opinion, or a self-review felt too agreeable.

aeo

Use when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py.

agent-decision-receipts

Use when an autonomous agent takes a side-effecting action (deploy, delete, pay, grant access) that may need proving later, or for EU AI Act Art. 12 record-keeping. Builds a tamper-evident signed receipt with build_action_manifest.py and verifies it.

agent-designer

Design multi-agent systems (supervisor, swarm, pipeline) and tool schemas; find bottlenecks in run logs. Use whenever agents split work or a run is slow or costly. Not for Claude Code workflow files (workflow-builder).

agent-harness

Use when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.

agent-launcher-orchestrator

Use when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an agent', 'run this nightly'). Reads the session goal, routes with goal_router.py and compiles the loop with loop_compiler.py.

agent-memory

Use when an agent keeps relearning the same correction, CLAUDE.md has grown unreadable, or you need to trace where a remembered rule came from. Promotes facts through four tiers only on recurrence across sessions and days, with memory_promote.py and a human adopt step.

agent-protocol

Use when C-suite advisor agents need to call each other or run a multi-role meeting. Defines invocation syntax, loop prevention, isolation and response formats.

agent-regression-evals

Use before shipping any agent, prompt, model or tool change, or when a pass-rate drop needs a verdict. Runs repeated trials, gates candidate vs baseline with paired statistics in regression_gate.py, checks tool-call trajectories and finds flaky cases.

agent-run-forensics

Use when asked why an agent did something, what a past session or run changed, whether tests really passed, or to verify a session summary. Answers from the recorded transcript, not memory, with trace_finder.py, trace_timeline.py and claim_checker.py.

agent-workflow-designer

Use when architecting a multi-step LLM or agent pipeline, choosing single vs multi-agent, or fixing context bloat and broken handoffs. Scaffolds the pattern, handoff contracts and failure handling with workflow_scaffolder.py.

agenthub

Run several agents on one task in parallel and keep the best result: faster code, copy variants, research angles. Use whenever the user wants multiple attempts compared or best of N; spawns agents in git worktrees, ranks and merges the winner.

agile-product-owner

Use for backlog work: writing user stories and acceptance criteria, splitting epics, estimating or prioritizing for a sprint. Generates stories with user_story_generator.py.

ai-act-readiness

EU AI Act readiness for an AI system. Use when launching AI in the EU, at AI intake, or /compliance-os:ai-act-readiness.

ai-decision-authority

Use before letting AI or an agent act on a marketing or GTM task without human review, or when writing an AI review policy. Places each workflow in AI-primary, collaborative or human-primary by stakes and reversibility.

ai-security

Use when assessing an AI/ML system or LLM agent for prompt injection, jailbreaks, model inversion, data poisoning or tool abuse. Maps findings to MITRE ATLAS and scores robustness with ai_threat_scanner.py.

aims-audit

ISO 42001 AI readiness check. Use before a stage 1 or internal audit, or /compliance-os:aims-audit.

analytics-tracking

Use for any GA4, Google Tag Manager, event-tracking or conversion-tracking setup, audit or broken-event debug, before touching tags. Generates the event taxonomy and tracking plan with tracking_plan_generator.py. Campaign performance analysis: campaign-analytics.

andreessen

Blunt market-first verdict on an idea, venture or career bet, leading with the strongest counterargument, or a 3x5-card daily plan. Use whenever the user asks is there a market, are we at PMF, should I do this, or says pmarca mode.

api-design-reviewer

Use for any PR or spec that adds or changes REST endpoints, before approving it. Lints conventions with api_linter.py, detects breaking changes with breaking_change_detector.py and scores the design with api_scorecard.py.

api-test-suite-builder

Use when asked to write API, integration or contract tests for REST endpoints. Builds the suite from the routes: happy paths, auth, validation errors and edge cases per endpoint.

app-store-optimization

Use for any App Store or Google Play listing, keyword, ranking or review question, before writing metadata. Scores the listing with aso_scorer.py and checks keywords, competitors, title and subtitle limits and reviews with its 8 ASO scripts.

apple-hig-expert

Use when designing or reviewing iOS, macOS, watchOS or visionOS UI against Apple's Human Interface Guidelines, including Liquid Glass, contrast and tap targets. Checks it with hig_checker.py.

ar-loop

Use for /ar-loop, or to run an autoresearch experiment on a schedule (10 min to monthly) with CronCreate.

ar-resume

Use for /ar-resume, or to continue a paused autoresearch experiment from its branch and results history.

ar-run

Use for /ar-run, or to run one manual autoresearch iteration: edit, evaluate, keep or discard.

ar-status

Show autoresearch results and progress. Use when asked how an experiment runs, or /ar-status.

arquiteto-de-empresa

Use when a founder wants to document or design a whole company as version-controlled markdown (company as code, a company wiki agents can read, an OKF bundle). Runs a 12-phase interview, scaffolds with scaffold_bundle.py and checks it with okf_linter.py.

atlassian-admin

Use for Atlassian org administration: Jira or Confluence users and groups, permissions, SSO, marketplace apps or security policy. Audits permissions with permission_audit_tool.py.

atlassian-templates

Use when creating or changing Jira or Confluence templates, blueprints or page layouts for reuse across the org. Scaffolds them with template_scaffolder.py.

autoresearch-agent

Make a file measurably better by trial: faster code, smaller bundle, higher pass rate or prompt score. Use whenever the user wants something optimized against a metric, before hand-tuning; loops edits, keeps wins, resets losses. Needs an eval command.

aws-solution-architect

Use when designing or costing an AWS architecture (serverless, Lambda, API Gateway, DynamoDB, ECS, Aurora, CloudFormation, migration to AWS). Designs it with architecture_designer.py, generates stacks with serverless_stack.py and finds savings with cost_optimizer.py.

azure-cloud-architect

Use when designing or costing an Azure architecture (AKS, App Service, Functions, Cosmos DB, Bicep or ARM, Azure DevOps, migration to Azure). Designs it with architecture_designer.py, generates Bicep with bicep_generator.py and finds savings with cost_optimizer.py.

behuman

Reply like a real person, direct and warm, without lists or hedging. Use whenever the user says you sound robotic, asks you to be real or talk like a person, wants mirror mode, or is going through grief, job loss or fear. Not for code or factual lookups.

board

Use to post or read messages on the AgentHub coordination board between competing agents.

board-deck-builder

Use when building a board deck, investor update or QBR from all C-suite perspectives. Structures the narrative and how to deliver bad news.

board-meeting

Use for /c-level-agents:boardroom or a strategic question that needs a structured multi-executive deliberation. Runs six phases: context, isolated C-suite views, critic, synthesis, founder review and decision.

board-prep

Use before a board meeting, investor update or fundraising pitch where the numbers will be challenged. Drills numbers cold, anticipates the hard questions and builds a narrative that admits weakness without losing the room.

boardroom

Use for /c-level-agents:boardroom, or a decision spanning several executive domains (a pricing change, raise vs cut). Runs a 6-phase C-suite deliberation and writes a board memo.

book-to-skill

Use when turning a book, docs folder or spec collection (PDF, EPUB, DOCX, HTML, Markdown) into an agent skill, before summarizing it by hand. Extracts with extract_document.py, compiles chapters, glossary and cheatsheet, validates with book_skill_validator.py and enforces a rights gate.

boost-asio-pro

Use for any C++ networking code with Boost.Asio or standalone Asio (TCP/UDP, SSL, timers, strands, io_context, co_spawn, awaitable, completion handlers), before writing or reviewing it. Applies lifetime, strand and cancellation rules that avoid the classic async bugs.

brief

Use for /c-level-agents:brief, or to frame a strategic question (options, assumptions, success criteria) as a one-page brief before deliberation.

browserstack

Use when running Playwright tests on BrowserStack or across a browser matrix ('browserstack', 'cross-browser', 'test on safari or firefox', 'browser compatibility').

business-growth-skills

Use when a growth request needs routing between customer-success-manager, sales-engineer, revenue-operations and contract-and-proposal-writer.

business-investment-advisor

Use when deciding whether a capital expense is worth it (equipment, property, an acquisition, hiring, technology), or for ROI, IRR, NPV, payback, build vs buy or lease vs buy.

business-name-fit

Use when naming a company, brand or product, or checking whether a name works abroad, before committing to one. Tests a culturally rooted name for pronunciation, bad meanings and trust in each target market, and suggests alternatives.

business-operations-skills

Route internal operations requests to the right BizOps skill: process, vendors, capacity, internal comms, SOPs, procurement. Use whenever the user asks where the bottleneck is or about vendor health.

c-level-agents

Use when the founder wants a virtual executive team or a /c-level-agents command. Lists the 13 C-suite agents and 21 commands and routes multi-role decisions.

c-level-skills

Find which C-level advisor fits a question: 14 C-suite roles, board meetings, culture, M&A. Use whenever the user asks which advisor to use.

caio-review

Use for /c-level-agents:caio-review, or to challenge a plan involving AI (no eval set, API vs fine-tune vs self-host, EU AI Act class).

campaign-analytics

Analyze campaign performance on the user's numbers: ROAS, CPA, ROI, multi-touch attribution and funnel drop-off. Use whenever the user asks which channel or ad is working, where spend is wasted, why conversions dropped, or shares campaign results to review.

capa-officer

Use for CAPA work in a medical device QMS: root cause analysis (5-Why, fishbone), corrective action plans, effectiveness checks or CAPA metrics. Tracks CAPAs with capa_tracker.py and analyzes causes with root_cause_analyzer.py.

capacity-planner

Size an ops or support team and plan headcount: Erlang C queue models, utilization risk, hiring order. Use whenever the user asks how many agents or staff they need, if the team is overloaded, or who to hire first.

capture

Use whenever the user unloads a messy brain dump of ideas, tasks and plans ('capture this', 'brain dump', a long unstructured paste) and wants it organized. Sorts it with dump_classifier.py into projects, tasks and connections with nothing lost.

caveman

Ultra-short replies that cut tokens about 75% by dropping filler, articles and pleasantries while staying technically accurate. Use whenever the user says caveman mode, talk like caveman, use caveman, less tokens, be brief, too wordy, or invokes /caveman.

cco-review

Challenge a churn, retention, segment or CS hiring plan. Use whenever asked or /c-level-agents:cco-review.

cdo-review

Use for /c-level-agents:cdo-review, or to challenge a plan touching training-data rights, data architecture or data monetization.

ceo-advisor

CEO and founder advice: company strategy, board and investor management, fundraising, org design, culture. Use whenever a CEO asks how to run the company, handle investors or board, or make a big bet.

cfo-advisor

Startup finance: runway and burn, unit economics (LTV, CAC, payback), fundraising and dilution, board financials. Use whenever the user shares burn, cash, ARR or CAC numbers or asks if they can raise.

cfo-review

Challenge a plan that spends real money: hiring wave, raise, channel budget. Use whenever asked or /c-level-agents:cfo-review.

challenge

Pre-mortem a plan: assume it failed in 12 months and work back to the assumptions, dependencies and execution risks. Use whenever the user will commit serious resources or feedback seems too positive.

change-management

Use when rolling out a reorg, pivot, tool switch, leadership change or product kill. Plans it with ADKAR, communication templates and resistance patterns.

channel-economics

Use for a direct vs partner channel review: fully loaded cost to serve, channel ROI and the best channel mix under constraints. Runs cost_to_serve_calculator.py, channel_roi_analyzer.py and channel_mix_optimizer.py.

chaos-engineering

Use before running a chaos experiment, gameday or fault injection, or after one to write it up. Designs it with steady state and abort criteria in experiment_designer.py, sizes the blast radius with blast_radius_calculator.py and drafts the postmortem.

chief-ai-officer-advisor

Use for AI strategy decisions: API vs fine-tune vs build, EU AI Act or US state risk classification, when self-hosting pays off, or AI hiring order. Runs model_buildvsbuy_calculator.py, ai_risk_classifier.py and ai_cost_economics.py.

chief-customer-officer-advisor

Use for retention strategy, customer segmentation or CS team sizing decisions (GRR vs NRR, churn causes, pooled vs named CSMs). Runs retention_decomposition_analyzer.py, customer_segmentation_designer.py and cs_coverage_calculator.py.

chief-data-officer-advisor

Use for data strategy decisions: training models on customer data, warehouse vs lakehouse vs mesh, valuing data for a raise or M&A, or data hiring order. Runs ai_training_data_audit.py, data_product_strategy_picker.py and data_asset_valuator.py.

chief-of-staff

Use when a founder question needs routing to the right C-suite advisor, or a cross-functional decision needs a board meeting convened. Loads company context, synthesizes the answers and tracks decisions.

chro-advisor

People strategy: hiring plans, comp bands, org structure, performance, retention. Use whenever the user asks who to hire, what to pay, how to structure teams or why staff leave.

churn-prevention

Use when designing a cancel flow, save offers, exit surveys or dunning emails, or cutting failed-payment churn. Sizes the revenue at stake with churn_impact_calculator.py first. Health scores and expansion: customer-success-manager.

ci-cd-pipeline-builder

Set up or refactor CI/CD for a repo: detect the stack, generate pipeline YAML. Use whenever the user wants builds or tests to run on each push or needs a CI workflow file.

ciso-advisor

Use for security leadership decisions: a security program, budget justification in dollars, SOC 2 vs ISO 27001 vs HIPAA roadmap, or board security reporting. Quantifies risk with risk_quantifier.py and tracks compliance with compliance_tracker.py.

ciso-review

Challenge a plan touching customer data, compliance or prod access. Use when asked or /c-level-agents:ciso-review.

claude-coach

Use when the user wants to get better at using Claude ('coach me', 'teach me Claude tricks', 'make me a power user'). Rates their prompts with prompt_rater.py and surfaces one relevant power-user tip per turn after activation.

clinical-research

Use when designing a prospective clinical study: choosing primary and secondary endpoints, estimating sample size and power, or scoring feasibility before submission. Runs endpoint_selector.py, sample_size_estimator.py and phase_gate_scorer.py; outputs are estimates for a biostatistician to confirm.

cloud-security

Use when checking AWS, Azure or GCP for security misconfigurations: IAM privilege escalation, public buckets, open security groups, IaC gaps. Runs cloud_posture_check.py and maps findings to MITRE ATT&CK.

cmmc-readiness

Use when a defense contractor or subcontractor is preparing for a CMMC 2.0 Level 2 self-assessment or C3PAO assessment, calculating or checking an SPRS score against NIST SP 800-171 Rev 2, deciding what can go on a POA&M, tracking POA&M closeout before Conditional status expires, or scoping assets, enclaves and cloud providers that handle CUI. Scores all 110 requirements with the 32 CFR 170.24 weights, blocks gaps that can never be deferred, and classifies the asset inventory into CMMC asset categories.

cmo-advisor

Marketing leadership: positioning, product-led vs sales-led vs community-led growth, budget split across channels, marketing team design. Use whenever the user asks how to grow, which go-to-market fits or where to spend.

cmo-review

Use for /c-level-agents:cmo-review, or to challenge positioning, ICP, messaging or channel mix before a launch.

code-reviewer

Use for any code review: a pull request, a diff, a commit, or a pasted function, handler or file in TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#/.NET, Java, C, C++, Rust, Ruby, PHP or Dart/Flutter. Applies per-language rule packs (security such as SQL injection and missing auth, async and resource handling, error handling, performance) and scripts that score a PR's risk and complexity, then gives a merge verdict with blocking and non-blocking findings. Use whenever the user asks to review, check or look over code, says 'code review', 'review this PR', 'review this diff' or 'is this safe to merge', or asks what is wrong with a snippet, even a single function.

code-to-prd

Use when asked to write a PRD or product spec from an existing codebase (reverse-engineer requirements, document pages, fields, routes and endpoints). Maps the code with codebase_analyzer.py and scaffolds the PRD with prd_scaffolder.py.

coding-agent-rollout

Roll out Claude Code to a team: shared or managed settings, MCP and plugin approval, layered CLAUDE.md, adoption. Use whenever the user sets up Claude Code for their team or org, or asks if a rollout or settings file is right.

cold-email

Use for any cold outreach or SDR email or follow-up sequence to prospects who did not opt in, before drafting. Scores the sequence for length, personalization and spam risk with email_sequence_analyzer.py. Opted-in nurture: email-sequence.

collab-proof

Use for /collab-proof or a session retrospective on what Claude contributed versus what the user drove. Builds an evidence-backed split of the session's decisions and work.

commercial-forecaster

Use when building a bookings, ARR, pipeline or NRR forecast, or a commit, best-case and pipeline board number. Forecasts with bookings_forecaster.py, projects cohorts with cohort_arr_projector.py and scores stage confidence with funnel_confidence_scorer.py, showing every conversion assumption.

commercial-policy

Use when writing or revising discount rules: discount matrix, approver thresholds, exception flows and the deal framework sales works under. Builds the matrix with discount_matrix_builder.py, routes exceptions with exception_router.py and checks the policy with policy_linter.py.

commercial-skills

Use when a commercial request needs routing (pricing, deal review, discounts, partners, channels, policy, RFPs, forecasts): 'review this deal', 'should we discount'. Lists the commercial skills and routes to one.

commit-craft

Turn a mix of changes into clean, reviewable commits with good messages, blocking staged secrets and .env files. Use whenever the user says commit this, wants to split work into commits, write a commit message, or is about to push.

company-os

Use when choosing or setting up how the company runs: EOS, Scaling Up or OKRs, accountability chart, scorecard, meeting rhythm, quarterly rocks.

competitive-intel

Use for competitor analysis, battlecards, win/loss review or positioning against alternatives. Builds a tracking system that feeds positioning, sales and roadmap.

competitive-teardown

Deep competitor teardown: pricing, reviews, hiring, SEO, UX, scored across 12 dimensions with SWOT and positioning maps. Use whenever the user asks how they compare to a rival or how to respond to a competitor's move.

competitor-alternatives

Use when creating an 'X vs Y', '[product] alternative' or comparison page, before drafting. Builds the comparison matrix with comparison_matrix_builder.py and picks one of four page formats with a fair, sourced structure.

compliance-os

Use when running several compliance frameworks at once: which apply, where controls overlap, a mock audit or one evidence checklist. Runs framework_selector.py, cross_framework_mapper.py, audit_simulator.py and evidence_pool_generator.py.

compliance-readiness

Use for /compliance-os:compliance-readiness, or before adding a framework or planning the annual audit calendar.

confluence-expert

Use when building or restructuring a Confluence space: page hierarchy, permissions, templates, Jira macros or a content audit. Generates structure with space_structure_generator.py and audits with content_audit_analyzer.py.

content-creator

Use when someone asks for 'content creator' by name. Deprecated alias: hands writing to content-production and planning to content-strategy.

content-humanizer

Make a draft sound less like AI: fix generic, robotic text with rhythm, specifics, personality and brand voice. Use whenever the user says copy sounds like ChatGPT, bland or stiff, or not like them.

content-production

Write a blog post, article or guide end to end: research, outline, draft, SEO pass and quality gates. Use whenever the user asks to write a blog post, draft an article on a topic, or turn notes into a full piece.

content-strategy

Use when deciding what content to create (topics, clusters, a blog or content plan), before listing ideas. Maps topic clusters with topic_cluster_mapper.py and ties each piece to a funnel stage and search demand.

context-engine

Use when starting a C-suite advisor session, when company context is missing or older than 90 days, or before company data goes to an external service. Loads and enriches ~/.claude/company-context.md and applies anonymization rules.

contract-and-proposal-writer

Use when drafting a freelance contract, proposal, SOW, NDA or MSA for US, EU, UK or DACH jurisdictions. Writes structured Markdown with docx conversion steps; not legal advice.

coo-advisor

Use for operations leadership: process design, OKR execution, operating cadence, bottlenecks or scaling playbooks. Tracks OKRs with okr_tracker.py and analyzes efficiency with ops_efficiency_analyzer.py.

copy-editing

Edit, proofread and tighten existing marketing copy in focused passes: clarity, voice, proofreading, specificity, readability and AI tells. Use whenever the user asks to polish, clean up, shorten or fix the wording of a page, email or ad.

copywriting

Use for any headline, tagline, CTA, landing, pricing or about-page copy request, before drafting. Scores candidate headlines with headline_scorer.py and applies a page-section framework, so the first draft is tested rather than guessed.

coverage

Find what is not tested: map untested pages and flows and coverage gaps. Use whenever the user asks what needs tests, about missing tests or test coverage.

cpo-advisor

Product leadership: PMF measurement, product vision, portfolio investment, product org design, board product reporting. Use whenever the user asks if they have PMF or how to split investment across products.

cpo-review

Challenge a roadmap, PMF claim or feature kill. Use whenever asked or /c-level-agents:cpo-review.

cro-advisor

Use for B2B revenue leadership: forecasting, quotas, sales model, NRR and churn, pricing or sales capacity. Forecasts with revenue_forecast_model.py and analyzes churn with churn_analyzer.py.

cro-review

Challenge a forecast, win-rate drop or sales hires. Use whenever asked or /c-level-agents:cro-review.

cross-eval

Use for /c-level-agents:cross-eval, or when a high-stakes memo needs independent review by several models before the boardroom.

cs-onboard

Use when setting up the C-suite advisors for the first time, or when company context is missing or stale after a raise or pivot. Interviews the founder across 7 dimensions and writes ~/.claude/company-context.md.

cto-advisor

CTO decisions: tech debt, architecture direction, scaling the engineering team, technology evaluation, DORA metrics. Use whenever the user asks whether to rewrite, how to grow the eng team or which tech to bet on.

cto-review

Challenge an architecture bet, 10x scaling plan or rebuild vs buy. Use whenever asked or /c-level-agents:cto-review.

culture-architect

Use when defining company values, turning them into behaviors, assessing culture health or designing rituals. Treats culture as operating behavior, not posters.

customer-success-manager

Use when reviewing customer accounts for health, churn risk or expansion. Scores health with health_score_calculator.py, churn with churn_risk_analyzer.py and upsell with expansion_opportunity_scorer.py.

data-quality-auditor

Use before analysis or model training on any dataset, or when asked to profile data or hunt missing values and outliers. Profiles it with data_profiler.py, missing_value_analyzer.py and outlier_detector.py and writes a remediation plan.

database-designer

Design a database schema: tables, relationships, indexes, normalization, SQL vs NoSQL, migration plans. Use whenever the user asks how to structure their data, which database to pick, or before writing DDL.

database-schema-designer

Use when asked for an ERD, table relationships, normalization or a schema migration plan. Produces the ERD and normalized DDL with migration steps.

deal-desk

Use before closing a deal that needs a discount beyond AE authority, has a redlined MSA or unclear per-deal economics. Scores it with deal_scorer.py, names approvers with discount_approval_router.py and flags risky terms with terms_redliner.py. Never auto-approves.

decide

Use for /c-level-agents:decide, or right after the founder approves a boardroom memo, to log it as a durable decision.

decision-logger

Use when logging a decision after a board meeting, reviewing past decisions or checking overdue actions. Keeps raw transcripts and approved decisions separately with decision_tracker.py.

deep-learning-book

Use when studying or applying Goodfellow, Bengio and Courville's Deep Learning, or asking if its advice still holds. Indexes all 20 chapters with a 2016-to-2026 delta, plans reading paths with reading_path_planner.py and diagnoses training failures with training_diagnostics.py.

deep-work

Use when someone wants to plan a deep work day, time-block their calendar or task list, budget or cut shallow work, protect focus hours, track deep-work sessions and streaks, run an end-of-day shutdown ritual, or says "/deep-work" or "/time-block". Classifies tasks deep vs shallow, builds an energy-first time-blocked schedule that refuses deep demand past the 4-hour ceiling, batches shallow work into at most two windows, and logs focus sessions against a weekly target.

deepread

Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes.

demo-video

Use when asked for a demo video, product walkthrough, feature showcase or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg and edge-tts to render it.

dependency-auditor

Audit project dependencies for CVEs and licenses and plan safe upgrades. Use whenever the user asks if their packages are safe, before a release or major version bump, while chasing a CVE, or for a license review.

design-qa

Use when a UI screen, page or component is about to be called done, handed off or shipped, or when generated UI looks generic or half-finished. Gates the rendered result, not the design file - finds controls that do nothing, placeholder copy, removed focus rings, missing loading/empty/error states, low contrast, small targets, hidden focus and broken reflow measured in the real browser, and flags template defaults without blocking on taste.

docker-development

Use for any Dockerfile or docker-compose file to write, optimize or review, before editing it. Checks layers, caching, size and security with dockerfile_analyzer.py and validates compose files with compose_validator.py.

dossier

Use for diligence or meeting prep on a specific company, person or organization ('prep me for a meeting with X', 'due diligence on Y'). Tests the user's stated hypothesis with balanced evidence (disconfirming_evidence_balance.py) and writes a .docx dossier.

email-sequence

Use for any drip, nurture, onboarding, welcome or re-engagement email sequence to opted-in users, before writing emails. Plans timing, triggers and exits and scores the sequence with sequence_analyzer.py.

email-template-builder

Use when adding or reworking transactional email (React Email templates, Resend, Postmark, SendGrid or SES, preview, i18n, dark mode, deliverability). Builds the template system and provider integration end to end.

embedded-iot-mentor

Use for any embedded or IoT hardware project (ESP32, STM32, Arduino, Pico, firmware, PCB, MQTT, Home Assistant, sensor dashboards), before buying parts. Picks the MCU, board and toolchain, decides where readings go and gives a phased build plan with time and cost.

engineering-advanced-skills

Pick the right advanced engineering skill: agents, RAG, MCP, CI/CD, databases, observability, release. Use whenever the user asks which skill fits a task.

engineering-skills

Find which engineering skill fits a task: architecture, frontend, backend, QA, DevOps, security, AI/ML, data, cloud. Use whenever the user is unsure which skill to use; load only that one.

env-secrets-manager

Use when auditing .env files, planning credential rotation, chasing a missing env var in production or hardening a repo against leaked secrets. Scans for committed secrets and drift with env_auditor.py.

epic-design

Use for any landing page, hero section or scroll-driven web design that should feel cinematic (parallax, scrollytelling, overlapping sections, text reveals, Apple-style animation), before coding. Inspects assets with inspect-assets.py, then builds with 45+ 2.5D techniques, no WebGL.

eu-ai-act-specialist

Use for EU AI Act (Regulation 2024/1689) compliance work: classifying an AI system's risk tier, planning the Art. 43 conformity route and Annex IV file, or listing obligations by role. Runs ai_system_risk_classifier.py, conformity_assessment_planner.py and ai_act_obligation_tracker.py, citing Articles.

eval

Rank finished AgentHub agents by metric or judge. Use when asked which agent won.

execute

Use for /c-level-agents:execute, or to turn an approved decision into a 90-day plan with weekly milestones and owners.

executive-mentor

Use when a founder or executive needs a plan stress-tested, a dreaded decision made, a hard board meeting prepared or an honest post-mortem. Adversarial thinking partner; scores options with decision_matrix_scorer.py and maps stakeholders with stakeholder_mapper.py.

experiment-designer

Plan A/B tests and product experiments: hypotheses, sample size, priority, reading results. Use whenever the user asks if a test won, how long to run it or what to test.

extract

Turn a fix or pattern that keeps coming up into a reusable skill with SKILL.md, reference docs and examples. Use whenever the user runs /si:extract or wants to package a recurring solution or lesson as a skill.

fable-goal

Use when the user wants a /goal prompt rather than the build itself ('/fable-goal', 'turn this into a goal prompt', 'write the prompt that builds X'). Turns their ramble into one copy-paste prompt checked by goal_prompt_self_check.py.

fda-consultant-specialist

Use for FDA medical device questions: 510(k) vs De Novo vs PMA, predicates and substantial equivalence, QMSR (21 CFR 820), HIPAA or device cybersecurity. Runs fda_submission_tracker.py, qsr_compliance_checker.py and hipaa_risk_assessment.py.

fda-qsr-audit-prep

Use for /compliance-os:fda-qsr-audit-prep, or before an FDA inspection, QMSR internal audit or Form 483 response.

feature-flags-architect

Use before adding, rolling out or retiring a feature flag or kill switch, or when flag debt piles up. Plans the rollout with rollout_planner.py, finds stale flags with flag_debt_scanner.py and audits kill switches with kill_switch_audit.py.

finance-skills

Pick the right finance skill: ratios, DCF, forecasts (financial-analyst), ARR, churn, CAC, LTV (saas-metrics-coach), month-end-close. Use whenever a finance ask is vague.

financial-analyst

Analyze financial statements, value a company with a DCF, explain budget variance, build rolling forecasts. Use whenever the user asks what a business is worth or why spend missed budget.

fix

Diagnose and fix a failing or flaky Playwright test. Use whenever a test fails, passes only sometimes, breaks intermittently or needs fixing.

focused-fix

Use when a whole feature or module is broken and needs fixing end to end ('make X work', 'the Y module is broken'). Maps every file and dependency of the area before changing anything. Single quick bug fixes do not need it.

form-cro

Use when a lead, contact, demo or checkout form is underperforming or being designed, before changing fields. Scores field friction with form_field_analyzer.py. Signup forms: signup-flow-cro.

founder-coach

Use when a founder is the bottleneck, can't delegate, is burning out or is moving from IC to CEO. Covers delegation, energy and calendar audits, blind spots and succession.

founder-mode

Use for /c-level-agents:founder-mode, or any founder strategy question that hasn't been routed yet. Sends it to the right C-suite advisor or the boardroom.

free-tool-strategy

Use when considering a free calculator, grader, checker or generator as a marketing asset, before building it. Estimates traffic, leads and ROI with tool_roi_estimator.py and scores the idea for search demand and fit.

freeze

Use for /c-level-agents:freeze, or to put a cooling-off lock on an irreversible decision made under pressure.

full-page-screenshot

Use when asked for a full-page or long screenshot of a web page. Captures SPA scroll containers, lazy images and very tall pages through Chrome DevTools Protocol with no extra dependencies.

gc-review

Use for /c-level-agents:gc-review, or to challenge a term sheet, customer MSA, IP assignment or regulatory exposure before signing.

gcp-cloud-architect

Design, deploy and cut the cost of Google Cloud setups: Cloud Run, GKE, Functions, Cloud SQL, BigQuery, moving to GCP. Use whenever the user asks how to host or run something on GCP, why their GCP bill is high, or plans a GCP migration.

gdpr-audit-prep

Use for /compliance-os:gdpr-audit-prep, or before a GDPR review, post-breach audit or DPA investigation.

gdpr-dsgvo-expert

Use for GDPR or DSGVO work: scanning a codebase for privacy risks, writing a DPIA or tracking data subject requests against the Art. 12(3) deadline. Runs gdpr_compliance_checker.py, dpia_generator.py and data_subject_rights_tracker.py; final calls go to the DPO.

general-counsel-advisor

Legal review of contracts and term sheets (MSA, SaaS, NDA, DPA, employment), IP strategy and regulatory exposure (HIPAA, GDPR, FDA, fintech). Use whenever the user asks if a contract is risky or what to watch in a deal; not a substitute for licensed counsel.

generate

Use when asked to write Playwright or e2e tests for a page, component or feature ('write tests', 'add tests for', 'e2e test').

git-worktree-manager

Use when running several branches or agents in parallel on one repo. Creates worktrees with isolated ports and env via worktree_manager.py and removes stale ones with worktree_cleanup.py.

google-workspace-cli

Use for Google Workspace admin or automation from the gws CLI (Gmail, Drive, Sheets, Calendar, Docs, Chat, Tasks). Sets up auth with auth_setup_guide.py, diagnoses with gws_doctor.py, runs recipes with gws_recipe_runner.py and audits security with workspace_audit.py.

grade-iterate

Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds the outcome with outcome_builder.py, reads verdicts with verdict_reader.py and runs held-back evals from eval_scaffold.py.

grants

Use for any NIH funding question ('find grants for my research', 'which NIH institute'). Maps the idea to institutes, study sections and NOSIs via RePORTER, matches mechanisms with mechanism_matcher.py and writes a .docx strategy. NIH only.

grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

grill-with-docs

Use when a plan should be stress-tested against the project's own docs (CONTEXT.md glossary, docs/adr decisions), or the user says 'grill with docs'. Scans ADRs with adr_scanner.py and updates the docs inline as terms and decisions settle.

handoff

Compact the current conversation into a handoff document for another agent to pick up, referencing existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them. Use whenever the user wants to hand off to a fresh agent, is ending a session mid-task, asks for a handoff doc or a summary of state, decisions and next steps for the next session, or starts a new session that picks up prior work.

hard-call

Use for a decision where every option hurts (layoff vs down round, killing a loved product). Runs 10/10/10 and regret minimization.

helm-chart-builder

Use for any Helm chart to create, review or harden (values.yaml, templates, subcharts, RBAC, pod security), before editing it. Analyzes the chart with chart_analyzer.py and validates values with values_validator.py.

hivemind

Use when delegating grunt work to free opencode workers instead of spending Claude tokens: one worker or a scout, coder and tester swarm in worktrees. Triggers on 'spawn a worker', 'swarm', 'delegate to opencode' or /oc.

hub-init

Use for /hub-init, or to start an AgentHub competition: task, agent count and evaluation criteria.

hub-run

Use for /hub-run, or to run a whole AgentHub competition end to end: init, baseline, spawn, eval and merge.

hub-status

Use for /hub-status, or to check AgentHub agent progress, branches and DAG state.

human-gate

Use before shipping anything that needs human sign-off (a plan, spec, report, page, migration or irreversible action). Builds a review page with review_page_builder.py and runs human_gate.py, which refuses to close with an open blocker or no named reviewer.

i18n-localization

Use when adding UI text, adding or shipping a language, reviewing translation files, or building i18n into an app. Checks missing keys, placeholders and CLDR plural forms with locale_sync.py, finds hardcoded strings with hardcoded_strings.py, and builds a pseudo-locale with pseudo_localize.py.

inbox-setup

Use when setting up email triage for the first time, before inbox-triage, or when priorities change. Interviews the user one question at a time and writes the knowledge base inbox-triage reads, validated with kb_validator.py.

inbox-triage

Use when the user wants their inbox processed ('triage my inbox', 'check my email'). Classifies recent mail with the inbox-setup knowledge base, drafts replies it never sends (checked by draft_safety_validator.py) and reports.

incident-commander

Use when declaring or running a production incident or outage, or writing its post-incident review. Classifies severity with incident_classifier.py, rebuilds the timeline with timeline_reconstructor.py and drafts the PIR with pir_generator.py. Security incidents: incident-response.

incident-response

Handle a suspected security breach: triage, SEV1-SEV4 severity, escalation and forensic evidence, per NIST SP 800-61. Use whenever the user thinks they were hacked, sees suspicious activity or a leaked key. Outages: incident-commander.

information-security-manager-iso27001

Use when designing or running an ISO 27001 ISMS in HealthTech or MedTech: risk assessment, control implementation, certification or security incidents. Assesses risk with risk_assessment.py and checks controls with compliance_checker.py.

internal-narrative

Use when preparing an all-hands, investor update, recruiting pitch or crisis message, or when stories told to different audiences drift apart. Keeps one company story and flags contradictions.

interview

Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job and writes a build sheet with build_sheet_builder.py, checked by primitives_validator.py; no API key needed.

interview-mapper

Use when coding or making sense of one interview transcript (customer, JTBD, expert, usability, exit). Extracts verbatim-grounded nuggets with extract_nuggets.py, verifies quotes with verify_quotes.py and checks conclusions hold across reruns with consensus.py.

interview-system-designer

Use when designing a hiring loop, competency matrix, scoring rubric or question bank, or checking interviewer calibration. Plans the loop per role with interview_planner.py.

intl-expansion

Use when expanding to a new country: market selection, entry mode, localization, regulation and regional go-to-market.

isms-audit-expert

Use for ISO 27001 audit work: internal or surveillance audits, Annex A control evidence, Statement of Applicability, nonconformities, Stage 1 and 2 prep. Plans risk-based audits with isms_audit_scheduler.py.

iso13485-audit-prep

Use for /compliance-os:iso13485-audit-prep, or before an ISO 13485 internal audit or DHF closure.

iso27001-audit-prep

Use for /compliance-os:iso27001-audit-prep, or before an ISO 27001 internal, surveillance or stage 1 audit.

iso42001-specialist

Use for ISO/IEC 42001 AI management system work: gap analysis against Clauses 4-10, the AI risk register and Annex A controls, or the internal audit plan. Runs aims_gap_analyzer.py, ai_risk_register_builder.py and aims_audit_scheduler.py.

jira-expert

Jira setup and queries: JQL, workflows, custom fields, automation, dashboards. Use whenever the user needs a Jira search, filter, dashboard or rule set up, or a workflow fixed.

karpathy-coder

Check code against Karpathy's four principles: surface assumptions, keep it simple, change surgically, verify goals. Use whenever the user is about to commit, reviews a diff, or worries code is overbuilt or too complex; runs complexity_checker.py.

kubernetes-operator

Use when building a Kubernetes operator or CRD (controller-runtime, kubebuilder, operator-sdk, KOPF), before writing the controller. Validates CRDs with crd_validator.py, lints reconcile loops with reconcile_lint.py and scores OperatorHub capability level.

landing

Use when asked for a premium single-file HTML landing page with 3D CSS, GSAP scroll effects and parallax. Locks positioning in a short intake, validates the palette with brand_palette_validator.py and the output with html_validator.py.

landing-page-generator

Use when asked for a landing, marketing or campaign page as a Next.js TSX component with Tailwind. Scaffolds it with landing_page_scaffolder.py using PAS, AIDA or BAB copy, SEO meta and Core Web Vitals targets.