compozy/agh.

agent-exploration

>-

agh

AGH runtime and contribution guide. Use for sessions, agents, native tools, skills, memory, network, tasks, capabilities, bundles, QA, docs, and repo work. Do not use for unrelated projects.

agh-cleanup-failure-paths

>-

agh-code-guidelines

>-

agh-contract-codegen-coship

Contract co-ship for AGH wire changes. Use when editing public DTOs, OpenAPI, JSON-RPC extension shapes, generated clients, or handler request/response semantics. Do not use for internal Go refactors or test-only changes that leave the wire contract unchanged.

agh-data-boundaries

Data-boundary audit for AGH route loaders, TanStack Query caches, paginated catalogs, filters, ordering, totals, live streams, workspace-scoped reads, and their backend APIs. Use when adding, changing, or debugging those paths. Don't use for presentational-only UI or backend work with no public read-model impact.

agh-design

AGH visual-design authority for production UI, static artifacts, prototypes, and reviews. Use when creating or reviewing an AGH surface or changing tokens, typography, spacing, depth, icons, or motion. Do not use for capture-only verification; use agh-ui-screenshot.

agh-qa-bootstrap

Bootstraps isolated AGH QA labs and emits the canonical manifest for downstream QA. Use when local QA needs daemon, workspace, provider, or playbook setup. Do not use for unit tests, planning-only work, or browser-only checks.

agh-schema-migration

Authors append-only Goose SQL migrations for AGH SQLite streams and keeps declarative schema sources, atlas.sum, Atlas checks, sqlc output, and migration tests synchronized. Use for SQLite table, column, index, constraint, trigger, or seed-data changes under internal/store or internal/memory. Do not use for in-memory structures, derived Markdown memory, or non-SQLite caches.

agh-test-conventions

>-

agh-ui-screenshot

Screenshot capture for deterministic PNG evidence and visual-contract bundles for AGH Storybook stories and local UI URLs. Use for visual audits, regression diffs, and design-parity checks. Do not use for interactive E2E flows, remote authenticated sites, or Storybook test execution.

agh-worktree-isolation

Isolates AGH runtime state for concurrent worktrees and QA runs. Use when another agent or runtime may share the machine, or when creating a parallel worktree. Do not use for single-worktree or build-only work.

ai-sdk

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, or tools, (2) Want to build AI agents, chatbots, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, etc.), streaming, tool calling, or structured output.

app-renderer-systems

Guides creation and modification of domain feature systems organized under a systems/ directory. Covers directory layout, API service layer patterns, TanStack Query hooks (queries, mutations, optimistic updates), React context and XState store conventions, hook organization, and public API barrel exports. Use when adding a new domain system, extending an existing one, or fixing bugs in a system-layer codebase. Don't use for generic React component work, backend API implementation, or codebases not organized around a systems/ domain pattern.

apply-comments

Apply pending @slide-comment markers written by the open-slide inspector tool. Use when the user asks to "apply comments", "process slide comments", "apply the inspector comments", or references markers left inside `slides/<id>/index.tsx`.

architectural-analysis

Architectural audit that hunts dead code, duplicated functionality, anti-patterns, type confusion, and code smells across a whole codebase. Use when the user asks for architectural analysis, to find dead or unused code, identify duplication, or assess codebase health. Don't use for style/formatting, performance profiling, security audits, or feature-level code review.

assistant-ui

Guide for assistant-ui library - AI chat UI components. Use when asking about architecture, debugging, or understanding the codebase.

assistant-ui-primitives

Guide for assistant-ui UI primitives - ThreadPrimitive, ComposerPrimitive, MessagePrimitive. Use when customizing chat UI components.

assistant-ui-runtime

Guide for assistant-ui runtime system and state management. Use when working with runtimes, accessing state, or managing thread/message data.

assistant-ui-streaming

Guide for assistant-stream package and streaming protocols. Use when implementing streaming backends, custom protocols, or debugging stream issues.

assistant-ui-tools

Guide for tool registration and tool UI in assistant-ui. Use when implementing LLM tools, tool call rendering, or human-in-the-loop patterns.

better-colors

OKLCH color space for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, and theme with Tailwind v4. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, hue drift, chroma, dark mode colors.

better-ui

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, image outlines, box shadows.

bubbletea

Build terminal user interfaces with Go and Bubbletea framework. Use when creating TUI apps with the Elm architecture, dual-pane layouts, accordion modes, mouse/keyboard handling, Lipgloss styling, and reusable components. Includes production-ready templates, effects library, and battle-tested layout patterns from real projects. Don't use for plain-text CLI scripts without an interactive UI, web/desktop GUIs, or non-Go terminal frameworks (Ink, Textual, Ratatui).

coderabbit-review-commit

Review exactly one commit with the CodeRabbit CLI in an isolated throwaway worktree.

combined

Skill with MCP and hook metadata

compozy

Explains Compozy capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Compozy, what commands are available, how the workflow pipeline works, or how to configure a workspace. Do not use for executing workflow steps — use the specific cy- skills instead.

consolidate-test-suites

Use when adding, moving, reviewing, or auditing tests in AGH to identify the invariant, owning layer, and canonical suite before changing coverage. Do not use as a replacement for framework-specific testing skills or final verification gates.

create-slide

Use this skill when the user wants to create, draft, author, or generate new slides / a presentation in this open-slide repo. Triggers on phrases like "make slides about X", "create a presentation", "draft slides for", "new slide", or when the user asks to add content under `slides/`. Do NOT use for editing the framework itself — only for authoring content inside `slides/<id>/`.

create-theme

Use this skill when the user wants to create, draft, author, or extract a slide theme in this open-slide repo. Triggers on phrases like "create a theme", "make a theme called X", "extract a theme from <slide>", "build a theme from these images". Produces a single markdown file under `themes/<id>.md` describing palette, typography, layout, fixed Title/Footer components, and motion philosophy. Do NOT use for editing slides themselves — only for authoring `themes/<id>.md`.

cy-create-prd

Creates a Product Requirements Document plus its companion user-story catalog (_user_stories.md) through interactive brainstorming with parallel codebase and web research. Use when starting a new feature or product, building a PRD, brainstorming requirements, or cataloging user stories and edge cases. Do not use for technical specifications, task breakdowns, or code implementation.

cy-create-tasks

Decomposes PRDs and TechSpecs into robust, independently implementable task files, assigning every test case from _tests.md to exactly one task and enriching tasks from codebase exploration. Use when a PRD or TechSpec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for PRD creation, TechSpec generation, or direct task execution.

cy-create-techspec

Creates a Technical Specification plus its companion test contract (_tests.md) by translating PRD business requirements into implementation designs through interactive technical clarification. Use when a PRD exists and needs a technical plan, when technical architecture decisions need documentation, or when a feature needs its exhaustive test-case catalog. Do not use for PRD creation, task breakdown, or direct code implementation.

cy-execute-task

Executes one PRD task end-to-end uninterrupted — resolves spec conflicts autonomously, implements, validates, and updates tracking without pausing for questions. Use when a prompt includes a task specification that must be implemented, validated, and reflected in task tracking files. Do not use for PR review batches, generic coding tasks without a PRD task file, or standalone verification-only work.

cy-final-verify

Enforces fresh verification evidence before any completion, fix, or passing claim, and before commits or PR creation. Use when an agent is about to report success, hand off work, or commit code. Do not use for early planning, brainstorming, or tasks that have not yet reached a concrete verification step.

cy-fix-reviews

Executes provider-agnostic PR review remediation using existing review round files under .compozy/tasks/<name>/reviews-NNN/. Use when resolving batched review issues, updating issue markdown files, implementing fixes, and verifying the result. Do not use for PRD task execution, review export/fetch, or generic coding tasks without review issue files.

cy-implement-spec

Spec-direct execution loop for Compozy specs — self-healing checkpoint driver that ships a spec end to end straight from its documents, no task decomposition: the spec's acceptance criteria become tracked exit conditions and the model works in long-running milestones cut by provability, one atomic commit each, then QA and deep-review peer-review rounds until SHIP. Use for continuous codex-loop goal runs over a .compozy/tasks/<slug> that has _techspec.md but no task graph, or when decomposition is deliberately skipped to keep the whole spec in one model context. Do not use for one-off tasks, PRD/TechSpec authoring, or a slug carrying an authored task graph (use cy-loop-tasks).

cy-loop-tasks

Task-graph execution loop for Compozy specs — self-healing checkpoint driver that ships a techspec end to end by executing its authored task graph (_tasks.md + task_NN.md), one atomic commit per Phase B task, QA, then deep-review peer-review rounds until SHIP. Use for continuous codex-loop goal runs over a .compozy/tasks/<slug> whose work is decomposed into task files, or with --frontend to delegate frontend tasks to herdr workers. Do not use for one-off tasks, PRD/TechSpec authoring, or a slug with spec documents but no task graph (use cy-implement-spec).

cy-research-issues

Runs a multi-agent research pass over the codebase (and optional competitor sources under .resources/) and converts the findings into an executable Compozy task suite: seven-section analysis documents, a lightweight _techspec.md, and task_NN.md issue files wired into a compozy.tasks/v2 _tasks.md graph, each carrying evidence, competitor references, and unit/integration/e2e test plans so cy-execute-task can run them directly. Use when auditing a subsystem, investigating a bug class, or turning improvement research into a runnable backlog without the interactive PRD/TechSpec ceremony. Do not use for PRD creation (use cy-create-prd), formal TechSpec authoring with ADR review gates (use cy-create-techspec), decomposing an already-approved spec (use cy-create-tasks), or executing the generated tasks (use cy-execute-task).

cy-review-round

Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with cy-fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.

cy-spec-peer-review

Cross-LLM peer review of a TechSpec via compozy exec — scoped Markdown findings for user-directed incorporation. Use when a TechSpec draft has already been approved and the user wants an external review round, especially for autonomy/network/memory-impacting designs. Do not use for PRDs, automatic approval gates, code review batches, or auto-looped review cycles.

cy-spec-preflight

>-

cy-tasks-tail-qa-pair

Appends a qa-report planning task and a qa-execution task at the end of every cy-create-tasks output, wired to the living docs/qa contract (scenario files, journeys, charters, bug registry, dated reports). Adds e2e coverage (Playwright or browser-use) for UI-bearing features. Use after cy-create-tasks finishes generating _tasks.md and the file lacks the trailing QA pair. Do not use for tasks generated outside the Compozy PRD pipeline, for ideation/brainstorming output, or for review-round task lists.

cy-web-docs-impact

>-

cy-workflow-memory

Maintains workflow-scoped task memory for Compozy runs using .compozy/tasks/<name>/memory/ files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across PRD task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.

deep-review

Deep review of branch diffs, working trees, or GitHub PRs at any size. Use when the user asks for CodeRabbit-grade review, an incremental re-review after new pushes, publication of findings to a PR, a cross-LLM peer-review verdict round, or conformance review against spec artifacts. Don't use for applying fixes, reviewing specs or PRDs as documents, or quick single-file feedback.

documentation-writer

Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

exa-web-search-free

Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key needed.

extreme-software-optimization

>-

fumadocs

Authoritative guide for the Fumadocs documentation framework — Core (headless), MDX (content loader), and UI (Tailwind v4 layouts and components). Use when scaffolding a Fumadocs project, editing source.config.ts, wiring loader() and meta.json conventions, picking a search adapter, composing DocsLayout/Notebook/Flux/Home layouts, customising the MDX component map, integrating OpenAPI specs, generating OG images, exporting PDF/EPUB/RSS, or configuring i18n across Next.js, React Router, TanStack Start, and Waku adapters. Surfaces canonical install snippets per adapter, decision tables for entry modes and content sources, and the most common pitfalls (Tailwind v3 silent failure, ESM-only config, .source/ generation, layout/page import mismatch, slug collisions, edge runtime ban). Don't use for generic MDX/Markdown questions outside Fumadocs, for unrelated React framework setup, or for projects that don't use fumadocs-core/fumadocs-mdx/fumadocs-ui.

git-rebase

Intelligently handle git rebase operations and resolve merge conflicts while preserving features and maintaining code quality. Use when rebasing feature branches, resolving conflicts across commits, and ensuring clean linear history without losing changes. Don't use for merge-commit workflows, cherry-picking individual commits, or initial repository setup.

herdr-orchestration

Orchestrate Claude and Codex worker TUIs from a controller agent through herdr panes and the herdr socket CLI. Use when delegating bounded tasks to herdr worker panes, running user-activated plan-first delegations (Claude Code plan mode, Codex Plan mode), waiting on native agent status (idle, working, blocked, done), or verifying worker reports. Workers launch as interactive TUIs via herdr agent start — never through headless runners (compozy exec, claude -p, codex exec). Not for cmux workspaces (see cmux-orchestration) and not for end-user herdr control.

hooks-only

Skill with hook metadata only

improve-react

Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead.

invalid-hook

Skill with invalid hook event

invalid-hook-command

Skill with missing hook command

invalid-mcp

Skill with invalid MCP server entries

lesson-learned

Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.

malformed-agh

Skill with malformed agh metadata

mcp-only

Skill with MCP metadata only

nats

|

next-best-practices

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

no-agh

Skill without agh metadata

no-workarounds

Fix problems at their root cause instead of patching symptoms. Use when debugging, fixing bugs, resolving test failures, planning a solution, or reviewing a change — especially where a fix would silence a signal (type assertion, lint suppression, swallowed error, timing hack, monkey patch) rather than repair its source. Not for formatting- or docs-only edits.

qa-execution

>-

qa-report

>-

real-scenario-qa

Dogfoods AGH through an autonomous startup scenario with live providers, cross-surface observation, and strict evidence audit. Use for release or complex-integration QA. Do not use for smoke, static, mock-only, or unit-test work.

refactoring-analysis

>

releasepr

Guides adoption and day-to-day use of the pr-release CLI in a consuming GitHub repository: installing the binary, wiring the release GitHub Actions workflow, authoring .pr-release.yaml, following conventional commits for semantic versioning, adding custom release notes with add-note, validating with dry-run, and understanding the release-PR then merge then production-release lifecycle. Use when a project depends on compozy/releasepr (pr-release) and needs to configure, run, or troubleshoot its release automation. Not for editing the pr-release Go source itself, and not a general changelog or semantic-versioning tutorial.

repository-orientation

Map an unfamiliar repository before changing it. Use when a task crosses packages, public contracts, persistence, runtime wiring, or verification lanes and the owning architecture is not yet clear.

ship-pr

Ships a finished feature, bug fix, or refactor end-to-end — explores the change's impact on docs/site/README, generates release notes (via pr-release if present, otherwise inline from git log), writes a complete PR description (including QA screenshots and summary when qa-report/qa-execution artifacts exist), commits staged changes following the repo's commitlint config, opens the PR via gh CLI, and optionally launches a CodeRabbit review watch loop. Use when a feature/bug/refactor is implementation-complete and ready to ship. Do not use for draft PRs without finished work, for amending an already-merged PR, for repo-level release publishing (use pr-release directly), or for in-progress development checkpoints.

skeeper

Explains how to use skeeper to keep spec artifacts (SPEC.md, ADRs, RFCs, plan/PRD/TechSpec markdown, custom globs) next to the code they describe without polluting main-repo history. Covers strict hooks, the tracked skeeper.lock file, namespaces, Git-like status/pull/push/sync/restore workflows, track/untrack, repair, SKEEPER_SKIP, and the GitHub Action. Use when setting up skeeper, configuring a sidecar, syncing or checking a lockfile, recovering drift or failed syncs, auditing bypasses, or wiring CI. Do not use for general Git hook questions, repos with no .skeeper.yml and no intent to add one, or editing skeeper internals.

slide-authoring

Technical reference for writing or editing open-slide pages — file contract, 1920×1080 canvas, type scale, layout, palette/visual direction, and assets. Consult this whenever you are about to write or modify any file under `slides/<id>/`, including from inside the `create-slide` or `apply-comments` workflows, or for any ad-hoc slide edit. Triggers on phrases like "edit slide", "tweak this page", "fix the layout", "change the palette", "investigate the slide framework", "how do slides work here".

storybook-stories

Create, update, or refactor Storybook stories following the project's standard patterns. Use this skill when adding stories for new components, updating existing stories, or fixing Storybook-related issues.

tailwindcss

Tailwind CSS v4 conventions — semantic design tokens for theme-safe styling, mobile-first responsive layouts, and v4-first utilities. Use when styling components or writing className utilities with Tailwind. Don't use for plain CSS, CSS-in-JS (styled-components, emotion), or other utility frameworks.

tanstack

TanStack Query, Router, and Form patterns for React. Use when writing useQuery/queryOptions, mutations, caching, file-based routes, search params, loaders, or TanStack Form validation. Don't use for TanStack Start, TanStack DB/collections, Zustand client state, or non-TanStack routing.

tech-logos

Install official tech brand logos from the Elements registry. Use when user needs logos for tech companies (Clerk, Vercel, GitHub, etc.), AI providers (OpenAI, Anthropic, Claude), social platforms, or any brand assets. Triggers on "logo", "brand", "icon for [company]", "add [company] logo", placeholder logo detection, or when building landing pages, auth UIs, or integrations showcases. Don't use for custom in-house logos, generic icon libraries (Lucide, Heroicons), or marketing image assets.

testing-boss

Testing doctrine for tests that reveal bugs instead of passing for the wrong reason — spanning software and LLM/AI systems. Use when authoring or reviewing tests, adding a mock, deciding where a test belongs, letting a coding agent generate tests, triaging flaky CI, designing an eval suite for an LLM/agent feature, or rebuilding a brittle suite. Not for general code review, library debugging unrelated to tests, CI pipeline design beyond tests, or production observability.

to-prompt

Turn code, issues, or context into a handoff brief for another LLM — full context, zero prescribed solution, written to docs/prompts/. Use when packaging a bug fix, an improvement, or a feature request for an external LLM to implement. Don't use for prompts that already prescribe an implementation, simple one-shot questions, or end-user-facing copy.

transitions-dev

Production-ready CSS transitions for web apps. Use when implementing notification badges, dropdowns, modals, panel reveals, page transitions, card resizes, number pop-ins, text swaps, icon swaps, success checks, avatar group hovers, error state shakes, search/input clear, skeleton loaders, shimmer text, sliding tabs, tooltips, staggered text reveals, card hover tilt, plus-to-menu morph, or accordions. Triggers on "add a transition", "animate the dropdown", "make the modal open smoothly", "swap icon", "page slide", "stagger animation", "open / close transition", "make it animate", "fade between", "success animation", "form error", "shake on invalid", "hover lift", "avatar stack hover", "clear the search", "skeleton loader", "loading shimmer", "shimmer text", "sliding tabs", "segmented control", "tooltip", "reveal text", "tilt card", "3D hover tilt", "cursor glare", "plus to menu", "FAB morph", "accordion", "collapsible", "expand / collapse", "disclosure", "replace this transition", "which transition fits here". Also the commands transitions reveal and transitions apply. For auditing or polishing existing motion against the motion-token scale ("motion tokens", "review my animations", "tune the durations", "align to the motion tokens"), use the companion transitions-polish skill.

transitions-polish

Polish and refine existing motion against the transitions.dev motion-token scale — duration, distance, scale, blur, and easing — plus the rules for WHEN each token applies (open/close asymmetry, hover-in vs hover-out, stagger offsets, and intent delays). An add-on to the transitions-dev skill, focused on tuning what already animates rather than adding new transitions. Use when the user asks to "polish my transitions", "refine the motion", "tune the timing / easing", "make the animation feel better / less janky", "tighten the durations", "fix the stagger", "align to the motion tokens", "audit the motion", "review my animations", "scan for ad-hoc transitions", "tokenize my animations", or runs the commands transitions review or transitions polish. Also drives the Refine panel's Small refinement feature. Triggers on "motion polish", "transition polish", "refine motion", "timing feels off", "too slow / too fast", "stagger", "delay", "open close timing", "hover in out".

typescript-advanced

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects. Don't use for plain JavaScript, runtime validation libraries (Zod, Yup), or basic TypeScript syntax questions.

web-prototype

|

writing-agents-md

Author lean AGENTS.md/CLAUDE.md instruction files — resident system-prompt context where every line pays rent. Use when writing an agent instruction file from scratch, auditing or trimming a bloated one, or gating whether a new rule earns residence and at which scope. Don't use for on-demand skills (use writing-skills) or human-facing docs and READMEs.

writing-tech-post

>-

zod

Zod schema validation best practices for type safety, parsing, and error handling. This skill should be used when defining z.object schemas, using z.string validations, safeParse, or z.infer. This skill does NOT cover React Hook Form integration patterns (use react-hook-form skill) or OpenAPI client generation (use orval skill).

zustand

Expert guide for Zustand state management patterns, store organization, and best practices. Use when implementing client state management with Zustand, creating stores, or managing shared UI state across components.