Browse Skills — Page 268
32,502 public skills · showing 26,701–26,800
- 100/100
skill-enabler
aaronjmars/aeon
Flip enabled:false → enabled:true for a comma-separated list of skill slugs in aeon.yml — validate against skills/, fail loudly on already-enabled or missing slugs, commit, open a PR with per-skill rationale
- 100/100
skill-epi-implement
benbrastmckie/nvim
Implementation skill for R-based epidemiology analysis. Invoke for epi/epi:study implementation tasks.
- 100/100
skill-epi-research
benbrastmckie/nvim
Research skill for epidemiology study design and analysis planning. Invoke for epi/epi:study research tasks.
- 100/100
skill-epidemiology-implementation
benbrastmckie/nvim
Implementation skill for R-based epidemiology analysis
- 100/100
skill-epidemiology-research
benbrastmckie/nvim
Research skill for epidemiology and study design
- 100/100
skill-eval
notque/vexjoy-agent
Evaluate skills: trigger testing, A/B benchmarks, structure validation, head-to-head bake-offs.
- 100/100
skill-evaluator
gotalab/skillport
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.
- 100/100
skill-evolution
yonatangross/orchestkit
Analyzes skill usage patterns and suggests improvements. Use when reviewing skill performance, applying auto-suggested changes, or rolling back versions.
- 100/100
skill-extractor
trailofbits/skills-curated
>-
- 100/100
skill-filetypes
benbrastmckie/nvim
File format conversion routing with specialized sub-agent dispatch
- 100/100
skill-filetypes-spreadsheet
benbrastmckie/nvim
Spreadsheet to table conversion routing
- 100/100
skill-finance
benbrastmckie/nvim
Financial analysis and verification for founders
- 100/100
skill-financial-analysis
benbrastmckie/nvim
Financial analysis with forcing questions and spreadsheet generation
- 100/100
skill-finder-cn
aAAaqwq/AGI-Super-Team
Skill 查找器 | Skill Finder. 帮助发现和安装 ClawHub Skills | Discover and install ClawHub Skills. 回答'有什么技能可以X'、'找一个技能' | Answers 'what skill can X', 'find a skill'. 触发词:找 skill、find skill、搜索 skill.
- 100/100
skill-fix-it
benbrastmckie/nvim
Scan codebase for FIX:/NOTE:/TODO:/QUESTION: tags and create structured tasks with interactive selection. Invoke for /fix-it command.
- 100/100
skill-forge
techygarg/lattice
Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions. Writing skill files manually almost always produces convention violations: wrong section order, missing confirmation gates, defaults.md without the right structure. This skill knows all of that and guides you through it. Use whenever adding any new atom, molecule, or refiner to Lattice, or when the user says 'create a new skill', 'add an atom', 'add a molecule', 'add a refiner', 'build X for Lattice', 'new lattice skill', or 'skill forge'. Does not validate, align docs, or deploy — those are separate skills you run after.
- 100/100
skill-formal-research
benbrastmckie/nvim
Coordinate formal reasoning research across logic, math, and physics domains. Invoke for formal-language research requiring cross-domain coordination.
- 100/100
skill-founder-implement
benbrastmckie/nvim
Execute founder plans and generate strategy reports
- 100/100
skill-founder-plan
benbrastmckie/nvim
Create founder analysis plans with interactive forcing questions
- 100/100
skill-founder-spreadsheet
benbrastmckie/nvim
Cost breakdown spreadsheet generation with forcing questions
- 100/100
skill-freshness
aaronjmars/aeon
Audit every enabled skill's upstream file dependencies for staleness — flags chained skills about to consume yesterday's article or a long-dead topic file
- 100/100
skill-frontmatter-doctor
Tibsfox/gsd-skill-creator
Use when authoring or reviewing a SKILL.md or agent .md and you need to detect and fix the four most common frontmatter defects — echoed or truncated triggers, tools written as a YAML array instead of a comma-separated string, a description outside the 1-1024 character bound, and a missing "Use when..." clause.
- 100/100
skill-funds
benbrastmckie/nvim
Funding landscape analysis with funder portfolio mapping. Invoke for funds tasks.
- 100/100
skill-generator
catlog22/Claude-Code-Workflow
Meta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and autonomous (stateless) phase patterns. Use for skill scaffolding, skill creation, or building new workflows. Triggers on "create skill", "new skill", "skill generator".
- 100/100
skill-git-workflow
benbrastmckie/nvim
Create scoped git commits for task operations. Invoke after task status changes or artifact creation.
- 100/100
skill-grant
benbrastmckie/nvim
Grant proposal research and drafting with funder analysis. Invoke for grant tasks.
- 60/100
skill-guard
UseAI-pro/openclaw-skills-security
Runtime security monitor for active OpenClaw skills. Watches file access, network calls, and shell commands.
- 100/100
skill-implementer
benbrastmckie/nvim
Execute general implementation tasks following a plan. Invoke for general implementation work.
- 100/100
skill-improve
striderZA/OpenCodeGameStudios
Improve a skill using a test-fix-retest loop. Runs static checks, proposes targeted fixes, rewrites the skill, re-tests, and keeps or reverts based on score change.
- 100/100
skill-improver
diegosouzapw/awesome-omni-skills
Skill Improvement Methodology workflow skill. Use this skill when the user needs Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improving a skill with multiple quality issues, iterating on a new skill until it meets standards, or automated fix-review cycles instead of manual editing and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
skill-improver
trailofbits/skills
Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes stop converging, and a mechanical scope guard. Reviews are performed by the plugin-dev skill-reviewer agent. Use to fix skill quality issues, iteratively refine a skill, or resume a loop after an escalation ('fix my skill', 'improve this skill until it passes review', 'skill improvement loop'). NOT for a one-time review — use the plugin-dev skill-reviewer agent directly.
- 100/100
skill-improver-v2
diegosouzapw/awesome-omni-skills
Skill Improvement Methodology workflow skill. Use this skill when the user needs Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improving a skill with multiple quality issues, iterating on a new skill until it meets standards, or automated fix-review cycles instead of manual editing and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
skill-index
yogsoth-ai/de-anthropocentric-research-engine
Full capability landscape of the DARE skill ecosystem — 823 skills across 8 research phases. Read this to understand what campaigns, strategies, tactics, and SOPs are available. Invoke this skill whenever you need to understand the complete arsenal before generating a Research Spec or routing a customized workflow.
- 100/100
skill-installation
uvwt/agentdock
审查、安装、配置、激活、验证、更新和回滚 AgentDock Skill 时使用;负责来源校验、安全评估、环境配置和已安装版本验收。
- 100/100
microsoft/skill-installer
microsoft/amplifier-bundle-work
Discover and install Amplifier-compatible skills from a local folder or Git repository into the requested project, personal directory, or bundle.
- 100/100
ComposioHQ/skill-installer
ComposioHQ/awesome-codex-skills
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
- 100/100
openai/skill-installer
openai/codex
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
- 60/100
anthropics/skill-installer
anthropics/claude-for-legal
>
- 100/100
skill-installer-v2
diegosouzapw/awesome-omni-skills
Skill Installer v3.0 workflow skill. Use this skill when the user needs Instala, valida, registra e verifica novas skills no ecossistema. 10 checks de seguranca, copia, registro no orchestrator e verificacao pos-instalacao and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
skill-installierer
Klotzkette/claude-fuer-deutsches-recht
Installiert einen Kanzlei-Skill aus einer überwachten Registry. Liest zuerst die Zulassungsliste, lädt die rohe SKILL.md vollständig herunter, führt Sicherheitsprüfungen und eine Qualitätskontrolle (skills-qualitaetspruefung) durch und schreibt Dateien erst nach ausdrücklicher Nutzerfreigabe. Lädt, wenn der Nutzer „Skill installieren [Name]\" eingibt, einen Skill aus dem Verzeichnis auswählt oder eine direkte Skill-URL übergibt.
- 100/100
skill-integration
Tibsfox/gsd-skill-creator
>
- 100/100
skill-iter-tune
catlog22/Claude-Code-Workflow
Iterative skill tuning via execute-evaluate-improve feedback loop. Uses ccw cli Claude to execute skill, Gemini to evaluate quality, and Agent to apply improvements. Iterates until quality threshold or max iterations. Triggers on "skill iter tune", "iterative skill tuning", "tune skill".
- 100/100
skill-judge
jjmartres/opencode
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
- 100/100
skill-lake-repair
benbrastmckie/nvim
Run Lean build with automatic error repair for missing cases, unused variables, and unused imports
- 100/100
skill-latex-implementation
benbrastmckie/nvim
Implement LaTeX documents. Invoke for LaTeX-language implementation tasks.
- 100/100
skill-latex-research
benbrastmckie/nvim
Research LaTeX documentation tasks. Invoke for LaTeX-language research.
- 100/100
skill-leaderboard
aaronjmars/aeon
Weekly ranking of which skills are most popular across CONFIGURED Aeon forks (excludes untouched templates)
- 100/100
skill-lean-implementation
benbrastmckie/nvim
Implement Lean 4 proofs and definitions using lean-lsp tools. Invoke for Lean-language implementation tasks.
- 100/100
skill-lean-research
benbrastmckie/nvim
Research Lean 4 and Mathlib for theorem proving tasks. Invoke for Lean-language research using LeanSearch, Loogle, and lean-lsp tools.
- 100/100
skill-lean-version
benbrastmckie/nvim
Manage Lean toolchain and Mathlib versions with backup, upgrade, and rollback support
- 100/100
skill-learn
benbrastmckie/nvim
Scan codebase for FIX:/NOTE:/TODO:/QUESTION: tags and create structured tasks with interactive selection. Invoke for /learn command.
- 100/100
skill-legal
benbrastmckie/nvim
Contract review and legal analysis for founders
- 100/100
skill-lifecycle-promotion
agentlas-ai/Agentlas-OS
Use when adding or auditing Agentlas skill lifecycle metadata, skill-registry.json, trial evidence, Curator promotion decisions, or first-class skill promotion gates.
- 100/100
skill-lint
cat-xierluo/legal-skills
Skill 格式审查工具,基于 SKILL-DEV-GUIDE.md 规范对技能进行合规性审计。本技能应在用户需要审查 skill 格式合规性、检查文档与代码一致性、识别冗余内容、生成技能审计报告时使用。不要用于:代码审查、功能测试、非 skill 项目。
- 100/100
skill-locations
remotion-dev/remotion
Document Remotion skill placement. Use when adding, moving, or editing Remotion skills to decide whether a skill belongs in .agents/skills as an internal skill or packages/skills as a public skill.
- 100/100
skill-logic-research
benbrastmckie/nvim
Research mathematical logic tasks using domain context and codebase exploration. Invoke for logic-language research involving modal logic, Kripke semantics, and related mathematical foundations.
- 100/100
skill-maintenance
ComposioHQ/composio
Create, update, validate, or reorganize repo-local Agent Skills under .agents/skills, including SKILL.md frontmatter, first-level references, compatibility symlinks, and validation scripts. Use only for skill-tree maintenance, skill taxonomy changes, or agent-guidance validation work.
- 100/100
skill-management
vellum-ai/vellum-assistant
Create and delete custom managed skills
- 100/100
skill-manager
cat-xierluo/legal-skills
管理 Claude Code Skills 和 Commands 的安装、同步、卸载和列表查看,支持从本地路径或 GitHub 仓库/子目录安装。本技能应在用户需要安装外部 skill/command、从 GitHub 仓库同步、批量安装本地目录、查看已安装的 items、或卸载不需要的 item 时使用。
- 100/100
skill-manager
anthropics/claude-for-legal
>
- 100/100
skill-map
PaulRBerg/agent-skills
Find skill installs and references across local files without scanning macOS protected home paths or obvious transcript, cache, dependency, and backup noise.
- 100/100
skill-market
benbrastmckie/nvim
Market sizing research with TAM/SAM/SOM framework
- 100/100
skill-math-research
benbrastmckie/nvim
Research mathematical tasks using domain context and codebase exploration. Invoke for math-language research involving algebra, lattice theory, order theory, topology, and category theory.
- 100/100
skill-meeting
benbrastmckie/nvim
Investor meeting note processing and CSV tracking
- 100/100
skill-memory
benbrastmckie/nvim
Memory vault management - create, search, classify, and index memories. Invoke for /learn command memory operations.
- 100/100
skill-meta
benbrastmckie/nvim
Interactive system builder. Invoke for /meta command to create tasks for .claude/ system changes.
- 100/100
skill-model-updater
bitwize-music-studio/claude-ai-music-skills
Updates model references across all skill files when new Claude models are released. Use when Anthropic releases new Claude models to keep skills current.
- 100/100
skill-monitor
oliver-kriska/claude-elixir-phoenix
Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.
- 80/100
skill-navigator
OneWave-AI/claude-skills
The 100th skill! Your intelligent guide to all 99 other skills. Recommends the perfect skill for any task, creates skill combinations, and helps you discover capabilities you didn't know you had.
- 100/100
skill-neovim-implementation
benbrastmckie/nvim
Implement Neovim configuration changes from plans. Invoke for neovim implementation tasks.
- 100/100
skill-neovim-research
benbrastmckie/nvim
Conduct Neovim configuration research using plugin docs and codebase exploration. Invoke for neovim research tasks.
- 100/100
skill-nix-implementation
benbrastmckie/nvim
Implement Nix configuration changes from plans. Invoke for nix implementation tasks.
- 100/100
skill-nix-research
benbrastmckie/nvim
Conduct Nix/NixOS/Home Manager research using MCP-NixOS, web docs, and codebase exploration. Invoke for nix research tasks.
- 100/100
skill-one
EveryInc/compound-engineering-plugin
Sample skill
- 100/100
skill-optimization
shinpr/ai-coding-project-boilerplate
Evaluates and optimizes skill file quality using 8 content patterns and 9 editing principles. Use when creating skills, refining skill content, or auditing skill quality.
- 100/100
skill-optimize
Fr-e-d/GAAI-framework
Run a structured evaluate-analyze-improve cycle on any GAAI skill to measure quality, detect regressions, and propose targeted improvements. Activate when a skill needs baseline evaluation, after SKILL.md modifications, or when friction-retrospective flags a skill.
- 100/100
skill-optimizer
rohitg00/pro-workflow
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
- 100/100
skill-orchestrate
benbrastmckie/nvim
Autonomous state machine that drives a task through its full lifecycle (research -> plan -> implement -> complete) without user confirmation between phases. Invoke for /orchestrate command.
- 100/100
skill-orchestrator
benbrastmckie/nvim
Route commands to appropriate workflows based on task type and status. Invoke when executing /task, /research, /plan, /implement commands.
- 100/100
skill-perfection
OmidZamani/dspy-skills
Use this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying skill content against official documentation, fixing issues in-place, and producing verification reports.
- 100/100
skill-physics-research
benbrastmckie/nvim
Research physics formalization tasks using domain context and codebase exploration. Invoke for physics-language research involving dynamical systems, chaos theory, and related formalization.
- 100/100
skill-planner
benbrastmckie/nvim
Create phased implementation plans from research findings. Invoke when a task needs an implementation plan.
- 100/100
skill-presentation
benbrastmckie/nvim
Presentation extraction and slide generation routing
- 100/100
skill-progressive-disclosure-design
samber/cc-skills
Decide how to split skill content between SKILL.md and reference files for context efficiency and reliable triggering. Use this whenever creating a new Claude skill, refactoring an existing one, or when a SKILL.md is growing past 300-400 lines. Also trigger when the user mentions "progressive disclosure", "reference files", "splitting skills", "skill bundling", "context window for skills", "SKILL.md too long", "what goes in references/", "skill structure", or expresses any uncertainty about where to put content within a skill. Use this even if the user phrases the question as a triggering problem ("how do I make my skill trigger better"), because that question is often confused with the splitting question and needs to be disentangled first.
- 100/100
skill-project
benbrastmckie/nvim
Project research with scope analysis and timeline estimation
- 100/100
skill-project-overview
benbrastmckie/nvim
Interactive repository analysis and project-overview.md generation via task creation. Invoke for /project-overview command.
- 100/100
skill-python-implementation
benbrastmckie/nvim
Implement Python code. Invoke for Python-language implementation tasks.
- 100/100
skill-python-research
benbrastmckie/nvim
Research Python development tasks. Invoke for Python-language research.
- 100/100
skill-rails-upgrade
benjaminasterA/antigravity-awesome-skills
Analyze Rails apps and provide upgrade assessments
- 100/100
skill-rails-upgrade-v2
diegosouzapw/awesome-omni-skills
Rails Upgrade Analyzer workflow skill. Use this skill when the user needs Analyze Rails apps and provide upgrade assessments and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
skill-refresh
benbrastmckie/nvim
Manage Claude Code resources - terminate orphaned processes and clean up ~/.claude/ directory
- 100/100
skill-researcher
benbrastmckie/nvim
Conduct general research using web search, documentation, and codebase exploration. Invoke for general research tasks.
- 100/100
skill-retro
alirezarezvani/claude-skills
Use when the user wants their skills graded from real session history, asks which installed skills actually work, or wants evidence-backed skill edits. Collects local sessions with collect_sessions.py, scores them against two rubrics and gates edits with score_aggregator.py.
- 100/100
skill-review
techygarg/lattice
Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then merges only the high-confidence, practical findings into a severity-ordered gap report with proposed fixes. Structural validation (conventions, cross-references) is skill-validate's job — this skill finds gaps that would realistically surface when someone actually uses the skill: missing scenario handling, ambiguous instructions, silent failure cases, and behavioral inconsistencies. Filters out theoretical edge cases, low-likelihood speculation, and findings owned by other skills. Use after writing or significantly changing any skill, or when the user says 'review this skill', 'deep review', 'does this skill work', 'find gaps in this skill', 'stress test this skill', 'review from different angles', or 'skill review'. Standalone — does not call other skills.
- 100/100
skill-reviewer
daymade/claude-code-skills
Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills.
- 100/100
skill-reviewer
microsoft/GitHub-Copilot-for-Azure
Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions. WHEN: \"review skill\", \"review skill PR\", \"review skill changes\", \"check skill quality\", \"skill PR feedback\".
- 100/100
skill-reviser
benbrastmckie/nvim
Thin wrapper that delegates plan revision to reviser-agent subagent. Invoke for /revise command.
- 100/100
skill-router
rohitg00/pro-workflow
The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".
- 100/100
skill-router-v2
diegosouzapw/awesome-omni-skills
Skill Router workflow skill. Use this skill when the user needs the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
skill-scout
affaan-m/ECC
Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
Page 268 of 326