Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Compresses verbose responses by removing filler and framing to save 200-400 tokens. Use when responses feel bloated or context is filling fast.
Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Installs egregore watchdog daemon via launchd or systemd for autonomous relaunching. Use when setting up egregore on a new machine. Do not use on CI/CD runners.
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates. Use when running quality checks before a PR.
Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads.
Autonomous orchestrator for manifest work items through the development lifecycle. Use when running egregore to process a backlog automatically.
Removes the egregore watchdog daemon and its associated files. Use when stopping automated session relaunching or cleaning up egregore infrastructure.
Presents adaptive codebase challenge questions with multiple-choice and trace exercises. Use when testing contributor knowledge of the codebase.
Adds developer-authored annotations to the gauntlet knowledge base. Use when capturing tribal knowledge or rationale not visible in code.
Builds the gauntlet knowledge base from AST extraction and AI enrichment. Use when initializing or refreshing codebase knowledge for challenges.
Audits the DSA problem bank for coverage gaps and proposes new YAML entries. Use when refreshing the problem bank during update-plugins runs.
Builds or updates the code knowledge graph via tree-sitter AST and SQLite. Use when setting up the graph before search or blast-radius analysis.
Searches the code knowledge graph by function, class, or type using FTS5 full-text search. Use when locating code entities by name or qualified path.
Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening. Use when onboarding contributors.
Browse hookify rule catalog. Use when installing pre-built rules or browsing categories. Do not use when writing custom rules; use hookify:writing-rules.
Verifies a package exists before install, defending against hallucination and slopsquatting. Use when adding, recommending, or installing a package.
Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment. Use when reviewing or learning from agent-written code.
Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior. Use when adding safety guardrails or preventing specific commands.
Analyzes changesets with risk scoring, categorization by type and impact, and release note preparation. Use when extracting insights from raw change data.
Summarizes recent git changes for context recovery after session breaks. Use when resuming work after a gap or handing off to another session.
Ramps implementation ambition a notch only after the prior increment is understood. Use when building a feature you must understand, not just ship.
Scores backlog items with RICE/WSJF/Kano and files GitHub issues for top candidates. Use when triaging a roadmap or prioritizing features for a sprint.
Audits changes for additive bias and Iron Law compliance. Use when reviewing completed work before merging or after AI-assisted implementation.
Enforces validation and evidence before claiming work complete. Use before declaring implementation done, creating a PR, or submitting deliverables for review.
Applies anti-sycophancy checklist to override agreement bias. Use when analyzing contested claims or avoiding socially convenient but inaccurate conclusions.
Pre-implementation gate covering think-first, simplicity, surgical edits, and verifiable goals. Use when starting implementation to verify the approach.
Shapes agent behavior via instruction framing and style transfer. Use when composing dispatch prompts or writing skill instructions for parallel review agents.
Provides review-workflow scaffolding for context, evidence, and output. Use at the start of any detailed review to ensure consistent, comparable findings.
Scores feature worthiness and enforces branch-size limits against overengineering. Use when evaluating whether a feature belongs in the current scope or branch.
Formats review deliverables with consistent structure for comparable findings. Use when finalizing any review or analysis that must be shared or compared.
Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers. Use when designing or auditing enforcement mechanisms for project rules.
Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.
Provides sanitization guidelines for external content in skills and hooks. Use when loading GitHub Issues, PRs, WebFetch results, or any untrusted input.
Detects workflow failures and inefficient patterns then files GitHub issues. Use when a workflow step repeatedly fails or produces inconsistent output.
Provides auth patterns for API keys, OAuth, and token management. Use when implementing or reviewing service authentication and credential handling.
Contract for the project decision journal (tradeoffs and lessons-learned logs). Use when recording a decision, tradeoff, or lesson, or building a consumer hook.
Recovers broken agent state via crash recovery, context overflow, and merge conflict protocols. Use when an agent session fails or a worktree is corrupted.
Defines the contract for deferred-item capture across plugins. Use when building or validating a plugin's deferred-capture wrapper or adding source labels.
Converts documents and URLs to markdown via tiered fallback (MCP markitdown, native tools, user notice). Use when a skill must ingest PDF, DOCX, or URL content.
Detects git forge (GitHub/GitLab/Bitbucket) and maps CLI commands cross-platform. Use when writing skills that must run on any git hosting provider.
Provides weighted scoring, rubrics, and decision-threshold patterns. Use when designing quality gates, evaluation systems, or decision frameworks.
Provides error classification, recovery, and graceful-degradation patterns. Use when implementing error handling or debugging resilience failures in any skill.
Decides hand-vs-compiler for loop transforms (unrolling, SIMD, fusion, hoisting). Use when reviewing/authoring a hot loop or tempted to hand-optimize one.
Implements hub-and-spoke lazy loading to minimize token usage in large skills. Use when building multi-module skills that need conditional on-demand loading.
Enforces markdown line-wrap and structure rules for clean git diffs. Use when writing or editing any committed markdown documentation or skill file.
Provides standardized pytest config, reusable fixtures, and CI integration patterns. Use when setting up or auditing a Python plugin's test infrastructure.
Tracks quotas, monitors thresholds, and degrades gracefully for rate-limited APIs. Use when integrating external services that impose rate or cost limits.
Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL). Use when assessing action reversibility before committing to an approach.
Provides sem semantic-diff detection, install-on-first-use, and fallback patterns. Use when building skills that consume git diff output.
Registers external services with health checks, central config, and unified execution. Use when integrating multiple external services needing coordination.
Applies stewardship virtues (Care, Curiosity, Humility, Diligence) to plugin work. Use when authoring plugins or reviewing code quality.
Defines testing quality metrics, coverage thresholds, and anti-patterns. Use when establishing test gates or validating a test suite's coverage targets.
Audits dependency supply chains for bad versions, lockfile drift, and artifact integrity. Use when adding deps, handling incidents, or releasing a plugin.
Implements structured usage logging and audit trails for cost and session tracking. Use when adding audit trails, usage analytics, or cost tracking to a skill.
Scores agent actions by expected gain, cost, uncertainty, and redundancy. Use when deciding whether to dispatch an agent or invoke a tool.
Manages digital garden notes, link structures, and health metrics. Use when curating a knowledge base, pruning stale notes, or tracking content maturity.
Searches and navigates stored knowledge in memory palaces. Use when looking for previously stored information or cross-referencing concepts across palaces.
Processes external resources into stored knowledge with quality scoring and routing. Use when ingesting articles, papers, or docs into a memory palace.
> info gaps. Use when verifying session state or summary before handoff or compression.
Claude Skills — questions
Answers built from the skills we actually parsed.