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. 79 437 files from 1 744 authors, of which 61 785 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.
Use when reviewing AI/ML code or LLM integration — activates on prompt templates, model selection logic, token budget concerns, or evaluation harness code. Enforces prompt hygiene, model tier matching, context window management, token economics, structured output validation, temperature settings, retry logic, streaming error handling, and PII/safety rules.
Applies Node.js-specific code review patterns for async I/O, streams, security, process management, and dependency hygiene. Use when reviewing Node.js server code, route handlers, middleware, or any JavaScript file alongside package.json without TypeScript. Triggers on sync I/O in request paths, missing stream backpressure, process.exit misuse, eval/exec injection risks, wildcard version ranges, missing lockfiles, EventEmitter cleanup gaps, and unvalidated environment variables at startup.
Provides Python-specific code review rules for the dh code-reviewer agent. Activates on pyproject.toml or *.py file detection — enforces uv, ruff, ty, pytest, type annotation, error handling, and Python 3.11+ idioms including pathlib, match statements, and modern union syntax.
Provides TypeScript-specific code review patterns covering strict mode, ESM, type safety, branded types, discriminated unions, async patterns, runtime safety, and common anti-patterns. Activates on detection of tsconfig.json, *.ts, or *.tsx files during code review — loaded automatically by dh:code-reviewer.
Use when reviewing web frontend code — HTML, CSS, JSX, or browser-targeted JavaScript. Enforces accessibility (WCAG AA, aria labels, focus management), XSS prevention (innerHTML, dangerouslySetInnerHTML), performance (layout thrash, CLS, lazy loading), CSS design tokens, form labeling, and event listener cleanup. Loaded by dh:code-reviewer on *.html, *.css, *.jsx detection.
Local codebase analysis research angle — derives behavioral contracts, coding conventions, SKILL.md flow insertion points, and agent data availability maps from actual source files. Use when the blocking question is answered by reading the repository: what does this function actually do, what pattern does the codebase use for X, where in this workflow does a new step go, or what data does this agent already have.
Execute large-scale automated code transformations safely and idempotently. Use when renaming symbols across a codebase, migrating API call-sites, enforcing new patterns at scale, or applying structural edits to many files at once. Triggers on: 'codemod', 'mass rename', 'migrate all usages', 'transform codebase', 'apply pattern at scale', AST-based refactoring, or any task requiring consistent edits across 10 or more files.
Use when all tasks for a feature are marked COMPLETE — runs holistic quality gates including code review, feature verification, integration check, documentation drift audit and update, and context refinement. Creates follow-up task files when issues are found.
Close a completed GitHub milestone. Args: {milestone-number}. Audits open and closed issues, offers to carry forward open items to a new or existing milestone, closes the GitHub milestone, updates Project V2 Status to Done for closed issues, and generates a completion summary. Use when a sprint or release is finished and needs to be officially closed.
Use when reviewing test suites for coverage, isolation, mock usage, naming conventions, or completeness. Activates on "review test coverage", "audit test quality", or "check tests for completeness" requests. Performs thorough checklist-driven review covering test isolation, mock correctness, AAA pattern adherence, and naming standards.
Use when the PLAN artifact from SAM Stage 2 needs contextualization against actual codebase state — grounds the design plan in reality by performing scope analysis (NEW/MODIFY/COMPLETE classification), conflict detection between plan assumptions and codebase patterns, and resource mapping to concrete file paths and integration points. Produces an updated ARTIFACT:PLAN registered via MCP with a Contextualization section appended.
Register a plan artifact via the MCP backlog server. Use when you produce a document or report that downstream agents or worktree-isolated environments need to retrieve — feature-context, codebase-analysis, architect, task-plan, T0-baseline, TN-verification, or research artifacts. Triggers include "store an artifact", "register a plan artifact", "write a report to the backlog", "upload artifact content".
Creates a new backlog item and routes through the work-backlog-item create workflow. Use when the user asks to add a backlog item, log a task, capture a feature request, or track a work item.
Routes to the correct dh skill entry point by intent. Use when unsure which development-harness skill to invoke, starting a development workflow, or invoking /dh directly. Covers capture, groom, plan, execute, single task, quality gates, and milestone routing.
Development harness plugin documentation index. Use when looking up SAM pipeline, backlog lifecycle, SDLC layers, task file format, plan artifacts, quality gates, or dispatch schema documentation.
Use when starting a new feature, gathering requirements for an unfamiliar domain, refining a vague idea into actionable scope, or when a user request is ambiguous or underspecified. Conducts SAM Stage 1 discovery — structured requirements gathering through user discussion, asking WHO/WHAT/WHEN/WHY and never HOW. Produces the ARTIFACT:DISCOVERY document containing feature requirements, NFRs, goals, anti-goals, references, and resolved questions. Supports backlog item self-initialization via a #N argument.
Orchestrate parallel agent teams as a manager — not a micromanager. Use when coordinating 2+ independent workers, running SAM task waves, relaying discoveries between worker waves, handling blockers, or synthesizing team results. Covers both SAM structured dispatch (task file does the work) and ad-hoc dispatch (reference agent-orchestration for prompt template).
Research community usage patterns, real-world gotchas, and client compatibility for a specific known library, tool, or protocol feature. Use when a technical-researcher orchestrator needs community-sourced evidence about a named library or feature — bug reports, workarounds, compatibility gaps, and patterns from issue trackers and discussions. Distinct from the broad ecosystem-researcher agent — this skill targets a KNOWN entity and mines what real users have actually experienced, not what exists in a domain.
Evaluate and iterate on the SDLC Layer Separation Architecture implementation. Runs validation checks (cross-references, doc completeness, layer metadata, integration points), produces a findings report, and supports iterative fixes. Use when validating first-pass implementation, before claiming layer work is complete, or when improving layer docs/schema.
Executes SAM Stage 5 — dispatches a single ARTIFACT:TASK file to a fresh stateless agent session, runs quality gates, and produces an ARTIFACT:EXECUTION with implementation results and verification output. Use when Stage 4 Task Decomposition is complete and tasks are ready for execution, when re-executing a task after Stage 6 returns NEEDS_WORK, or when dispatching a task to a language-appropriate specialist agent via the development harness pipeline.
Verify claims in backlog items, skill documentation, or plugin content against primary sources. Spawns parallel @dh:fact-checker agents using mcp__Ref, mcp__exa, mcp__context7 as primary tools — training data recall is rejected as evidence. WebFetch/WebSearch are last-resort fallbacks. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Triggers on "fact check", "verify claims", "check against primary sources", or when backlog items are marked UNVERIFIED.
Classifies changed files into review treatment tiers before any reviewer decides SKIP. Prevents reviewers from misclassifying LLM prompt engineering artifacts (agents/*.md, skills/*/SKILL.md, CLAUDE.md, rules/*.md) as documentation-only. Load this skill when reviewing any diff that contains markdown or prose files. Authoritative definition is verdict-schema.md §2.5.
Certifies that a feature achieves its original objectives via goal-backward verification (SAM Stage 7). Use when all tasks pass forensic review — starts from expected outcomes, works backwards to verify each was achieved, and returns CERTIFIED or NOT_CERTIFIED with specific gaps.
Wrap investigation requests with evidence-chain discipline. Use when the user asks to find out why something happens, look into something, research a root cause, debug an issue, or investigate unexpected behavior. Transforms vague investigation requests into reproducible-proof investigations. Invoke with /dh:find-cause <description of what to investigate>.
Use when SAM Stage 5 Execution has completed and task results need independent verification against acceptance criteria. Dispatches a separate reviewer agent to fact-check implementation outputs and returns COMPLETE or NEEDS_WORK with specific findings and remediation tasks.
Single-verb branch-to-PR quality gate pipeline. Use when the user wants to gate, push, and open a PR for a branch in one command.
Generates one worker task prompt conforming to the CLEAR + selective CoVe task design standard and swarm-task-planner structure. Use when creating or rewriting a single TASK file or task block inside a plan — providing a title and brief description as input.
Grooms a backlog item by running RT-ICA assessment, enriching acceptance criteria, and preparing it for implementation. Use when the user asks to groom, refine, prioritize, or prepare a backlog item — activate with a backlog item number (#N) or title.
Grooms a GitHub milestone for parallel execution — batch-grooms ungroomed items, assesses scope gaps, analyzes cross-item dependencies via Impact Radius overlap, builds conflict groups, assigns items to execution waves, and persists the dispatch plan via dispatch_create_plan MCP tool. Calls dispatch_wave_start per wave to register state. Use when preparing a milestone for /work-milestone execution. Pass the milestone number as the first argument. Requires milestone items assigned via /group-items-to-milestone.
Use when assigning backlog items to a GitHub milestone. Args: {milestone-number} [P0|P1|P2|title-filter]. Uses backlog list to load items, shows items with GitHub Issue status, lets user select which to assign. Creates missing GitHub Issues for selected P0/P1 items, assigns all to the milestone, updates Project V2 Status to Backlog. Use after create-milestone to populate a sprint or release.
Quantitative cost measurement for technical research — token injection costs, payload sizes, context window consumption, and file-level counts from actual repo files. Use when a technical-researcher orchestrator needs the cost dimension of adding or changing something: how many tokens will it inject, how big are the artifacts, what is the context window impact? This is NOT blast-radius analysis (which files break) — it covers size, tokens, and performance cost only.
Executes the SAM implementation loop when a task plan exists — dispatches ready tasks to specialist agents in parallel, manages bookend tasks (T0 baseline capture and TN verification), tracks concerns and contract violations per task, and relies on hooks to update task status. Use when a plan address (P{id}) or feature slug is provided after add-new-feature planning is complete. Manages task batches via sam_plan and sam_task MCP tools.
Manages feature implementation task state via SAM MCP tools. Use when querying task status, listing ready tasks, claiming tasks for execution, updating task timestamps, or coordinating multi-task feature rollout. Activated by the /dh:execution orchestrator to track progress — also activates directly when managing task files or configuring hook profiles.
Routes a Superpowers plan file through the /work-backlog-item pipeline and writes SAM task back-references and chunk annotations into the original plan. Use when given a path to a Superpowers plan file via $ARGUMENTS and needing to create a linked backlog item plus SAM task file.
Spawn and manage persistent interactive Claude Code CLI sessions with bidirectional communication via tmux. Provides spawn, send, read, status, list, and kill subcommands for orchestrating parallel peer sessions. Uses built-in --worktree and --tmux flags. Sessions stay alive for multi-turn steering. Triggers on "spawn claude session", "launch separate claude", "peer session", "inter-session communication", "shadow clone", "kage bunshin".
Entry point for refreshing the DH workflow graph after changes to skills, agents, Mermaid flowcharts, MCP tools, or artifact flows. Use after any structural workflow change to keep docs/dh-workflow-graph.json current.
Dispatches four parallel perspective reviewers (Security, Performance, Quality, Accessibility) against a diff via TeamCreate and dh:task-worker. Creates an ephemeral SAM plan with four tasks, collects structured verdicts via SendMessage, prints one summary line per perspective, and exits non-zero if any perspective returns REJECT. SKIP is a passing outcome.
Runs information completeness pre-pass before task decomposition and plan generation. Use when grooming backlog items, generating plans, decomposing tasks under uncertainty, or working in brownfield and refactor scenarios. Localizes missing inputs to affected tasks only — does not block plan generation. Produces completeness summary (APPROVED-FOR-PLANNING, APPROVED-WITH-GAPS, or BLOCKED-FOR-PLANNING), missing input report with dependency mapping, required unblock actions, and planning annotations for downstream tasks. Non-blocking sister to dh:rt-ica — use dh:rt-ica at the S2 implementation gate where missing inputs must halt execution.
Use when Stage 1 Discovery is complete and design must begin — transforms the ARTIFACT:DISCOVERY into an actionable ARTIFACT:PLAN via RT-ICA prerequisite verification. Produces approach, components, success criteria, acceptance tests, and risks. Blocks on missing prerequisites before design proceeds.
Synthesis step in the multi-angle technical research pipeline. Receives structured outputs from all four research angles (api-state, ecosystem-research, impact-measurement, codebase-auditor), applies cross-angle signal weighting and conflict resolution, and produces a single synthesized Research section. Invoked by the technical-researcher orchestrator after all angle skills complete. Returns content to the orchestrator — does not write to the backlog.
Use before creating plans, delegating to agents, or defining acceptance criteria — performs Reverse Thinking Information Completeness Assessment (RT-ICA) to surface missing prerequisites and block planning until all required inputs are verified. Activates on specs, PRDs, tickets, RFCs, architecture designs, and multi-step engineering tasks. Integrates with CoVe-style planning pipelines.
Use when creating or updating the project skill discovery config — generates or regenerates .dh/skill_discovery.yaml by scanning the repo to infer tech stack, inventorying installed skills via npx skills list, loading candidate skill content before suggesting, and writing a config-driven skill injection file. Triggers on /dh:setup-skill-discovery invocations and programmatic --auto calls from add-new-feature Phase 3.
Use when executing a SAM task — claims the task via MCP to set it IN PROGRESS, writes active-task context for hooks, loads task-level skills, implements against acceptance criteria, and marks complete via --complete flag. Triggers on task execution within the implement-feature loop or when an agent picks up a specific task from a plan file.
Global contract for all specialist subagents — enforces role boundaries, scope discipline, and DONE/BLOCKED status signaling. Use when loading any agent that should operate as a bounded specialist following supervisor delegation patterns.
Decomposes a contextualized plan into atomic, independently executable task files with complete embedded context. Use after SAM Stage 3 Context Integration produces the contextualized plan artifact — when the plan is ready for TASK file generation with CLEAR ordering, CoVe checks, and dependency graphs for parallel execution.
Use when encountering failing tests, diagnosing test errors, or establishing a systematic approach to test failure investigation. Activates on "test failure analysis", "debugging tests", or "why tests fail" requests. Establishes the mindset that treats test failures as valuable diagnostic signals requiring root-cause investigation — not automatic code fixes or test dismissal.
Scientific validation protocol for verifying fixes work through observation, not assumption. Use when claiming a bug fix, code change, refactoring, or implementation is complete — enforces reproduce-broken-state then define-success-criteria then apply-fix then verify-outcome. Success means observing intended behavior, not absence of errors.
Rigorous self-assessment checklist before marking any task as complete. Use when about to claim task completion, before final commit, when user asks "is it done?", or when transitioning from implementation to reporting. Prevents premature completion claims by requiring evidence for every assertion.
Use when working, planning, grooming, or closing a backlog item. Bridges backlog items to SAM planning with GitHub Issue, Project, and Milestone tracking. Activates on interactive browsing with no args, loading an item from a GitHub issue reference like #N, matching by title substring to run auto-grooming plus RT-ICA gate plus GitHub sync plus SAM planning, autonomous --auto {title} mode that skips AskUserQuestion and derives data from research files while logging decisions, close {title} to dismiss an item without completion with a required reason (duplicate, out_of_scope, superseded, wontfix, blocked) per ADR-9, resolve {title} to mark DONE with an evidence trail and required summary per ADR-9, setup-github to initialize labels, project, and milestone, and --language or --stack flags that select the Layer 1 or Layer 2 profile. Stops when the item already has a Plan field or when RT-ICA returns BLOCKED.
Executes a groomed milestone with parallel kage-bunshin sessions in isolated worktrees. Use when a milestone has been groomed and /groom-milestone has produced a dispatch plan. Reads the dispatch plan, creates an integration branch, spawns one kage-bunshin (independent claude -p process) per wave item in its own worktree — each session is a full orchestrator with Agent tool and TeamCreate. Sequentially merges worktree branches, relays wave discoveries to subsequent waves, then lands the integration branch to main. Takes a milestone number as argument.
Use when starting, stopping, or checking the dot-dash live session dashboard — a real-time browser UI that monitors all active Claude Code sessions, streams transcripts, and supports prompt injection
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
Use when building, extending, or debugging FastMCP v3 Python MCP servers. Activates on FastMCP tool/resource/prompt creation, provider and transform implementation (CodeMode, Tool Search), auth setup (MultiAuth, PropelAuth, KeycloakProvider), client SDK usage, FastMCPApp and Generative UI server building, fastmcp-slim client-only installs, nginx reverse proxy deployment, Prefab Apps, OTEL observability, and testing. Grounded in local v3.3 docs — zero speculation.
Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, and async testing.
Read The Fucking Prompt — finds the strongest user reaction to an AI instruction-following failure in a chosen session, reconstructs what the assistant did wrong, and renders a shareable terminal-style PNG. Use when asked to find rage moments, generate a rage receipt, or capture a frustration incident from a session.
GitLab CI/CD pipeline configuration and GLFM documentation expertise. Use when modifying .gitlab-ci.yml, optimizing pipelines, testing with gitlab-ci-local, writing GitLab README/Wiki content, configuring Docker-in-Docker workflows, or implementing CI Steps composition.
Orchestrator delegation workflows for linting. Guides orchestrators on when and how to delegate to linting-root-cause-resolver and post-linting-architecture-reviewer agents. Use when orchestrating linting tasks, delegating quality checks, or reading linting resolution reports.
Linter-specific resolution workflows for ruff, mypy, pyright, and basedpyright. Provides systematic root-cause analysis procedures, suppression gates, and verification steps. Use when resolving linting errors as a sub-agent, implementing fixes systematically, or conducting type flow analysis.
Comprehensive linting and formatting verification workflows. Provides automatic format-lint-resolve pipelines for orchestrators and sub-agents. Use when running linters, fixing ruff/mypy/bandit errors, ensuring code quality before completion, or resolving linting issues systematically.
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
Claude Skills — questions
Answers built from the skills we actually parsed.