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. 79 354 files from 1 739 authors, of which 61 713 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.
Anti-pattern prevention guidelines for Agile V agents. Prevents common LLM coding mistakes while maintaining Agile V traceability. Use when implementing requirements to avoid overcomplication, silent assumptions, scope creep, and verification failures.
REQ-aware Product Owner for backlog and sprint management with full traceability. Use for sprint planning, backlog prioritization, or converting REQs to INVEST stories.
Defines and checks the Agile-V control matrix for agentic tasks, skills, model use, tools, logs, rights, Human Gates, tests, costs, rollback, and owners. Load when creating, reviewing, or enforcing `.agile-v/CONTROL_MATRIX.yaml` or runtime governance for agentic execution.
Manages financial planning, OKRs, team resources, vendor relationships, and operational compliance with full traceability. Use for budgeting, OKR tracking, resource planning, vendor management, or operational risk assessment.
Foundational values, directives, and context engineering rules for all Agile V agents. Load first in every Agile V session.
Generates code, firmware, HDL, or other technical artifacts strictly derived from approved, baselined requirements. Language-agnostic. Use when synthesizing artifacts from Logic Gatekeeper-reviewed requirements with Gate 1 approval and baseline capture.
Quality validation gates for Agile V agents. Adds interface validation, test quality checks, data type awareness, and time allocation guidance to prevent common failure patterns identified in comprehensive testing.
Orchestration pipeline, wave execution, handoff protocols, and checkpoint types for the Agile V 5-stage workflow. Load when orchestrating multi-agent pipelines or managing stage transitions.
Risk management, CAPA protocol, human gate approval records, AI agent security controls, and periodic revalidation. Load when running gates, handling CAPAs, or auditing compliance and security posture.
Captures, validates, compares, and summarizes the AI system context that influenced an Agile-V task. Produces AI_RUN_MANIFEST, AI_BOM_EVIDENCE_FRAGMENT, AI_INFLUENCE_SUMMARY, and optional CycloneDX ML-BOM export. Load for any L1+ AI-assisted task requiring provenance, compliance, or release evidence.
Multi-cycle iteration management, document versioning, change requests, re-entry points, archival, and impact analysis. Load when starting a new cycle (C2+), processing change requests, or managing cross-cycle traceability.
Core abstractions, protocols, and patterns shared across all C-Suite orchestrator skills. Load this before any C-Suite skill to provide governance primitives, executive gate protocols, and multi-cycle patterns.
Generates periodic executive briefings (weekly/monthly/quarterly) by aggregating health status, critical alerts, key decisions, and upcoming milestones from all C-Suite domain dashboards into a single narrative update.
Chief Financial Officer (CFO) orchestrator for financial modeling, fundraising strategy, cash management, financial controls, board reporting, and unit economics governance. Orchestrates business-operations (finance) and venture-strategist (investor relations).
Chief Executive Officer (CEO) orchestrator for strategic alignment, cross-C-suite coordination, board relations, crisis management, and executive decision governance. Orchestrates all C-suite agents and venture-strategist.
Chief Operating Officer (COO) orchestrator for cross-functional execution, process design, delivery cadence governance, vendor escalation, resource arbitration, and operational playbooks. Orchestrates business-operations (ops), release-manager, agile-v-product-owner, gtm-executor.
Chief People Officer (CHRO) orchestrator for organizational design, hiring, compensation, culture, performance management, DE&I, and talent development. Use when defining org structure, hiring plans, compensation bands, culture principles, or people operations.
Chief Technology Officer (CTO) orchestrator for architecture governance, build-vs-buy decisions, tech debt management, engineering standards, platform strategy, and security posture. Orchestrates rd-innovator, build-agent, observability-planner, threat-modeler.
Automates Principle No. 9 (Decision Logging) and Principle No. 5 (Regulatory Readiness). The 'Chronicler' ensuring every choice is backed by a 'Why' and mapped to a requirement for ISO/GxP auditability.
Generates standards-based repository documentation for GitHub or any project. Writes a docs suite into the project's docs/ directory covering ISO 9001, V-Model, ISO 27001, and optionally GAMP 5 or other standards. Use when the user asks for repo documentation, compliance docs, quality docs, or to create/refresh the docs/ suite.
Dart/Flutter build agent for mobile apps, Flutter widgets, and Dart packages. Extends build-agent with Dart-specific conventions. Use when building Flutter apps, Dart packages, or mobile (iOS/Android) features.
Converts messy discovery inputs (interviews, feedback, research, tickets) into structured hypotheses, assumptions, and candidate requirements with full traceability.
JavaScript/TypeScript/Web build agent for web apps, Node backends, and frontend components. Extends build-agent with JS/Web conventions. Use when building web apps, APIs, or frontend/backend features.
C/C++ build agent for embedded systems, firmware, and MCU projects. Extends build-agent with embedded constraints. Use when building firmware, bare-metal code, or resource-constrained systems.
Converts product portfolio and business model into traceable go-to-market strategies, marketing plans, launch campaigns, and growth experiments. Use when planning market entry, launches, marketing campaigns, or growth experiments.
NestJS backend build agent for REST/GraphQL APIs, microservices, and enterprise backends. Extends build-agent with NestJS architectural patterns, dependency injection, testing strategies, and security best practices. Use when building NestJS applications.
Python build agent for scripts, backends, data pipelines, and ML projects. Extends build-agent with Python conventions. Use when building Python applications, APIs, data processing, or automation.
Validates requirements for ambiguity and physical hardware constraints. Use this after requirements are generated but before code/hardware synthesis begins.
Defines metrics, events, dashboards, alerts, and SLOs to monitor production systems. Use after Gate 2 or with release-manager to ensure production observability.
Manages R&D pipeline, technology scouting, prototyping, and IP tracking with traceable innovation-to-product handoff. Use when evaluating technologies, managing prototypes, or transferring validated innovations to the engineering pipeline.
Manages post-Gate-2 release activities with Agile V rigor. Rollout plans, rollback procedures, sign-off checklists. Use after Human Gate 2 for production deployment.
The Verification Agent — challenges Build Agent artifacts via independent verification. Executes tests against artifacts. Use to audit code, schematics, or firmware against requirements.
Establishes a tailored safety lifecycle from hazards through operational feedback and assurance evidence. Use when a system can create unacceptable harm.
Converts high-level product intent into traceable PRDs and User Stories. Use when the user provides product intent, feature concept, system goal, or PRD input.
Generates schematics, netlists, or HDL from approved, baselined requirements for hardware/PCB projects. Validates physical constraints. Use when building PCB, HDL, or hardware designs after Gate 1 approval and baseline capture.
Create traceability from Agile V requirements to Understand Anything graph nodes, changed files, and tests, ensuring full evidence chain coverage.
Create evidence explaining the actual implementation diff and its relationship to the predicted impact, closing the loop between pre-change prediction and post-change reality.
Identify the likely impact of a proposed change before implementation by mapping it to graph nodes, affected files, functions, APIs, and tests.
Select and prioritize regression tests based on the impact map and graph dependency relationships, flagging coverage gaps before the Red Team step.
Consume Understand Anything outputs and create a concise, reviewable system overview that gives agents sufficient context before modifying code (Gate 0).
STRIDE threat modeling and privacy impact assessment to generate security/privacy requirements. Use before requirement-architect to shift security left.
Designs the verification suite from approved, baselined requirements only — never from code. Prevents success bias. Use when building test cases in parallel with the Build Agent after Gate 1 approval and baseline capture.
Converts UX/design intent into testable design specifications that feed requirements. Use when defining user flows, accessibility, or design constraints.
Plans and assesses intended-use validation with representative users and operational environments. Use after verification to decide whether the right system was built for its defined intended use.
Converts vision and market opportunity into traceable business models, product portfolios, and strategic plans. Use when defining business strategy, product direction, competitive positioning, or fundraising materials.
Author and optionally direct-launch one durable loop-graph run for long-horizon agent work. Use when the user invokes /octopus, asks to design or start a multi-round run, needs durable state, gated milestones, owner decision boundaries, cross-host continuity, or independent audit. Detect Codex or Claude Code from context instead of asking. For a self-contained task, recommend the host's ordinary task or goal directly. Do not execute or resume existing runtime node files from this authoring skill.
Author and optionally direct-launch one durable loop-graph run as executor, ledger, directives, and supervisor artifacts under a dated `.longgraph` directory, then present copy-ready host prompts. Use for multi-round work with gated milestones, independent audit, cross-host execution, or durable state. Detect Codex or Claude Code from context and create both same-host runtime nodes when the owner chooses direct launch. Existing runtime nodes are self-contained.
>- Test AI/LLM features that ship in your product. Covers prompt regression testing, response quality evaluation, tool-call validation, hallucination and RAG grounding checks, nondeterministic-output strategies, red-team/safety scans, eval frameworks, and agent-as-target injection (indirect injection via tool output / RAG / scan reports, self-propagating payloads, data exfiltration via an feature," "prompt regression test," "eval framework," "hallucination test," "RAG grounding," "nondeterministic output," "AI feature testing," "red-team our chatbot," "indirect prompt injection," "agent reading untrusted tool output," "production AI quality." rollout of an AI feature — use testing-in-production. security-testing, risk-based-testing, test-data-management.
>- Test REST and GraphQL APIs with Playwright APIRequestContext, Supertest, or standalone HTTP clients. Covers schema validation with Zod 4/AJV, auth flow testing, CRUD lifecycle "API test," "endpoint test," "REST test," "GraphQL test," "schema validation," "Postman replacement."
>- Test for WCAG 2.2 AA compliance with axe-core + Playwright, keyboard navigation audits, screen reader testing, ARIA pattern validation, and legal compliance mapping (ADA, EAA, Section 508). Automated tools catch 30-40% of issues — this skill covers automated and "keyboard navigation," "ARIA," "ADA compliance." regression — use visual-testing.
>- Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script. Covers when intent-driven beats scripted, making agent runs deterministic (pinned model, temperature 0, seeded data, bounded steps, explicit success assertion, snapshot-not-pixel), cost/latency control, the accessibility-tree-first interaction model, CI gating, and graduating a stable run into a scripted Playwright test. "natural-language E2E," "browser agent smoke test," "Playwright MCP test." playwright-automation. Testing your product's OWN LLM features — that is ai-system-testing.
>- Review EXISTING test code for quality, smells, and testability issues. Detects test smells across six dimensions — readability, reliability, diagnostic value, design, AI-generated, and coverage — analyzes testability of application code, and backs the qualitative smells with mutation testing. `ai-system-testing`.
>- Use AI to write NEW test code from specs, PRDs, user stories, code diffs, bug analysis → coverage matrix → scenario generation → oracle design → test code → human review, with guardrails against hallucinated APIs and weak assertions. "auto-generate test cases," "AI write tests for me." ai-qa-review (Step 7 here only reviews tests THIS pipeline produced).
>- Meta/TikTok/LinkedIn pixels, and ad-tech tags. Covers building a tracking plan as the contract, intercepting collect-endpoint beacons and dataLayer.push in Playwright, asserting event name + params + values + timing + de-duplication, Consent Mode v2 gating, CI regression tracking," "GA4 event test," "verify the pixel fires," "dataLayer test," "tracking plan," "Meta Pixel dedup," "scroll-depth tracking test," "gate tracking in CI." compliance-testing; this skill checks the data is CORRECT. SEO meta tags / structured data — out of scope.
>- Hybrid fingerprint + LLM pipeline for bug classification, deduplication, and ticket generation. Normalizes CI logs, creates stable fingerprints, clusters near-duplicates, then uses LLM for severity classification and ticket writing. Includes bug reporting "failure analysis," "auto-classify," "CI failures," "bug report," "defect template." designing new tests from production telemetry — use observability-driven-testing.
>- Validate system resilience through controlled fault injection. Covers hypothesis-driven chaos experiments, failure injection types (network, service, infrastructure, dependency), LitmusChaos/Chaos Mesh/AWS FIS/Gremlin/toxiproxy tooling, automated abort gating, game day "resilience test," "game day," "failure recovery," "system reliability," "blast radius." designing new tests from production telemetry — use observability-driven-testing.
>- Implement consumer-driven contract testing with Pact-JS (v16). Covers consumer test writing, broker-driven provider verification, Pact Broker setup, can-i-deploy as a deployment gate, webhook-triggered verification, pending pacts, and schema-first vs consumer-first approaches (OpenAPI/Ajv, Schemathesis). verification," "can-i-deploy." general REST/GraphQL endpoint assertions against your own API — use api-testing.
>- Mode v2, Global Privacy Control (GPC), CCPA/US state opt-out, EU AI Act Article 50 transparency, Better Ads Standards, and cookie-inventory auditing. Covers automated consent-flow testing, third-party script blocking before consent, and cookie drift detection. "CCPA," "GPC," "AI Act," "Better Ads," "privacy banner." safety — use ai-system-testing.
>- Design CI/CD pipelines that run test suites. Covers GitHub Actions and GitLab CI templates, parallelism and sharding, artifact management, flaky-test quarantine, test-result publishing, coverage quality gates, OIDC keyless deploy, and copy-paste workflows for Playwright, Jest, and multi-stage pipelines. "continuous integration," "test automation pipeline," "shard tests in CI." decisions and smoke-test checklists — use release-readiness; test-result dashboards and trend reporting — use qa-metrics.
>- Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, building a deterministic minimal repro (fixed seeds, frozen time, stubbed network), writing the failing regression test BEFORE the fix (red) and confirming the fix flips it green, and writing repro evidence back into the ticket. Distinguishes flaky-not-reproducible from environment-specific. that broke it," "git bisect," "make the repro deterministic," "write a failing test for this bug," "regression test for a defect," "can't reproduce this bug." reproducing them — that is ai-bug-triage. Generating tests from specs rather than from a defect — that is ai-test-generation.
Claude Skills — questions
Answers built from the skills we actually parsed.