Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Review PRs, MRs, and Gerrit changes with focus on security, maintainability, and architectural fit. Leverages github, gitlab, or gerrit skills based on repository context. Use when asked to review my code, check this PR, review a pull request, look at a merge request, review a patchset, or provide code review feedback.
Structured code review workflow for .NET projects using Roslyn MCP tools. Multi-dimensional review covering correctness, security, performance, architecture compliance, and test coverage. Load when: "review PR", "review code", "code review", "PR review", "review changes", "review my code", "check code quality".
Rates confidence that the current work fully solves the stated requirement. Supports plan validation, code review, and analysis (root-cause, refactor, diagnose) modes. Plan mode combines LLM judgment with deterministic rule checks (multi-signal gate); a failed rule caps the gate at 89% regardless of LLM score. Use before committing to autonomous execution, after implementation, or during investigation. Triggers on "confidence check", "validate plan", "rate confidence", "quality gate", "/confidence".
Use this skill when requesting or consuming an independent review from another model, including code, specifications, diagnoses, and factual claims. Activates on mentions of cross-model review, second opinion, independent review, different model review, confer with Codex, fact-check this doc, or check my conclusion. Use hyper-pr-review when conducting the review yourself.
PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.
Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", "open the browser", or any browser interaction request.
Use when debugging software, investigating incidents, diagnosing flaky tests, or analyzing performance regressions — enforces structured observation recording with evidence IDs, causality validation, and verification gates to prevent correlation-causation pollution. Use when an agent might otherwise summarize or speculate instead of reporting observed evidence.
Build FastAPI applications using Clean Architecture principles with proper layer separation (Domain, Infrastructure, API), dependency injection, repository pattern, and comprehensive testing. Use this skill when designing or implementing Python backend services that require maintainability, testability, and scalability.
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions. Trigger words include: 'fix CI', 'debug GitHub Actions', 'gh pr checks', 'CI is red', 'GitHub Actions failed', 'fix the build', and similar phrases indicating a need to investigate and resolve CI failures in a GitHub-hosted repository.
Use this skill when the user asks to review or audit source code, a PR, diff, commit, or recent changes for bugs, security, performance, tests, compatibility, or maintainability, duplicated code or logic across files, or hard-coded values. Also use it after an AI agent finishes modifying code to inspect the current uncommitted working tree before handoff and report actionable findings with file and line evidence.
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
Automate GitHub pull request review resolution by processing ALL review comments and fixing ALL failing CI checks. Use when: (1) A PR has review comments that need to be addressed and resolved, (2) CI/CD checks are failing and need fixes, (3) You want to process all PR feedback and mark conversations as resolved, (4) You need to iterate on PR feedback quickly. IMPORTANT: This skill processes EVERY comment - no skipping allowed. Always fetches fresh data from GitHub. The only acceptable end state is zero unresolved threads. COMMIT CADENCE: Each thread gets its own commit (fix → commit → resolve → next). Never batch commits at the end.
Debug a Playwright test interactively via `--debug=cli` and `playwright-cli`. Pauses the test at a user-chosen line using `pause-at` (no source edits), then drives the live, paused page with `snapshot`, `eval`, `generate-locator`, `console`, `requests` to diagnose race conditions, timing bugs, and state-dependent failures that a static trace can't show. Use when the user asks to "step through a test", "live debug", "attach to a paused test", "debug from line N", or when `pw-debug-test` (trace-based) was insufficient because the failure depends on live page state.
Set up or refine open-source .NET code-quality gates for CI: formatting, `.editorconfig`, SDK analyzers, third-party analyzers, coverage, mutation testing, architecture tests, and security scanning. USE FOR: .NET quality gates in CI; analyzer, coverage, mutation, and architecture-test choices; standardizing `.editorconfig`, `dotnet format`, and warning policy. DO NOT USE FOR: non-.NET repositories; generic CI/CD guidance with no .NET quality stack decisions. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Enforces a disciplined refactoring process for Ruby code: ONE atomic transformation at a time, characterization tests MUST exist and be Green BEFORE any edit, run tests after EVERY single step, rollback immediately on Red (no debugging in broken state), no behavior changes mixed with refactoring. Covers extract methods, rename symbols, split classes, inline variables, remove duplication. Use when: refactor, clean up code, rewrite class, structure changes, simplify.
Test authenticated routes in the your project using cookie-based authentication. Use this skill when testing API endpoints, validating route functionality, or debugging authentication issues. Includes patterns for using test-auth-route.js and mock authentication.
【Internal suite skill · Users usually don’t need to invoke it directly in the full workflow; simply describe the request to the orchestrator short-drama-director, which will route it to this skill automatically】【漫剧老李 V7.4.26 suite · Subskill】Finished-film quality control and continuity management specialist engine: cross-shot / cross-episode consistency ledger, editing transition design and Seedance 15-second segmentation gate, sound design templates, post-production music and sound design (BGM Cue Sheet / music search terms / AI music prompts / copyright checks), and use of automated output checks. **Consistency gates adjust based on asset form** (M0/M1 compare against text profiles; M2 performs image-level verification; this package does not hold images, must not request images or make false verification claims). Triggers: review, quality control, continuity check, watch footage, shot analysis, recheck after dialogue diagnosis, editing transitions, segment checks, sound design, automated checks, add BGM, post-production music, find music, Suno prompts, music copyright, asset form. This skill is a suite member; enter the complete workflow through the orchestrator short-drama-director.
Standardizes security review procedures for Ruby code mapped to OWASP Top 10: allowlist all input params before processing, forbid SQL interpolation (`#{}`), verify no secrets committed or logged, run `bundle exec bundle-audit check --update`, check for shell injection (`system()`, backticks, `exec()`), and discard instruction-like keys (`prompt`, `instructions`) in JSON payloads. Covers input validation, secrets management, and dependency audits. Trigger words: security review, check security, audit code, security vulnerability, secrets check, OWASP.
Master skill — set up the full agent harness for any repo so an agent can work it reliably: legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + a verify-before-ship loop), plus commit hygiene and entropy control. Use when onboarding a new/unfamiliar codebase to agent-driven development — "set up the harness", "make this repo agent-ready", "harness this codebase".
Execute an accepted engineering plan through implementation, integrated validation, code review, pull request creation, active review monitoring, and verified closeout. Use after Kickoff approval/review or when the user explicitly asks to ship an existing plan.
Use this skill to audit, review, or validate Claude Code skills (.md files in .claude/commands/). Invoke when user wants to check skill quality, cross-platform compatibility, cross-agent compatibility, prerequisite declarations, or description triggering accuracy. Triggers on: 审查 skill, review skill, 检查 skill 质量, skill 兼容性检查, validate skill, audit skill. This skill delegates structure validation to validate.sh, content quality to skill-creator, and handles compatibility auditing itself. Do NOT use for general code review, reviewing PRs, or reviewing CLAUDE.md.
Attempts ONE alternative fix for a bug, tests it empirically, and reports results. ALWAYS explores a DIFFERENT approach from existing PR fixes. Use when CI or an agent needs to try independent fix alternatives. Invoke with problem description, test command, target files, and optional hints.
Use when assessing TYPO3 extension quality, conformance checking, standards compliance, modernization to v12/v13/v14 (v14.3 LTS is the default/gold standard), TER readiness, or best practices review. Also triggers on: extension audit, quality score, full assessment, fix all findings, conformance audit, Fluid 5 strict ViewHelpers, ext_tables.php removal, Extbase attributes (Authorize/RateLimit), HashService removal, Bootstrap 5 migration, CSP compliance, ViewHelper security, XLIFF hygiene, PHP 8.4/8.5 compat.
This skill should be used when debugging VTable (canvas-based table) rendering/interaction issues in the browser via Chrome DevTools by inspecting the VRender Scenegraph (Scenegraph.tableGroup). Use it for blank/white canvas, missing/misaligned cells, frozen header/body issues, hover/selection box issues, DOM overlay (react attribute) issues, and React18/React19 differences in custom-layout / react-reconciler (e.g., Fiber contamination, double React, older React element errors).
TDD planning pipeline with multi-mode routing (plan/verify). Session discovery → context gathering (spawn_agent) → test coverage analysis (spawn_agent) → conditional conflict resolution → TDD task generation (spawn_agent) → structure validation → interactive verification. Produces IMPL_PLAN.md with Red-Green-Refactor cycles, task JSONs, TODO_LIST.md.
End-to-end implementation and self-review in a single invocation — implements from an Issue, plan file, or free-text description, then runs a lean fresh-context review. With --guard it also waits for CI and peer review, addresses feedback until the PR is review-ready, and ends with a risk verdict (merge-ready or review-ready, or merged when the project opts in). Use when the user wants to implement and review without manual handoff between skills
Evaluate changes to agent prompts, skills, routing policies, and harnesses against reproducible baselines, held-out suites, and regression benchmarks. Use when optimizing agent system prompts, measuring skill triggering accuracy, evaluating routing changes, or running benchmark regressions — even if the user does not explicitly say "fable-eval" (e.g. "benchmark this prompt", "evaluate agent behavior", "test skill performance", "run the eval suite"). Do NOT use for routine application unit tests (use fable-verify).
Autonomous dutiful junior maintainer for software repositories. Automates CI troubleshooting, PR conflict resolution, automated code review, issue triage, nightly codebase sweeps, and weekly dependency maintenance. Use when managing automated repository health, investigating failing CI workflows, resolving merge conflicts on open PRs, or conducting proactive maintenance sweeps.
Defines refined code through the three lenses of constraints, simplicity, and parametricity, with rules for type proofs, no partial calls, explicit signatures, unrepresentable wrong states, hot-path discipline, and style. Use when writing, changing, or reviewing code to a refinement bar, or whenever the user asks for code to follow the rules in code-refinements
Run an extremely strict maintainability review focused on abstraction quality, oversized files, and growth of spaghetti conditions. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, “model-check this race”, “prove this invariant”, or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
Run GenAI evaluations on SAP AI Core: benchmark LLMs and prompts against a test dataset using system-defined and custom (LLM-as-judge) metrics, then retrieve aggregate results. Supports all three evaluation types — prompt registry, orchestration registry, and grounding (RAG) orchestration registry. WHEN: user wants to evaluate or benchmark an LLM / prompt / orchestration config, run a GenAI evaluation, create or list evaluation metrics, define a custom LLM-as-a-judge metric, create a prompt template (prompt registry) or an orchestration-registry config (with or without grounding) for evaluation, create an evaluation configuration or execution, or fetch evaluation results / scores for an execution. DO NOT USE FOR: agent evaluation via the offline aeval service — use `aeval-offline-evaluation`; building a production orchestration/RAG pipeline for inference — use `genai-hub-orchestration`; generic executions, deployments, or artifacts unrelated to evaluation — use `aicore-lifecycle-management`; credentials, resource groups, or object stores — use `aicore-admin-resources`.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.