Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Scan .NET/C# code for performance anti-patterns (async, memory/strings, collections/LINQ, regex, serialization, I/O) with tiered severity, reporting findings without editing. Use when auditing hot paths, reviewing allocation-heavy code, or analyzing the API for optimization opportunities.
A specialized skill for creating and configuring xUnit test projects. Use when you need to create a test project, set up the project structure, configure NuGet packages, or organize test folders. Covers csproj configuration, package management, project structure, and xunit.runner.json configuration. Make sure to use this skill whenever the user mentions creating a test project, xUnit setup, project structure for tests, NuGet test packages, or csproj configuration for testing, even if they don't explicitly ask for project setup guidance. Keywords: xunit project, xunit setup, test project creation, test project setup, project structure, folder structure, xunit package, nuget packages, test packages, how to create a test project, xunit configuration
Analyzes errors, searches past solutions in memory, provides immediate fixes with code examples, and saves solutions for future reference. Use when user says "debug this", "fix this error", "why is this failing", or when error messages appear like TypeError, ECONNREFUSED, CORS, 404, 500, etc.
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite <target>".
Use before claiming anything works, is fixed, is done, or passes; before status updates on changes you haven't run; before agreeing with someone else's claim about your work; and before state-changing commands like restarts, deletes, or config edits.
Execute native agentic ethical penetration testing and automated security audits against staging or authorized application targets. Discovers API logic flaws, BOLA/IDOR vulnerabilities, missing authentication, sensitive file exposures, and security misconfigurations within bounded scope. Produces verified security findings with reproduction PoCs and automatic Fable remediation work cards.
Audit and certify repository merge and release readiness against required quality gates, clean git working trees, and verified distribution artifacts. Use when preparing a release tag, validating release checklist criteria, publishing npm/PyPI packages, or certifying a branch for merge — even if the user does not explicitly say "fable-release" (e.g. "prepare the release", "is this ready to merge", "ship to production", "publish the package"). Do NOT use when verification is stale, failing, or missing (use fable-verify first).
Independently review git diffs against requested specifications, architectural invariants, and code standards, grounding findings in evidence. Use when reviewing pull requests, inspecting code changes before merge, auditing diffs for regressions, or performing pre-commit sanity reviews—even if the user doesn't explicitly say "fable-review" (e.g. "review this diff", "check this PR", "critique my changes", "code review this branch"). Do NOT use to implement fixes directly (use fable-tdd/fable-execute) or run tests (use fable-verify).
Launch, manage, and verify live applications across CLI binaries, web servers, TUIs, Electron apps, and background daemons with readiness probes and clean teardown. Use when starting development servers, executing live smoke tests, testing interactive CLI binaries, or driving runtime smoke verification — even if the user does not explicitly say "fable-run" (e.g. "start the dev server", "launch the app", "test the running CLI", "smoke test the web app"). Do NOT use for static analysis or unit testing without a running process (use fable-verify).
Verify complex code changes against independent mathematical oracles, derived specifications, headless browser environments, and isolated sandbox states. Use when deriving independent verification oracles, testing algorithms against reference models, verifying UI with headless browsers, or testing state transitions in sandboxes — even if the user does not explicitly say "fable-simulator" (e.g. "simulate this workflow", "verify with an independent oracle", "headless browser check", "derive a test oracle"). Do NOT use for simple unit test runs (use fable-verify).
Drive testable behavior changes and bug fixes through disciplined red-green-refactor cycles with observable regression tests. Use when implementing new features with unit/integration tests, fixing reproducible bugs, modifying business logic, or writing test-first behavior contracts — even if the user does not explicitly say "fable-tdd" (e.g. "fix this bug test-first", "write a test and make it pass", "add this feature with tests", "TDD this logic"). Do NOT use for broad exploratory prototyping without clear assertions (use fable-discover or fable-plan) or for post-implementation reviews (use fable-review).
Falsify software implementations and gather fresh, machine-checked acceptance proof across tests, builds, typechecks, and runtime smoke checks before completion. Use when running test suites, checking type correctness, validating acceptance criteria, or verifying post-mutation code integrity — even if the user does not explicitly say "fable-verify" (e.g. "verify my changes", "run all tests and typecheck", "check if everything passes", "prove this works"). Do NOT use for planning (use fable-plan) or diff code review (use fable-review).
Runs a pre-handoff QA checklist on a Figma design before it goes to engineering. Use when asked to QA a Figma design, do a pre-handoff check, or validate a Figma file is ready to build. Produces a structured QA report covering file hygiene, component usage, accessibility, and handoff readiness with explicit pass/fail status per item. Optimised for Opus 4.7 and newer models.
FMC finish-work workflow: run bun run check, fix failures, commit with a user-facing English message by default, and only show a draft when the user clearly did not want a commit. Use for finish work, run checks, wrap up, land changes, or create commits.
Re-reads code you just wrote with fresh perspective to catch bugs, errors, and issues. Use after completing a feature, fixing a bug, or any code changes. Triggers on "review my code", "fresh eyes", "check for bugs", "did I miss anything", or "sanity check".
Keep iterating on code changes until the tests pass, the build succeeds, or linting is clean. Runs in a tight loop of fix → run → check → repeat. Use when you want the agent to autonomously grind through test failures or build errors.
Comprehensive Java development skill based on Alibaba Java Coding Guidelines (Songshan Edition). Use when writing, reviewing, or refactoring Java code to ensure compliance with industry best practices. Triggers on: (1) Writing new Java code (.java files), (2) Reviewing existing Java code, (3) Refactoring Java projects, (4) Database design with MySQL, (5) API design and implementation, (6) Unit testing, (7) Concurrent programming, (8) Security implementation, or any Java development tasks requiring adherence to coding standards.
INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response, single_step, trajectory, RAG), CLI management commands, SDK-based creation, and example management. Uses the langsmith CLI tool.
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.
Run linting and formatting checks. Use when user asks to "run linter", "/lint", "check linting", "fix lint errors", or requests code linting/formatting. Don't use for the full format/type/test pass (use /validate-code) or for installing commit-time hooks (use /setup-pre-commit).
Test and evaluate MCP server tools in the current Claude Code session. Use when auditing MCP configurations, validating tool quality, testing MCP servers end-to-end, generating test cases, checking tool descriptions and schemas, analyzing tool efficiency and redundancy, or debugging MCP integration issues. Covers tool discovery, quality analysis, test generation with AAA pattern, execution, rating, and cross-tool redundancy analysis.
Take a judge live on production traffic — create an Opik online evaluation rule (LLM-as-judge or Python metric) on a project with sampling, filters, variable mapping, and a cost cap, then confirm new traces are being scored. Works over the SDK's REST client; reads rules and score names via the MCP when connected. Returns the rule, the score name it emits, and how to watch it. Use for "score production traces", "monitor hallucinations in prod", "take this judge live", "set up an online evaluation rule", "alert me when quality drops". Not for offline experiments (use evaluate or compare) or for finding what is already broken (use diagnose).
Improve a prompt with the Opik Agent Optimizer — resolve the prompt, a dataset, and a metric, pick the algorithm, run a bounded optimization, check the gain on held-out data, and save the winner as a new prompt version with the optimization run link. Runs via the opik-optimizer package; reads prompts and datasets via the MCP when connected. Use for "optimize this prompt", "improve my system prompt", "make the agent answer better", "tune the prompt against my dataset", "run the prompt optimizer". Not for measuring quality once (use evaluate), before/after on a suite (use compare), or hand-editing a prompt without data.
Decide ship or hold for a candidate from the compare skill's numbers, against an explicit release policy — regressions, pass rate, safety-tagged cases, subgroup consistency, latency and cost budgets, flakiness, evidence size, and whether the judge is validated. Reads two experiments on an Opik test suite via the SDK (or the MCP when connected) and returns a verdict with every criterion shown pass/fail. Use for "is this safe to ship", "can I merge this", "go/no-go on this change", "gate this release", "should I roll this out". Not for producing the numbers (use compare), building an evaluation (use evaluate), or deploying anything
Review code and architectures against the OWASP Top 10:2025 — the ten most critical web application security risks. Use when: (1) reviewing code for security vulnerabilities, (2) auditing a feature or codebase against OWASP categories, (3) providing remediation guidance for identified vulnerabilities, (4) writing new code and needing secure coding patterns. Triggers: 'review for security', 'OWASP audit', 'check for vulnerabilities','security checklist', 'is this code secure', 'security review', 'fix vulnerability'.
Comprehensive pre-merge validation checklist for Python/React pull requests. Use before approving or merging any PR. Covers code quality checks (linting, formatting, type checking), test coverage requirements, documentation updates, migration safety, API contract compatibility, accessibility compliance, bundle size impact, and deployment readiness. Provides a systematic checklist that ensures nothing is missed before merge. Does NOT cover security review depth (use code-review-security).
Use when choosing the best first failing RSpec spec or vertical slice for a Ruby on Rails change. Covers request vs model vs service vs job vs engine spec selection, system spec escalation, smallest safe slice planning, and Rails-first TDD sequencing. Trigger words: where to start testing, what test to write first, RSpec, test-driven development, TDD, first failing test.
Write tests using React Native Testing Library (RNTL) v13 and v14 (`@testing-library/react-native`). Use when writing, reviewing, or fixing React Native component tests. Covers: render, screen, queries (getBy/getAllBy/queryBy/findBy), Jest matchers, userEvent, fireEvent, waitFor, and async patterns. Supports v13 (React 18, sync render) and v14 (React 19+, async render). Triggers on: test files for React Native components, RNTL imports, mentions of "testing library", "write tests", "component tests", or "RNTL".
Reviews a code change with three independent reviewers (bugs, the repo's written standards, the spec it came from), tries to disprove each finding, and reports only what holds. Applies chosen fixes to the user's own change; for anyone else's, writes suggestions and can post them as PR comments. Use when the user asks to review, check, or take a second look at a change: "review my changes", "review PR 285" or "!482", "review against DESIGN.md", "is this ready?", review-changes by name, or pasted review findings to handle. Not for whole-repo audits, PR descriptions, explaining a diff, or when the user names another review tool
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.