debug
Diagnose problems with an installed LlamaCloud release — pods crashing, services not reachable, login broken, parses failing, OCR queue stuck, etc. Use when…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Testing & quality
13,114 results
github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination
verify
Prove a RuView result is real — run the deterministic SHA-256 proof and the witness bundle (ADR-028), and lint any claim for MEASURED-vs-CLAIMED honesty.
endpoint-pentest
Authorized, conservative security assessment of the HTTP/API endpoints beside an MCP server. Covers route discovery, OpenAPI/Swagger leakage, auth bypass,…
cc-documentation-quality
Review documentation quality across README, comments, API docs, changelog, and AI documentation (CLAUDE.md, .cursorrules, copilot-instructions). Use when…
setup-ast
Configure tree-sitter CLI and language grammars for AST-powered code review. Use when AST extraction fails, tree-sitter not found, grammars missing, or setting…
ryux-visual-qa
RYUX Visual QA: did the build match the intended design: compare, list deviations, fix, render again. Load when something visual has been implemented and is…
release-check
Check whether a change is ready to release by reviewing diff, tests, docs, risks, and migration notes.
foundry-testing
Write Foundry-based tests and scripts. Trigger phrases - foundry testing, write test, fuzz test, fork test, invariant test, deploy script, gas benchmark,…
vitest-v4
This skill should be used when the user asks to "write tests", "add tests", "test coverage", "run tests", "debug failing tests", "mock functions", or mentions…
solana
This skill should be used when the user asks to "build a Solana program", "write Anchor code", "create a PDA", "work with SPL tokens", "test with…
github-quality
Evaluate GitHub repository quality and value through a three-layer assessment system (objective metrics, engineering quality, community reputation). Use this…
apple-ads
Run an Apple Ads account as a system — live delivery and market-position reads, one audited write path with a change ledger, always-on keyword testing with…
debug-finance
Use when debugging a wrong number, missing data, or unexpected analytics output in this project. Walks the project's specific failure modes (V1 vs V2…
testing
Writing tests for the B2C CLI project using Mocha, Chai, and MSW. Use when writing unit or integration tests, mocking HTTP requests with MSW, testing CLI…
bep-production-verification
Design, implement, run, or review production verification tests, post-deployment checks, production smoke tests, or another bounded verification profile…
bep-software-debugging
Diagnose a reproducible software defect, regression, intermittent failure, or unexplained performance change and identify its causal fix. Do not use for…
bep-software-testing
Design, implement, or review automated tests, regression proof, test-layer selection, contracts, migrations, integration boundaries, E2E journeys, fixtures, or…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing…
testing-strategy
Design automated tests that reduce uncertainty, cover real contracts, and avoid brittle coverage theater.
load-and-test
Rebuild CDS artifacts, reload SQLite fixture data, and run the full test suite. Use after schema or service changes.
test-discipline
Design assertions that prove the actual contract and fail on realistic regressions
chromium-local-smoke-tests
Pattern for always-on Chromium browser smoke coverage using a deterministic local Edge page plus a stable public-web slice
code-review
Review pull requests in mcp-windows for concrete bugs in MCP and CLI contracts, Windows UI automation, element identity, snapshots, bounded searches, and…