Browse Secure Claude Skills
Search verified agent skills and review security grades before installing · full A–Z index
- Audit TestsHunt untested and under-tested logic in whatever project this runs in and write meticulous, edge-case-exhaustive unit tests until coverage is total. Learns the project's stack, test runner, and house style first, measures real coverage (installing the tool if missing), triages every source file, then writes tests that match the existing suite and verifies them green. Use whenever the user wants to write or add unit tests, improve/increase test coverage, find untested code, hunt edge cases, ha...Votes: 0GitHub stars: 2
- Ci Suite AuditAudit registered CI test suites and recommend retention, split, nightly, quarantine, or turn-off verdicts based on runtime receipts, failure history, touch-set overlap, and prose/junk assertion analysis. Use when an operator asks to "audit test suites", "curate CI tests", "find slow tests", "identify redundant tests", "review test retention", "evaluate test gate health", or prepare the full-suite audit.Votes: 0GitHub stars: 5
- 3 COMPLETED| What was just completed | What's next | |---|---| | Five Markdown skills updated; Fable, GLM and targeted Sol QA Approved. | Publish ready PR against development; await review/merge. No installation. |Votes: 0GitHub stars: 5
- Task HygieneCleanup and triage of the task ledgers FOUND_DEFECTS.md, CURRENT_ERRORS.md, .matrx/AGENT_TASKS.md, .matrx/ARMAN_TASKS.md. Use when invoked as /task-hygiene <step>, cleaning up tasks, defects, or errors, triaging an error dump, promoting defects, or bootstrapping these files.Votes: 0GitHub stars: 3
- Subagent DispatchDelegating work down to subagents: briefs, report statuses, independent review. Use when writing an implementer or verifier brief, dispatching a subagent to build, fix, or verify work you own, or a subagent reports DONE, blocked, or concerns. NOT for campaign-scale doctrine (use campaign-pattern).Votes: 0GitHub stars: 3
- Safety NetReal tests around a big code change: written first, proven to fail on a planted break, run by a fresh agent in the live product before and after. Use when told to use safety-net, or before a change wide enough that one agent cannot see every way it breaks. NOT for one test (forcing-function-tests).Votes: 0GitHub stars: 3
- Plan AttackPre-commitment attack on a plan by an agent that did not write it. Use when presenting a feature-deep-dive plan, assigning vision-to-fleet briefs, moving a register to build mode, ratifying a scope list, or coding a new contract or table. NOT for built work or DONE reports (use subagent-dispatch).Votes: 0GitHub stars: 3
- Forcing Function TestsThe bar every automated test or guard must clear: green only when the real system works. Use when writing, fixing, or reviewing a test, mock, stub, fixture, snapshot, or self-test; adding a regression test for a bug; or about to call work done because tests pass.Votes: 0GitHub stars: 3
- Campaign PatternThe doctrine for turning a vision into a finished, verified, deployed system with near-zero owner involvement. Use when launching, coordinating, resuming, or working any large build, module, campaign, or multi-agent project, or when writing its launch prompt.Votes: 0GitHub stars: 3
- Security AuditReview security questions or vulnerabilities. Use the complete workflow only for explicit comprehensive audits, pen tests, or report requests.Votes: 0GitHub stars: 3
- Angular Testing Jest Angular Unit TestingWrite or review Angular tests in existing Jest projects, with narrow typed mocks, deterministic async behavior, and assertions that catch regressions.Votes: 0GitHub stars: 4
- Angular Testing Jest Angular Unit TestingWrite or review Angular tests in existing Jest projects, with narrow typed mocks, deterministic async behavior, and assertions that catch regressions.Votes: 0GitHub stars: 4
- PytestUse when writing Python tests with pytest - fixtures, parametrization, markers, conftest layout, pytest-asyncio, pytest-django, coverage with pytest-cov, mocking with pytest-mock, parallel runs with xdist, or CI integrationVotes: 0GitHub stars: 21
- ThreadingUse when handling PyQt/PySide6 threading - QThread patterns, QThreadPool/QRunnable, thread safety rules, moveToThread, Qt Concurrent, QTimer, testing threaded code, lifecycle managementVotes: 0GitHub stars: 21
- Playwright Visual RegressionUse when setting up visual regression testing with Playwright - toHaveScreenshot baselines, masking dynamic content, handling animations, full-page and element screenshots, cross-browser runs, CI integration, VUDA MCP tooling, or debugging flaky visual diffsVotes: 0GitHub stars: 21
- Django TddUse when testing Django applications with pytest - TDD workflow, pytest-django setup, factory_boy and model-bakery fixtures, DRF API testing, mocking and patching, integration tests, or coverageVotes: 0GitHub stars: 21
- Django HtmxUse when building dynamic Django web apps with htmx - partial rendering, HTMX responses, querystring tag, CSPVotes: 0GitHub stars: 21
- FixturesUse after sumo-qa-deciding-approach routes here, when the user asks "review my changes" / "is this safe to merge" / "what could break". Refuses to claim safe-to-merge without fresh verification evidence.Votes: 0GitHub stars: 7
- FixturesUse after sumo-qa-deciding-approach routes here, when the user asks "review my changes" / "is this safe to merge" / "what could break". Refuses to claim safe-to-merge without fresh verification evidence.Votes: 0GitHub stars: 7
- Code PurgeDeep code analysis and automated cleanup skill. Removes dead code, unused imports, unreferenced files, and duplicated logic from any codebase. Simplifies overly complex or hard-to-maintain code. Always backs up before changes and validates with tests after. Use when the user asks to: - "clean up", "remove dead code", "purge unused code" - "find and delete unused files/folders" - "remove duplicate code" or "refactor duplicated logic" - "simplify this codebase" or "the code is too complex" - "...Votes: 0GitHub stars: 214