10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 406 ms
skillrohunj/claude-build-workflowrecord
- test-and-break
Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports. Use after deploying to staging. Triggers on: test the app, find bugs, QA the deployment, break the app, test staging.
- test-and-break
skillgithub/awesome-copilotrecord
- breakdown-test
Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projects.
- breakdown-test
skillcursor/pluginsrecord
- principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
- principle-test-behavior-not-implementation
skillanthropics/financial-servicesrecord
- break-trace
Root-cause a reconciliation break to its source transaction or posting — follow the audit trail from the break row back to the originating entry on each side and state what differs and why. Use after gl-recon has classified a break.
- break-trace
- 5break-uidemo or tutorialno passport yet
skillemilkowalski/skillsrecord
- break-ui
Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with t
- break-ui
- 6breakdemo or tutorialno passport yet
- break
Renders a component you choose under every scenario that can reach it on a temporary page and stress tests it.
- break
librarydanielfm/pybreakerrecord25,244,773 downloads/month
- breaker
skilladdyosmani/agent-skillsrecord
- debugging-and-error-recovery
Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root caus
- debugging-and-error-recovery
- 9codexskill-enhanceaimodelfound in code, not yet checkedno passport yet
MCP serverdeathgod89/codexskill-enhanceaimodel
- codex_break_assumptions
Assumption breaker: given a claim or analysis, surfaces hidden assumptions and generates counterexamples to test them.
- codex_break_assumptions
- 10socratesfound in code, not yet checkedno passport yet
- socrates_prove_tests
Mutation-test a file: break it on purpose and confirm the tests catch each break.
- socrates_prove_tests
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.