algo-stress-testing
Skill3 starsChanged 3 months agoNo licenceView on GitHub
Activate when a competitive-programming or AlgoJudge-style solution is failing hidden/system tests with a Wrong Answer (WA) verdict, an intermittent WA that only reproduces on certain inputs, or a Time Limit Exceeded (TLE) that appears solution-specific rather than universal. Trigger on explicit requests to 'stress test', 'differential test', 'fuzz test', 'random test', or 'compare against brute force'; on phrasings like 'my solution passes the samples but fails hidden tests', 'find a counterexample', 'find the smallest/minimal failing case', 'my AC-looking solution WAs on system tests', or 'this TLEs on some hidden input but I can't find which'. Also trigger when the working files include a fast/optimized solution (solution.cpp, sol.py, fast.py, main.cpp) that needs to be checked against a brute-force reference (brute.cpp, naive.py, slow.py) using a randomized test generator (gen.py, generator.cpp, gen.cpp). Do NOT activate for compile errors, runtime crashes with an obvious stack trace/exception, pure algorithm-design brainstorming with no implementation yet, or performance profiling that is unrelated to output correctness.
In this repository59 other files it gives its agents.
- ai-prompt-evaluatorSkill
- ai-rag-pipeline-architectSkill
- algo-complexity-analyzerSkill
- algo-edge-case-generatorSkill
- algo-plagiarism-detectorSkill
- algo-stress-testingSkill
- api-mock-generatorSkill
- backend-rest-api-designSkill
- campus-assignment-cleanerSkill
- campus-dsa-visualizerSkill
- campus-fyp-architectureSkill
- campus-git-team-workflowSkill
- campus-hackathon-fast-scaffoldSkill
- campus-ieee-citationSkill
- campus-lab-report-generatorSkill
- campus-presentation-scriptSkill
- ci-workflow-architectSkill
- database-migration-guardianSkill
- db-architectSkill
- devops-dockerfile-optimizerSkill
- devops-vercel-render-deploySkill
- docs-broken-link-checkerSkill
- env-syncSkill
- frontend-clean-uiSkill
- port-inspectorSkill
- react-state-architectureSkill
- repo-doctorSkill
- security-auditorSkill
- test-e2e-playwrightSkill
- test-unit-generatorSkill
- ai-prompt-evaluatorSkill
- ai-rag-pipeline-architectSkill
- algo-complexity-analyzerSkill
- algo-edge-case-generatorSkill
- algo-plagiarism-detectorSkill
- api-mock-generatorSkill
- backend-rest-api-designSkill
- campus-assignment-cleanerSkill
- campus-dsa-visualizerSkill
- campus-fyp-architectureSkill
- campus-git-team-workflowSkill
- campus-hackathon-fast-scaffoldSkill
- campus-ieee-citationSkill
- campus-lab-report-generatorSkill
- campus-presentation-scriptSkill
- ci-workflow-architectSkill
- database-migration-guardianSkill
- db-architectSkill
- devops-dockerfile-optimizerSkill
- devops-vercel-render-deploySkill
- docs-broken-link-checkerSkill
- env-syncSkill
- frontend-clean-uiSkill
- port-inspectorSkill
- react-state-architectureSkill
- repo-doctorSkill
- security-auditorSkill
- test-e2e-playwrightSkill
- test-unit-generatorSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.