kyaulabs/prism/debug
- community
Checking that the SKILL.md file is still in the repository.
Use to reproduce a defect, test a causal hypothesis and fix the root cause through TDD.
Install
npx vskill@latest install kyaulabs/prism/debugSKILL.md
Debugging
Establish expected versus observed behavior. Read relevant code, logs and tests without opening credentials or exposing secret values. Reproduce the smallest useful failure and record the actual failing evidence.
Form a specific hypothesis, then test it with the smallest safe experiment. Use temporary local instrumentation when useful and within task scope. Changes to live production systems require appropriate authority; ordinary source edits within an authorized task do not need repeated approval. Never log secrets.
Add a failing regression test at the highest practical public boundary. Fix the cause, not merely the symptom; run the test and relevant broader checks. Remove owned temporary instrumentation, preserving unrelated changes. Review non-trivial fixes in the current session and commit verified work normally.
If evidence contradicts the hypothesis, revise it rather than stacking patches. Ask for direction when progress stalls or consequences exceed the authorized scope. Report uncertainties and tests that could not be run.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/prism-core/skills/debug/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kyaulabs/prism/debug)