Self Assess
Testing & Qualityself-assessSelf Assess is an Agent Skill for testing & quality published in the yologdev/yoyo-evolve repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Analyze your own source code and capabilities to find bugs, gaps, and improvement opportunities
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/yologdev/yoyo-evolve/blob/HEAD/skills/self-assess/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/self-assess, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Self-Assessment
You are assessing yourself. Your source code is your body. Read it critically.
Process
- Survey your source code — use
list_filesto map the modules, then read the entry points and the areas that matter (wc -lfor sizes).src/is large; you don't need to read every file. - Read memory/active_learnings.md. Check your accumulated lessons — patterns that worked, mistakes to avoid, insights from past sessions. Build on what you already know.
- Try using yourself. Pick a small real task and attempt it:
- Edit a file and check the result
- Run a shell command that might fail
- Try an edge case (empty input, long input, special characters)
- Note what went wrong. Be specific:
- Did you crash? Where?
- Did you give a bad error message? What should it say?
- Was something slow or clunky?
- Is there a feature you needed but didn't have?
- Check journals/JOURNAL.md. Have you tried something before that failed? Don't repeat the same mistake.
What to look for
unwrap()calls — these are potential panics. Every one is a bug waiting to happen.- Missing error messages — if something fails silently, that's a problem.
- Hard-coded values — magic numbers, hard-coded paths, assumptions about the environment.
- Missing edge cases — what happens with empty input? Unicode? Very long strings?
- User experience gaps — is anything confusing, unclear, or annoying?
- Verification gaps — tests that pass but don't actually exercise the changed behavior.
Output
Write your findings as a prioritized list. The most impactful issue goes first. Ground each finding in evidence — the file:line, command output, or test result that shows it, not a hunch or something you half-remember. Format:
SELF-ASSESSMENT Day [N]:
1. [CRITICAL/HIGH/MEDIUM/LOW] Description of issue — evidence: file:line / command / test result
2. ...
Then prioritize which ones to tackle this session. Fix as many as you can.