diagnose
100 / 100 · Low risk
Fine to try.
Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regression wrong", "this number changed", "my script errors out", "the result won't reproduce", "debug this", "this estimate looks wrong", or "it worked yesterday". Tuned for research code (R/Stata/Python): type coercion, NA/merge blow-ups, factor levels, clustering/SE choices, weighting, collinearity/conv…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Other copies in this repository
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'diagnose' ] || [ -L ~/.agents/skills/'diagnose' ]; then echo 'A skill folder named diagnose already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/pedrohcgs/claude-code-my-workflow' "$d" && git -C "$d" checkout --quiet 'fe7077463c06e6d1572bb6c13d1b00525a4ff28e' -- '.agents/skills/diagnose' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/diagnose' ~/.agents/skills/'diagnose' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'diagnose' ~/.claude/skills/'diagnose' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/pedrohcgs/claude-code-my-workflow/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | fe70774 | 100 |
| 2026-11-07 | 58bed80 | 45 |