deft-directive-debug
100 / 100 · Low risk
Fine to try.
Systematic, evidence-based root-cause investigation. Use when the user asks "why did X break / slow down / regress?", wants to debug a failure, run a forensic investigation, or find the root cause of a bug -- to enter a sustained investigation MODE with a claim ledger, mandatory falsification before any conclusion, a chat answer-embargo until evidence closes, and a deterministic validator gate. Triggers: "debug", "root cause", "investigate", "why did X break", "why is X slow", "systematic debug…
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/'deft-directive-debug' ] || [ -L ~/.agents/skills/'deft-directive-debug' ]; then echo 'A skill folder named deft-directive-debug already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/deftai/directive' "$d" && git -C "$d" checkout --quiet 'd64615ee1074908fe26ebfc49eb766a3a0c18b06' -- 'content/skills/deft-directive-debug' && mkdir -p ~/.agents/skills && cp -R "$d"/'content/skills/deft-directive-debug' ~/.agents/skills/'deft-directive-debug' && 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/'deft-directive-debug' ~/.claude/skills/'deft-directive-debug' (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/deftai/directive/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | d64615e | 100 |
| 2026-11-09 | 164fe7a | 100 |