postmortem-improve
100 / 100 · Low risk
Fine to try.
Run a postmortem → improve loop so LibrAgent sessions learn without dirtying project git. Capture evidence-backed failures, then apply a Top-1 update to `@harness/LESSONS.active.md` (app-local; injected into the system prompt) for behavioral defects, or route deterministic tool/code defects to a fix/bug task (never paper over with lessons). Works for solo sessions and org/teamwork. Use after incidents, repeated failures, mission retros, stuck KANBAN/Blocked items, or when the user asks for cont…
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.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'postmortem-improve' ] || [ -L ~/.agents/skills/'postmortem-improve' ]; then echo 'A skill folder named postmortem-improve already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/fritzprix/libr-agent' "$d" && git -C "$d" checkout --quiet '0679557c88a47a5b14b020b9785e0de95e0a1f94' -- 'src-tauri/bundled_skills/postmortem-improve' && mkdir -p ~/.agents/skills && cp -R "$d"/'src-tauri/bundled_skills/postmortem-improve' ~/.agents/skills/'postmortem-improve' && 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/'postmortem-improve' ~/.claude/skills/'postmortem-improve' (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/fritzprix/libr-agent/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-12 | 0679557 | 100 |