skills/post-mortem/SKILL.md
Document a resolved bug or incident as a structured post-mortem. Captures root cause, what was tried, what fixed it, and lessons learned — committed locally for future reference.
npx skillsauth add RonanCodes/ronan-skills post-mortemInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
After resolving a tricky bug or incident, document what happened so you never debug the same thing twice. Creates a structured markdown file committed to the repo.
/post-mortem "stale closure in useEffect causing infinite re-renders"
/post-mortem "CI failing on arm64 — missing native dependency"
/post-mortem
If no argument is given, ask the user to describe the issue that was just resolved.
/debug-escape finds the root cause and the fix is appliedCollect information from the current session:
Check git history for supporting context:
git log --oneline -10 — recent commits related to the fixgit diff — what changed in the fixCreate the file at .post-mortems/<date>-<slug>.md where:
<date> is YYYY-MM-DD<slug> is a kebab-case summary (e.g. stale-closure-useeffect, ci-arm64-native-dep)Use this template:
# <Title>
**Date:** <YYYY-MM-DD>
**Time to resolve:** <approximate>
**Severity:** <low | medium | high | critical>
**Area:** <file path, module, or system area>
**Tags:** `bug/introduced/<slug>` → `bug/fixed/<slug>`
## Symptom
<What was observed — exact error messages, unexpected behavior, how it manifested>
## Root Cause
<What was actually wrong and why — be specific>
## What We Tried
1. <First attempt> — <why it didn't work>
2. <Second attempt> — <why it didn't work>
3. ...
## What Fixed It
<The actual fix — reference the commit if already committed>
```diff
<include the key diff if short enough>
### 3. Tag the Fix
Tag the fix commit so it's easy to find via `git tag -l "bug/*"`:
```bash
git tag bug/fixed/<slug> <fix-commit-hash>
If /debug-escape already tagged the introducing commit as bug/introduced/<slug>, reference both in the post-mortem. If the introducing commit wasn't tagged yet and you know which commit introduced the bug, tag it now:
git tag bug/introduced/<slug> <introducing-commit-hash>
The tag pair tells the full story: git log bug/introduced/<slug>..bug/fixed/<slug> shows everything between cause and cure.
Check if .post-mortems/ is gitignored. It should NOT be — these files are meant to be committed and shared with the team.
Stage and commit the post-mortem:
git add .post-mortems/<date>-<slug>.md
git commit -m "📝 docs: post-mortem — <short description>"
bug/fixed/<slug> — tag the introducing commit too if knowntesting
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".