Skills for Real Engineers. Straight from my .agents directory.
postmortem
Agent skill fromSethGammon/Citadel
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
How to install postmortem
npx skills add SethGammon/Citadel# or add only this skill to Claude Code: copy the folder
skills/postmortem/
# into
~/.claude/skills/postmortem/ (all projects)
.claude/skills/postmortem/ (one project)
1# /postmortem — Campaign Postmortem Generator23## Orientation45**Use when:** A campaign just completed and you want a structured analysis of what broke, what safety systems caught, and what patterns emerged. Also for ad-hoc incident analysis from recent git history.67**Don't use when:** You want to preserve session context for the next conversation (use `/session-handoff`), extract reusable patterns from findings into the knowledge base (use `/learn`), or score and improve quality iteratively (use `/improve`).89## When to Use1011- After any Archon campaign completes (Archon should suggest it)12- After a difficult debugging session13- When the user says "what just happened" or "what broke"14- When /do routes "postmortem", "retro", "what broke", "what happened"1516## Inputs1718One of:191. A campaign file path (.planning/campaigns/*.md)202. A time range ("last session", "today", "this week")213. Nothing (reads the most recent completed campaign)2223## Protocol2425### Step 1: GATHER2627Collect data from all available sources:2829**From the campaign file (if it exists):**30- Direction vs what was actually built (scope drift?)31- Phase completion timeline (which phases needed rework?)32- Decision log entries (what architectural choices were made?)33- Review queue items (what needed human eyes?)34- Circuit breaker activations (what hit the limit?)35- Feature ledger (what shipped?)3637**From telemetry (.planning/telemetry/):**38- hook-timing.jsonl: which hooks fired most, any patterns39…
Excerpt shown under the repository's MIT license.
More skills in Citadel
Similar skill repositories
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
