Retrospective Codify

Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today's lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.

423 stars 6 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mizchi/skills --skill retrospective-codify
Manual install
git clone --depth 1 https://github.com/mizchi/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/retrospective-codify ~/.claude/skills/retrospective-codify

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Retrospective Codify

Toward the end of a task, extract the insight of "if only I had known this first, I would not have taken detours" and pin it down as one of: a static rule, a skill, or an always-on rule. Prioritize landing it in a reproducible form that does not rely on prompts.

## When to use

Invoke only on an explicit user request to extract or codify reusable lessons. The following describe suitable material after that request, not automatic triggers:

- Near task completion, when the requested retrospective has enough execution evidence
- When you arrived at the solution after trial and error (stuck on the first attempt, built a wrong hypothesis, burned time due to missing docs, etc.)
- When you might perform a similar task again in the future

When not to use:
- Simple tasks that passed on the first try (nothing to extract)
- Project-specific one-off handling (a commit message is enough)

## Workflow

1. **Pair failure with success**: From the current task, write out the following 3 points.
   - The first attempt (what you did / how it failed)
   - The final solution (what worked)
   - The bridging insight (why the first attempt did not get there)
2. **Verbalize "what you should have known first"**: Summarize the insight in 1-3 sentences. Write it not as retrospection but as an instruction to your future self (in imperative form: "do not do X" / "check Y first").
3. **Classify**: Decide the output destination following the decision table below.
Read the full skill on GitHub

Details

Skill name
retrospective-codify
Repository
mizchi/skills
Path
retrospective-codify/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Retrospective Codify skill do?

Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today's lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.

How do I install the Retrospective Codify skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizchi/skills --skill retrospective-codify. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Retrospective Codify popular?

It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.

Related skills

Actions CI Tuning

423

mizchi/skills

Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.

Testing & QA

AI Index

423

mizchi/skills

Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.

AI, LLMs & Agents

Apm Usage

423

mizchi/skills

Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.

DevOps & Cloud

Skill Finder

423

mizchi/skills

Use ONLY when the user explicitly asks to discover or evaluate a skill from OUTSIDE the curated catalog — e.g., "find a Stripe skill", "is there a skill for X?", "evaluate this candidate before adopting". Meta-skill, complementary to skill-selector: do NOT auto-invoke on routine apm-management, project-init, or catalog-resident requests. Cross-source survey across vetted registries (Anthropic official, claude-skill-registry, VoltAgent/awesome-agent-skills, ComposioHQ, Superpowers, GitHub topic) with a mandatory waxa-eval adoption gate.

AI, LLMs & Agents

Publish Agent Skill

423

mizchi/skills

Package, publish, verify and update an agent skill through a Claude Code plugin marketplace, APM or the npx skills CLI. Use when preparing skill distribution or diagnosing installation, missing resources and stale updates.

AI, LLMs & Agents

Waxa Eval

423

mizchi/skills

Use when iterating on a skill's prompt with the waxa CLI (https://github.com/mizchi/skills/tree/main/tools/waxa) — authoring scenarios, choosing graders, interpreting unclear-points, advancing a ledger, and judging convergence. Encodes the four-stage iteration pattern observed in real iter loops (structural fix → grader breadth → surface-form coverage → residual unclear) and the scenario-design pitfalls (blank-slate executor's network limit, prompt expectation explicitness, regex coverage of Japanese/English surface forms). Meta-skill: do NOT auto-invoke for routine skill edits; fires only whe

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.