New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Retrospective Codify

by mizchi in mizchi/skills

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.

No licenceAuto-check passedProduct & Project Management

Install Retrospective Codify

skills CLI
$ npx skills add mizchi/skills --skill retrospective-codify -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mizchi/skills retrospective-codify --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mizchi/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/retrospective-codify .claude/skills/retrospective-codify && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
retrospective-codify
GitHub stars
356
Token cost
~3.2k tokens
SKILL.md length
1,322 words
Files
3
Skills in repo
69
Repo updated
First seen
Licence
None found

At a glance

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.

  • Works in 6 steps: Pair failure with success: From the… → Verbalize "what you should have known… → Classify: Decide the output destination… → …
  • Explicitly says codify todays lessons
  • SKILL.md covers When to use, Workflow, Classification decision and Output templates, plus 5 more sections
  • Calls pnpm

What it does

Retrospective Codify is an agent skill from mizchi/skills. 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.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `README.md` and `SKILL-ja.md`).

It sits in Product & Project Management, covering Retrospectives and Agent instruction files. The repository describes itself as: Agent skills by mizchi, distributed via APM.

When your agent uses it

  • Explicitly says codify todays lessons
  • Make it a skill
  • Drop it into lint
  • Asks to extract a reusable rule from a trial-and-error fix

Example prompts

  • “what failed first”
  • “what finally worked”
  • “codify today”
  • “/retrospective-codify”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Pair failure with success: From the current task, write out the following 3 points.
  2. Verbalize "what you should have known first": Summarize the insight in 1-3 sentences. Write it not as retrospection but as an instruction…
  3. Classify: Decide the output destination following the decision table below.
  4. Dedup check (mandatory): Before proposing, cross-check against existing knowledge. If a duplicate or nearby rule exists, choose "append to…
  5. Write out: Generate the artifact following the template (below) for the chosen format.
  6. Confirm: Show the diff to the user and get approval. If rejected, keep it as a session note instead of a skill.

What it can do on your machine

Read from SKILL.md and the folder at commit 62f5808. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Retrospective Codify loads about 3.2k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 1,322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,322 words (~3,170 tokens).

“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…”

— opening of SKILL.md by mizchi
name
retrospective-codify

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files in retrospective-codify of mizchi/skills.

  • SKILL.md
  • README.md
  • SKILL-ja.md

Open the folder on GitHubat commit 62f5808

Compare with similar skills

Retrospective Codify next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Retrospective Codify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retrospective Codify this skillmizchi/skills356—~3.2kAutomated safety check: PassNone
Feature LifecycleInebrio/Routerly100—~3kAutomated safety check: PassAGPL-3.0
Codex Retrospectivemajiayu000/spellbook286—~1.6kAutomated safety check: PassMIT
Living Docs Governanceqshanx/docs-governance132—~4.1kAutomated safety check: PassMIT
Skill Retrokenneth-liao/ai-launchpad-marketplace126—~2.1kAutomated safety check: PassNone
Refit Environment RetrospectiveYeachan-Heo/oh-my-claudecode40k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Feature Lifecycle

    Inebrio/Routerly

    Run a Tier 1 or Tier 2 feature end to end — feature level, story level, parallelism, integration, and retrospective.

    100 GitHub stars~3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Codex Retrospective

    majiayu000/spellbook

    A skill your agent uses when you want Codex to review its own recent history (last N days or specific period) and improve its behavior.

    286 GitHub stars~1.6k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Living Docs Governance

    qshanx/docs-governance

    把长期项目的文档当成一个小系统来维护，防止文档腐烂——四份各司其职的脊柱文件（CLAUDE.md 共享章程 / CLAUDEMAP.md 地图 / PROJECTSTATUS.md 健康仪表盘 / PROJECTLOG.md 流水账）+ Codex 的 AGENTS.md 入口桥接 + 固定读序，并按需连接 ARCHITECTURE、CONTEXT、ADR、契约、测试、回归和 Issue…

    132 GitHub stars~4.1k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Skill Retro

    kenneth-liao/ai-launchpad-marketplace

    A skill your agent uses when reviewing how skills performed during a session, when the user wants to analyze skill invocations and identify improvements, or when the user says "skill retro", "review…

    126 GitHub stars~2.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

  • Refit Environment Retrospective

    Yeachan-Heo/oh-my-claudecode

    Reads an agent environment's own traces, friction reports and logs across sessions, then proposes fixes on the surface that owns each one, only with your approval.

    40k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Skill Management

    Szotasz/marveen

    List, inspect, patch, or delete skills from ~/.claude/skills/.

    115 GitHub stars~1.9k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from mizchi/skills

All 69 skills in this repo

  • Publish Agent Skill

    mizchi/skills

    Package, publish, verify and update an agent skill through a Claude Code plugin marketplace, APM or the npx skills CLI.

    356 GitHub stars~1.7k tokensUpdated 6 days ago
    Auto-check passed

  • AI Index

    mizchi/skills

    Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English.

    356 GitHub stars~3.6k tokensUpdated 6 days ago
    Auto-check passed

  • Cloudflare Deploy

    mizchi/skills

    Deploy applications and infrastructure to Cloudflare with the cf CLI and typed cloudflare.config.ts.

    356 GitHub stars~2.9k tokensUpdated 6 days ago
    Auto-check: notes

  • Review Image

    mizchi/skills

    Review screenshots or other images with OpenRouter vision models via bundled Deno scripts.

    356 GitHub stars~1.3k tokensUpdated 6 days ago
    Auto-check passed

  • Sqlc Gen Moonbit Safety

    mizchi/skills

    Post-generation safety checks for sqlc-gen-moonbit + Cloudflare D1.

    356 GitHub stars~995 tokensUpdated 6 days ago
    Auto-check passed

  • Apm Usage

    mizchi/skills

    Reference for APM (Agent Package Manager) — apm.yml syntax, install / uninstall / update commands, target detection, lockfile workflow.

    356 GitHub stars~1.9k tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Retrospective Codify

What does Retrospective Codify 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. Retrospective Codify is an agent skill from mizchi/skills.md rule.

When should I use Retrospective Codify?

Retrospective Codify fits situations like: explicitly says codify todays lessons; make it a skill; drop it into lint; asks to extract a reusable rule from a trial-and-error fix.

How do I install Retrospective Codify in Claude Code?

Run `npx skills add mizchi/skills --skill retrospective-codify -a claude-code`. Or copy the skill folder (retrospective-codify in mizchi/skills) into .claude/skills/retrospective-codify in your project. Claude Code loads it when a task matches its description.

How do I install Retrospective Codify in Codex?

Run `npx skills add mizchi/skills --skill retrospective-codify -a codex`. Or copy the skill folder (retrospective-codify in mizchi/skills) into .agents/skills/retrospective-codify in your project. Codex loads it when a task matches its description.

Can I use Retrospective Codify in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mizchi/skills --skill retrospective-codify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retrospective-codify, .gemini/skills/retrospective-codify, .github/skills/retrospective-codify and .opencode/skills/retrospective-codify in your project.

What does Retrospective Codify need to run?

Going by SKILL.md and its folder, Retrospective Codify needs the command-line tools its instructions call (pnpm).

Does Retrospective Codify access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Retrospective Codify safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Retrospective Codify use?

No licence was found for Retrospective Codify or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Retrospective Codify use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Retrospective Codify?

Skills that share tags, products or a category with Retrospective Codify: Feature Lifecycle (Inebrio/Routerly, 100 stars), Codex Retrospective (majiayu000/spellbook, 286 stars), Living Docs Governance (qshanx/docs-governance, 132 stars) and Skill Retro (kenneth-liao/ai-launchpad-marketplace, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retrospective Codify?

mizchi (a GitHub user) maintains it in mizchi/skills, which has 356 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on October 2, 2026.

Source: mizchi/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.