Crowi Fix

OrganizationPopular

crowi

crowi-fix

バグ報告・小修正のための軽量ワークフロー。spec 不要。再現(失敗するテスト)を先に作り、 systematic-debugging で根本原因を特定してから直す。ゲート(type-check / test / lint)→ codex 1 パスレビュー → commit。設計判断が要る規模なら crowi-design / crowi-feature へ誘導。キーワード: fix, バグ, 修正, bug, 不具合, repro, 直して, 壊れてる

Overview

Publisher	crowi
Repository	`crowi`
Skill name	`crowi-fix`
Stars	1.1K
Forks	166
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by crowi on GitHub. Read the source before you install it.

Installation

Install the Crowi Fix AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/crowi/crowi/tree/main/.claude/skills/crowi-fix
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/crowi/crowi.git /tmp/crowi
mkdir -p .claude/skills
cp -r /tmp/crowi/.claude/skills/crowi-fix .claude/skills/crowi-fix

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Crowi Fix in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Crowi Fix on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Crowi Fix is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Crowi Fix (repro-first の軽量バグ修正)

「壊れているものを直す」ための最短経路。crowi-feature の planner/レビューループは重すぎ、アドホックだと再現なし・根本原因なしの推測修正が混ざる — その中間を定型化する。

crowi-feature との使い分け

条件	使うもの
挙動が壊れている・期待とのズレが明確・設計判断不要	crowi-fix
新しい挙動を足す / 契約・スキーマ変更を伴う / 設計判断あり	crowi-feature(必要なら crowi-design から)
修正方針に複数案があり trade-off 判断が要る	いったん止まってユーザーに確認(勝手に選ばない)

途中で「設計判断が要る」と気づいたら、進めずにその時点で報告して切り替える。

ワークフロー

Step 1: 再現(repro-first)

修正より先に、失敗するテストを書く(api は jest + supertest + mongodb-memory-server)。「バグが直るとこのテストが green になる」が完了の定義。
テストで再現しづらい UI バグ: 再現手順を記録し、クリティカルフロー (feature-planner.md の表)に該当し小さく書けるなら packages/e2e/tests/ に足す(無理はしない)。
再現できないバグは直さない — 推測修正は禁止。再現条件をユーザーに確認して止まる。

Step 2: 根本原因の特定(systematic-debugging)

症状 → 仮説 → 検証を繰り返し、根本原因を file:line で特定してから修正に入る。対症療法(症状を隠すだけの分岐)を書かない。

Step 3: 修正 + ゲート

最小 diff。関係ないリファクタを混ぜない。
ゲート: pnpm --filter @crowi/api type-check(web を触ったら +web)/ 該当テスト(Step 1 のテスト含む)/ pnpm lint(errors=0)/ 契約を触ったら pnpm --filter @crowi/api-contract build + pnpm check:openapi。

Step 4: codex 1 パスレビュー(fix or drop)

bash
mkdir -p .reviews/codex-runs/fix-<topic>
# prompt: 「git status --porcelain + git diff HEAD で修正を取得し(untracked は直接読む)、
#          退行・境界・並行の観点で敵対レビューせよ」+ FINDINGS schema (crowi-review と同形)
bash .claude/scripts/codex-run.sh --sandbox read-only --tier terra \
  --prompt-file .reviews/codex-runs/fix-<topic>/prompt.md \
  --schema-file .reviews/codex-runs/fix-<topic>/schema.json \
  --out .reviews/codex-runs/fix-<topic>/out.json --label fix-<topic>

重い 3 lens は使わない(1 パスのみ)。
findings は「直すか捨てる」の二択: 自分でコードに当てて裏取りし、正しければその場で直してゲート再走。誤り・過大なら捨てる(報告に 1 行)。 どこかへの退避は禁止(fix or drop — 退避先は存在しない)。
exit 2(codex 不可)/ exit 3(出力が不正 — codex が exit 0 で何も書かなかった場合もここに来る) なら skip して報告(レビュー無しで止めない)。どちらも fix の進行を止めない。

Step 5: commit

fix(<scope>): <what> + 本文に root cause を 1-3 行。テストは同 commit か test(<scope>) 分割(diff サイズで判断)。
ユーザー可視のバグ修正なら changeset(patch)を追加。内部のみなら不要。
main 直でも worktree でも可。main 直の場合は commit 前に main write lock を取得し commit 後に解放(CLAUDE.md「main write lock」参照)。worktree の場合、完了後は /crowi-complete-feature(task ファイル無し → synthesize が signal を立てる — 既存互換)。 push しない。

鉄則

再現なしに直さない / 根本原因なしに直さない
レビュー指摘は fix or drop(退避先は存在しない)
設計判断が要ると気づいたら勝手に進めず crowi-design / ユーザーへ
push はユーザー指示待ち

Frequently asked questions

What does the Crowi Fix AI skill do?

Why use Crowi Fix on TypingMind?

Because you install it once and use it with any model. Crowi Fix is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Crowi Fix in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crowi/crowi/tree/main/.claude/skills/crowi-fix. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Crowi Fix?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Crowi Fix?

As many as you like. As long as a model supports skills, you can use Crowi Fix with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Crowi Fix AI skill free?

Yes. It is published on GitHub by crowi under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Refactor Docs

openclaw

OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Openclaw Repair Sweep

openclaw

OrganizationPopular

Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

Openclaw Test Performance

openclaw

OrganizationPopular

Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

Openclaw Testing

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Crowi Fix (repro-first の軽量バグ修正)

crowi-feature との使い分け

ワークフロー

Step 1: 再現(repro-first)

Step 2: 根本原因の特定(systematic-debugging)

Step 3: 修正 + ゲート

Step 4: codex 1 パスレビュー(fix or drop)

Step 5: commit

鉄則

Frequently asked questions

Related AI Skills

Set up your own AI workspace now