Autonomous Dev
bkywksj/knowledge-base
自主连续开发方法论(Codex 版)。把一个项目按「每轮一个最小可提交单元」的方式推进到完成: 每轮读真相源 → 选下一个未做项 → 做一个最小单元 → 过验证门 → 记录勾选 → 最小提交 → 报进度。
xangi 上で起きた事象(再投稿・cron が回らない・データ不整合・想定外の動作・エラー等)の調査・根本原因分析・横展開・報告を行い、明示依頼時にだけ修正する汎用スキル。「調査して」「原因調べて」「再発防止」「横展開して」「xangi-kaizen」「事象を分析して」で発動。
$ npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install karaage0703/ai-assistant-workspace xs-xangi-kaizen --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/xs-xangi-kaizen .claude/skills/xs-xangi-kaizen && rm -rf skills-srcUse ~/.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/
Install the "xs-xangi-kaizen" agent skill from https://github.com/karaage0703/ai-assistant-workspace/tree/main/skills/xs-xangi-kaizen into .claude/skills/xs-xangi-kaizen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xs-xangi-kaizen", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/karaage0703/ai-assistant-workspace/tree/main/skills/xs-xangi-kaizenType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install karaage0703/ai-assistant-workspace xs-xangi-kaizen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/xs-xangi-kaizen .agents/skills/xs-xangi-kaizen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xs-xangi-kaizen" agent skill from https://github.com/karaage0703/ai-assistant-workspace/tree/main/skills/xs-xangi-kaizen into .agents/skills/xs-xangi-kaizen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xs-xangi-kaizen", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install karaage0703/ai-assistant-workspace xs-xangi-kaizen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/xs-xangi-kaizen .cursor/skills/xs-xangi-kaizen && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "xs-xangi-kaizen" agent skill from https://github.com/karaage0703/ai-assistant-workspace/tree/main/skills/xs-xangi-kaizen into .cursor/skills/xs-xangi-kaizen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xs-xangi-kaizen", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/karaage0703/ai-assistant-workspace.git --path skills/xs-xangi-kaizen--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install karaage0703/ai-assistant-workspace xs-xangi-kaizen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/xs-xangi-kaizen .gemini/skills/xs-xangi-kaizen && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "xs-xangi-kaizen" agent skill from https://github.com/karaage0703/ai-assistant-workspace/tree/main/skills/xs-xangi-kaizen into .gemini/skills/xs-xangi-kaizen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xs-xangi-kaizen", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install karaage0703/ai-assistant-workspace xs-xangi-kaizenInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/xs-xangi-kaizen .github/skills/xs-xangi-kaizen && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "xs-xangi-kaizen" agent skill from https://github.com/karaage0703/ai-assistant-workspace/tree/main/skills/xs-xangi-kaizen into .github/skills/xs-xangi-kaizen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xs-xangi-kaizen", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install karaage0703/ai-assistant-workspace xs-xangi-kaizen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/xs-xangi-kaizen .opencode/skills/xs-xangi-kaizen && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "xs-xangi-kaizen" agent skill from https://github.com/karaage0703/ai-assistant-workspace/tree/main/skills/xs-xangi-kaizen into .opencode/skills/xs-xangi-kaizen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xs-xangi-kaizen", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
xs-xangi-kaizenxangi 上で起きた事象(再投稿・cron が回らない・データ不整合・想定外の動作・エラー等)の調査・根本原因分析・横展開・報告を行い、明示依頼時にだけ修正する汎用スキル。「調査して」「原因調べて」「再発防止」「横展開して」「xangi-kaizen」「事象を分析して」で発動。
Xs Xangi Kaizen is an agent skill from karaage0703/ai-assistant-workspace. xangi 上で起きた事象(再投稿・cron が回らない・データ不整合・想定外の動作・エラー等)の調査・根本原因分析・横展開・報告を行い、明示依頼時にだけ修正する汎用スキル。「調査して」「原因調べて」「再発防止」「横展開して」「xangi-kaizen」「事象を分析して」で発動。
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).
It sits in Productivity & Automation, covering Scheduled and recurring tasks. It works with Git. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c689862. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
gitdockerFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git and docker, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Xs Xangi Kaizen loads about 1.3k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 268 words of instructions outside code blocks.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
trajectory/` を見る。環境変数やチャンネル割り当ては各 bot の `.env` で確認する。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.
The full file from karaage0703/ai-assistant-workspace at commit c689862, republished under its MIT licence (© karaage0703). 268 words, ~1,288 tokens.
.claude/skills/xs-xangi-kaizen/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.AIアシスタントで起きた事象を調査し、根拠のある原因と対策を報告する。xangi固有のコマンドは、その環境で利用できる場合だけhelpを確認して使う。
スキルの背景・設計思想・参考文献は README.md を参照。
何が起きた / いつ / どこで(チャンネル・対象スキル)。事実を時系列で整理する。
ステップ:
xangi tool discord_history --count 30
xangi tool discord_history --channel <ID> --count 50[NOTES_DIR] の過去 xangi-kaizen ノートを事象キーワードで grep# xangi-kaizen タグの全事例
grep -rl '#xangi-kaizen' [NOTES_DIR] | sort
# 対象スキル名・キーワードで絞り込み
grep -rl '#<対象スキル名>' [NOTES_DIR]
grep -rl 'state\|cron\|<キーワード>' [NOTES_DIR]/*xangi-kaizen* 2>/dev/null複数のソースを横断的に追う。一つの観点で結論を出さない。
ステップ 0(重要): 調査対象 bot の workspace を特定する。 xangi は bot ごとに別 workspace・別プロセスで動く構成を取りうる。複数 bot を運用している場合、手元の workspace だけを見ても対象 bot の事象は写っていないことがある。
# Docker 運用の場合: bot がどのコンテナか確認
docker ps --format '{{.Names}}\t{{.Image}}'
# コンテナの workspace マウント元を確認
docker inspect <container> --format '{{range .Mounts}}{{.Source}} -> {{.Destination}}{{println}}{{end}}' | grep '/workspace'特定した <bot-workspace> 配下の logs/sessions/ と logs/tool-trajectory/ を見る。環境変数やチャンネル割り当ては各 bot の .env で確認する。
| 観点 | コマンド/対象 |
|---|---|
| state ファイル | [STATE_DIR]/*_state.json、references/*_last_check.json 等の中身と stat -c "%y %n" |
| git 履歴 | git log -p --all -- <path>、git show <commit>:<path> |
| git reflog | git reflog --since=<時刻>(ブランチ切替・rebase・reset の追跡) |
| cron / schedule | xangi tool schedule_list 2>&1 | grep -B2 -A3 <キーワード> |
| セッションログ(生応答) | 対象 bot の <bot-workspace>/logs/sessions/*.jsonl。事象の出たチャンネル ID で grep -rl <channelId> → 該当ファイルの当該ターンを開き、assistant result を確認 |
| tool-trajectory ログ | <bot-workspace>/logs/tool-trajectory/*.jsonl。tool search / loop / drift / stream buffer / cache などのイベントが時系列で残る |
| 該当スクリプト/コード | skills/<name>/scripts/、または対象リポのソース。ログで事象を確定した後に「なぜそうなるか」を辿る |
| 投稿履歴 | xangi tool discord_history --channel <ID> --count 30 |
「これしか見ていない」状態で次フェーズに行かない。
「なぜ」を最低3回掘る。 誰が読んでも納得できる説明になるまで掘り続ける。
仮説 → 証拠 → 検証のサイクル。仮説が間違っていたら戻る。証拠が不足する場合は原因未確定として報告する。
patchが適用できない場合は、期待した本文と現ファイルを再比較する。表記差・読み取り後の変更・別hunkの失敗を区別し、mtime/hashや他プロセスの更新証拠がある場合だけ「競合」と報告する。
例:
pull --rebase / checkout 多発を確認 → ✓「ここまで掘れば再発防止策が書ける」と思える深さまで掘る。一段で止まると対症療法になる。
応答内容系(変な出力・空・drift)はコードからの推測で終わらせない。「コードのこの fallback だ」で止めず、Phase 2 で開いた当該ターンの生ログと突き合わせて確定する。ログで確定するまでは報告に「ここは未確認の推測」と明示する。
同じパターンの他ファイル/問題を網羅検索する。1件直しても、別の場所で同じ事故が起きうる。
# ランタイム状態ファイル系を全部洗い出し
git ls-files | grep -iE "state|cache|last_check|cookie|credential|\.pid$"
# 巨大ログ系(リポジトリ肥大化のリスク)
git ls-files | xargs -I {} stat -c "%s %n" {} 2>/dev/null | sort -rn | head -20
# 最近書き換えられた tracked ファイル(書き換え頻度 + tracked = 罠)
git ls-files | xargs -I {} stat -c "%y %n" {} 2>/dev/null | sort -r | head -30事象の根本パターンに沿って検索クエリを組み立てる。「state ファイルが git ロールバックされた」が真因なら「他に git 管理されてる runtime state は無いか」を網羅する。
診断依頼なら原因・証拠・対策案・未確認事項を報告して完了する。変更依頼の場合だけ以下へ進む。
実装方針:
.gitignore に追加)報告フォーマット:
詳細レポートは [NOTES_DIR] にタグ付きで保存する。事例は積み重ねていく(次回の調査で Phase 1 の KEDB として効く)。
[NOTES_DIR]YYYYMMDD_xangi-kaizen_<事象タイトル>.md---
title: <事象タイトル>
date: YYYY-MM-DD
type: incident
tags:
- xangi-kaizen
- incident
- <対象スキル名>
---xs-note-taking スキルに従う(命名規則・フロントマター・同期手順を活用)過去事例を参照したいときは:
grep -rl '#xangi-kaizen' [NOTES_DIR] | sort詳細経緯はノートや knowledge/lessons_archive.md に残し、繰り返し使う判断基準だけを短くAGENTS.mdへ反映する案を示す。調査だけの依頼で行動ルールを勝手に書き換えない。
xs-xangi-kaizen
xangi-kaizen でこの事象を調査して
原因調べて
再発防止策を立てて
調査して、横展開もしてほしい
事象を分析して© karaage0703, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/xs-xangi-kaizen of karaage0703/ai-assistant-workspace.
Open the folder on GitHubat commit c689862
Xs Xangi Kaizen 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Xs Xangi Kaizen this skillkaraage0703/ai-assistant-workspace | 136 | — | ~1.3k | Automated safety check: Notes | MIT | |
| Autonomous Devbkywksj/knowledge-base | 330 | — | ~573 | Automated safety check: Notes | Custom licence | |
| RenderLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.8k | Automated safety check: Pass | MIT | |
| Gh Issuestrpc-group/trpc-agent-go | 1.9k | 8 repos | ~8.7k | Automated safety check: Pass | Apache-2.0 | |
| Dependency Watchtelegramdesktop/tdesktop | 33k | 1 repos | ~2.2k | Automated safety check: Pass | GPL-3.0 | |
| Cron Opsczl9707/build-your-own-openclaw | 1.9k | — | ~593 | Automated safety check: Pass | MIT |
bkywksj/knowledge-base
自主连续开发方法论(Codex 版)。把一个项目按「每轮一个最小可提交单元」的方式推进到完成: 每轮读真相源 → 选下一个未做项 → 做一个最小单元 → 过验证门 → 记录勾选 → 最小提交 → 报进度。
LeoYeAI/openclaw-master-skills
Deploy and operate apps on Render (Blueprint + one-click Dashboard deeplink, same flow as Codex render-deploy).
trpc-group/trpc-agent-go
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments.
telegramdesktop/tdesktop
Audit Telegram Desktop dependencies on freshly fetched origin/dev for releases and security fixes, including upstream lag and backport candidates in patched forks.
czl9707/build-your-own-openclaw
Create, list, and delete scheduled cron jobs. An agent skill from czl9707/build-your-own-openclaw.
Automattic/agent-skills
A skill your agent uses when working with WP-CLI (wp) for WordPress operations: safe search-replace, db export/import, plugin/theme/user/content management, cron, cache flushing, multisite, and…
karaage0703/ai-assistant-workspace
arXiv論文の検索・トレンド発見・詳細分析を行う統合スキル。興味度スコアでユーザーに刺さる論文を自動選定。PDF全文読み込み・Notion蓄積対応。「arXivチェックして」「論文検索」「論文分析して」で使用。
karaage0703/ai-assistant-workspace
異なるproviderのAI(Codex/Claude/Grok/Cursor/Antigravity等)から独立意見を集め、共通論点で相互検討して統合する。最初に利用可能エージェントを検出する。「みんなで考えて」「マルチエージェントで分析して」「複数のAIでレビューして」と言われたら使う。
karaage0703/ai-assistant-workspace
ポッドキャストの音声取得・文字起こし・まとめを行う統合スキル。「ポッドキャストまとめて」「音声配信をダウンロード」「Podcastの内容を教えて」で使用。
karaage0703/ai-assistant-workspace
スキルの作成・改善を行うスキル。既存スキルの分析から抽出したパターンとテンプレートで統一感のあるスキルを効率的に作成。スキルを作りたい、新しいスキルを追加したい、スキルを改善したい、SKILL.mdを書きたい場合に使用。
karaage0703/ai-assistant-workspace
ワークスペース内の遠い知識や活動をつないで、新しいアイデアを生成する思考支援スキル。過去記事・メモ・発信資産から企画や実装ネタを出したい時に使用。「アイデア出して」「知識をつないで」「一見関係ないものをつないで」で使用。
karaage0703/ai-assistant-workspace
カレンダー予定を確認するスキル。ICS(Googleカレンダー等)と手動追加(画像読み取り)を統合。「今日の予定」「明日の予定」「カレンダー画像送って」「スケジュール確認」で使用。/calendar で発動。
Works with
Categories
xangi 上で起きた事象(再投稿・cron が回らない・データ不整合・想定外の動作・エラー等)の調査・根本原因分析・横展開・報告を行い、明示依頼時にだけ修正する汎用スキル。「調査して」「原因調べて」「再発防止」「横展開して」「xangi-kaizen」「事象を分析して」で発動。. Xs Xangi Kaizen is an agent skill from karaage0703/ai-assistant-workspace.
Xs Xangi Kaizen fits situations like: tasks that involve Scheduled and recurring tasks.
Run `npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a claude-code`. Or copy the skill folder (skills/xs-xangi-kaizen in karaage0703/ai-assistant-workspace) into .claude/skills/xs-xangi-kaizen in your project. Claude Code loads it when a task matches its description.
Run `npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a codex`. Or copy the skill folder (skills/xs-xangi-kaizen in karaage0703/ai-assistant-workspace) into .agents/skills/xs-xangi-kaizen in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add karaage0703/ai-assistant-workspace --skill xs-xangi-kaizen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xs-xangi-kaizen, .gemini/skills/xs-xangi-kaizen, .github/skills/xs-xangi-kaizen and .opencode/skills/xs-xangi-kaizen in your project.
Going by SKILL.md and its folder, Xs Xangi Kaizen needs the command-line tools its instructions call (git and docker). Our summary lists: Docker.
SKILL.md contains no URLs. Its commands use git and docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Xs Xangi Kaizen is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Xs Xangi Kaizen: Autonomous Dev (bkywksj/knowledge-base, 330 stars), Render (LeoYeAI/openclaw-master-skills, 2.2k stars), Gh Issues (trpc-group/trpc-agent-go, 1.9k stars) and Dependency Watch (telegramdesktop/tdesktop, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
karaage0703 (a GitHub user) maintains it in karaage0703/ai-assistant-workspace, which has 136 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on September 23, 2026.
Source: karaage0703/ai-assistant-workspace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.