メニュー
Use when a task involves heavy implementation, debugging, test fixing, refactoring, or multi-file edits that Codex could execute, or when orchestrating Claude + Codex together in a session.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/ucsandman/claude-skills --skill fable-gptコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Fill a repo's .env from the machine's credential stores without ever reading or printing a secret value. Use when the user says "/secrets", "fill in the .env", "get the keys", "wire up the credentials", "pull the secrets from offlocal", or when launch.py / a dev server refuses to start because keys are still on example values.
Use when finished work needs to go out — the user says "ship it", "update docs commit and push", "commit and push", or asks "anything else we need to update?" before a release or at the end of a work session.
Use before writing a new skill, before saying no skill exists for something, or whenever Wes asks "do I have a skill for X" / "is there a skill that…". Also use when a task sounds like it needs a capability that might already be installed (spreadsheets, PDFs, docx, scraping, copywriting, a framework, a provider) — most of this machine's skills are NOT in the session listing, so "I don't see one" is not evidence that none exists.
SOC 職業分類に基づく
SKILL.md を表示中
| name | fable-gpt |
| description | Use when a task involves heavy implementation, debugging, test fixing, refactoring, or multi-file edits that Codex could execute, or when orchestrating Claude + Codex together in a session. |
gpt-5.5 at xhigh reasoning (~/.codex/config.toml); do not pass --model/--effort unless deliberately overriding.| Situation | Route |
|---|---|
| Quick, bounded task | /codex:rescue (foreground) |
| Big, open-ended, or long-running | codex-rescue subagent (already model: sonnet, Bash-only — passes agent-model-guard) or --background; poll /codex:status, fetch /codex:result |
| Continue prior Codex work | say "resume"/"continue" (maps to --resume-last) |
| Routine pre-commit review or second-opinion diagnosis | /codex:review — default here before spending Claude subagent tokens; reserve /code-review or /adversarial-review for high-stakes diffs |
Goal: [one sentence]
Files: [paths]
Constraints: [style, don't touch X]
Done when: [verification command + expected result]
One task per delegation. Split unrelated work into separate rescues.
Workspace root gotcha: Codex's sandbox root is the session's cwd, not the task's target repo. If the target repo differs from cwd, the codex-rescue subagent and /codex:rescue will spawn a task that can't write ("patch rejected: writing outside of the project") — Codex burns the whole run discovering this. Invoke the companion runtime directly instead:
node "<plugin>/scripts/codex-companion.mjs" task --prompt-file <spec.md> --cwd "<target-repo>" --write --background
Long specs go in a --prompt-file (avoids shell quoting). Job state is keyed to the --cwd value — pass the SAME --cwd to status/result/cancel or the job appears not to exist. Errors print to stderr; don't 2>/dev/null status calls.
git diff — read what actually changed.