
Manage Codex worklog files under `.agents/worklog/codex`, hard-gate stale learnings through `learn_index.md`, and audit learn metadata deterministically. Use when a Codex agent or user needs to bootstrap worklog context, maintain plan/todo/learn files, or validate stale learn state before trusting prior session knowledge.
Write and review shellscript documentation with shdoc annotations. Use when Codex creates, edits, or reviews `.sh` files or shell executables and should add, repair, or normalize `@file`, `@brief`, `@description`, `@arg`, `@option`, and `@example` comments to match shdoc conventions.
Apply Python development policy using uv-first execution, test-first behavior validation, and pre-commit quality gates. Use when implementing or refactoring Python code.
Guidance and workflow for planning, writing, submitting, revising, and publishing scientific manuscripts in high-impact journals. Use when Claude needs to advise on research quality, study design, manuscript structure, journal selection, peer review responses, or publication strategy.
AIくさい日本語を、人が書いたように自然でこなれた日本語へ書き換えるスキル。ブログ記事、メモ、メール、文書、SNS投稿、チャット返信などの日本語を書いたり推敲したりするときに使う。AIっぽい言い回しを消したいとき、日本語を自然にしたいとき、言い換えたいとき、硬さを抜きたいとき、トーンを整えたいとき、人間らしい声や温度を足したいときに使う。
Enforce gh-first GitHub investigation, pull request maintenance, and Conventional Commit output rules. Use when investigating GitHub issues or pull requests, creating or updating pull requests, summarizing investigation results, or preparing commit messages.
Use this skill when converting custom PyTorch models to Hugging Face Transformers format. Helps with: (1) Creating PretrainedConfig and PreTrainedModel classes, (2) Writing ImageProcessor/Tokenizer, (3) Compatibility testing, (4) Hub upload preparation. Use when the user wants to make their model compatible with transformers library.
Attach local files to a GitHub issue or pull request comment via Playwright CLI and return the hosted attachment URLs without submitting the comment. Use when you need GitHub-hosted image or document URLs on github.com or GitHub Enterprise Server.
Enforce gh-first GitHub investigation, pull request maintenance, and Conventional Commit output rules. Use when investigating GitHub issues or pull requests, creating or updating pull requests, summarizing investigation results, or preparing commit messages.
Write and review shellscript documentation with shdoc annotations. Use when Codex creates, edits, or reviews `.sh` files or shell executables and should add, repair, or normalize `@file`, `@brief`, `@description`, `@arg`, `@option`, and `@example` comments to match shdoc conventions.
Attach local files to a GitHub issue or pull request comment via Playwright CLI and return the hosted attachment URLs without submitting the comment. Use when you need GitHub-hosted image or document URLs on github.com or GitHub Enterprise Server.
AIくさい日本語を、人が書いたように自然でこなれた日本語へ書き換えるスキル。ブログ記事、メモ、メール、文書、SNS投稿、チャット返信などの日本語を書いたり推敲したりするときに使う。AIっぽい言い回しを消したいとき、日本語を自然にしたいとき、言い換えたいとき、硬さを抜きたいとき、トーンを整えたいとき、人間らしい声や温度を足したいときに使う。
Use this skill when converting custom PyTorch models to Hugging Face Transformers format. Helps with: (1) Creating PretrainedConfig and PreTrainedModel classes, (2) Writing ImageProcessor/Tokenizer, (3) Compatibility testing, (4) Hub upload preparation. Use when the user wants to make their model compatible with transformers library.
Apply Python development policy using uv-first execution, test-first behavior validation, and pre-commit quality gates. Use when implementing or refactoring Python code.
Guidance and workflow for planning, writing, submitting, revising, and publishing scientific manuscripts in high-impact journals. Use when Claude needs to advise on research quality, study design, manuscript structure, journal selection, peer review responses, or publication strategy.