FanBB2333

Example skill bundled with skim for demos and quick-start usage.

Fixture skill used by the skim CLI workflow tests.

Standardize Git commit messages with Conventional Commits v1.0.0. Use this skill when the user mentions commit, 提交, 提交代码, 提交信息, commit message, conventional commit, feat/fix/chore, or asks to create/amend a commit.

Describe what this skill does and when to use it.

Generate and refine your personal skills from conversation history.

Summarize a repository and propose next steps.

Run GPU work on the user's own cluster through the nvidb job queue instead of starting it by hand. Use whenever a task needs a GPU, needs to run on a remote machine, is long-running, or must survive this session ending - training, evaluation, inference…

Multi-dimensional agent thinking framework mapping classical philosophical schools to LLM control strategies. Use when the user needs exploratory reframing (dao), audience-fit and role ethics (confucian), strict rule enforcement (legal), structured planning…

Use when you want the model to emulate GPT's distinctive Chinese output style — lively metaphors, conversational warmth, proactive engagement, and colloquial flow. Designed to make any model (Claude, Gemini, GLM, etc.) sound authentically GPT-like in Chinese…

Use when the model is GPT (gpt-5.x, gpt-5.x-codex, or similar) and generating Chinese text. Prevents unnatural GPT-specific Chinese expressions (corporate jargon, violent metaphors, filler phrases) and guides output toward a professional, human-readable style…

Use when user invokes /sigmeow to activate chaos cat mode - a cat personality overlay that introduces cat-themed mischief into code at configurable chaos levels (none, low, medium, hard) while still completing tasks correctly

Diagnose and fix code bugs using Traditional Chinese Medicine (TCM) diagnostic methodology (Observation, Listening, Inquiry, Palpation). Use when the user mentions debugging, bug fixing, error diagnosis, code repair, or when a test failure or runtime error…

Adversarial-Feynman prompting skill that improves output quality through relentless self-interrogation and first-principles simplification. Use when the user needs high-confidence, logically rigorous, and jargon-free explanations, or when working on complex…