Loading...
Loading...
Found 2,989 Skills
Fix a bug with systematic debugging, TDD, and PR workflow
Small tweaks to existing features — no design needed, just TDD and PR
Commit, push, and open a pull request in Azure DevOps. Use whenever the user wants to open, update, or draft a PR and the project is hosted on Azure DevOps (`dev.azure.com`, `visualstudio.com`, or explicit mentions of ADO, Azure Repos, or work item IDs like `AB#1234`). Links work items to the PR, sets reviewers, and supports draft-by-default.
Build a production-quality CLI tool for any module or application. Auto-detects language, recommends CLI libraries, and follows a 5-step approval-gated workflow: Analyze, Design, Plan, Execute, Summarize. Don't use for building GUI/TUI apps, web APIs, or authoring one-off shell scripts.
Use when the user asks to investigate, audit, trace, or explain how a feature, issue, module, workflow, API, config, or behavior works across one or more codebase projects.
Use when a user has finished using one installed skill and wants to preserve actionable feedback about that skill while the session context is still fresh
Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.
Explains the intent behind source code by finding original session transcripts. Use explain with a function, file, or line of code to understand why it exists.
ルート直下の `skills-lock.json` の `computedHash` を upstream リポジトリの最新状態と照合して更新する。`source` が `Fandhe-AI/` で始まらないエントリは clone せず skip (安全弁)。submodule 配下の `skills-lock.json` は触らない。contribute-skill のマージ後や upstream 同期後、「ハッシュ更新」「skills-lock 同期」などで使用。
Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user asks for a model structure chart, architecture diagram, or rendered image link for a specific model such as DeepSeek, GLM, Qwen, Kimi, MiniMax, Step, Hunyuan, or Qwen3-VL.
Detect and analyze potential malware distribution repositories masquerading as legitimate security software
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.