Loading...
Loading...
Found 36 Skills
Monorepo tooling, task orchestration, and workspace architecture for JavaScript/TypeScript repositories. Use when setting up Turborepo, Nx, pnpm workspaces, or npm workspaces; designing package boundaries; configuring remote caching; optimizing CI for affected packages; managing versioning with Changesets; or untangling circular dependencies. Activate on "monorepo", "turborepo", "nx", "pnpm workspace", "task pipeline", "remote cache", "changesets", "CODEOWNERS", "circular dependency", "affected packages", "workspace". NOT for git submodules or multi-repo federation strategies, non-JavaScript monorepos (Bazel, Pants, Buck), or single-package repository setup.
One-stop companion and installer for the official Tencent IMA skill (腾讯 IMA / ima.qq.com). Handles zero-config installation to Claude Code / Codex / OpenClaw via `npx skills add`, guides API key setup, detects and fixes known issues in the upstream package (including the missing-YAML-frontmatter bug in submodule SKILL.md files), and implements a personalized fan-out search strategy with priority-based knowledge base boosting. Use this skill whenever the user mentions IMA, 腾讯 IMA, ima.qq.com, ima-skill, installing or configuring ima-skill, searching across IMA knowledge bases, 知识库搜索, 笔记搜索, fan-out search with preferred KBs, or reports errors like "Skipped loading skill(s) due to invalid SKILL.md". Also trigger for any request to diagnose, repair, or personalize the behavior of an ima-skill installation. This is a wrapper layer around ima-skill — it installs and orchestrates ima-skill rather than replacing it.
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。
Start a new Blockbench model or scene from a short intake form and deliver a render-ready Blender scene. Asks for quality, texture style (PBR 2K/HD/standard, vanilla Minecraft, classic Blockbench), animation (keyframed or Havok physics), scene type (scene, vignette, isometric room), subject, output folder and render preset; builds .bbmodel files with the headless Blockbench MCP server and parallel agents; imports them into Blender; and writes a render.cmd that renders stills on every GPU and assembles them into a video with FFmpeg. Use when the user runs /blockbench-new-model or asks for a new Blockbench model delivered as a rendered Blender scene or video.
This skill provides comprehensive knowledge for building static websites with Hugo static site generator. It should be used when setting up Hugo projects (blogs, documentation sites, landing pages, portfolios), integrating Tailwind CSS v4 for custom styling, integrating headless CMS systems (Sveltia CMS or TinaCMS), deploying to Cloudflare Workers with Static Assets, configuring themes and templates, and preventing common Hugo setup errors. Use this skill when encountering these scenarios: scaffolding new Hugo sites, choosing between Hugo Extended and Standard editions, integrating Tailwind CSS v4 with Hugo Pipes, configuring hugo.yaml or hugo.toml files, integrating PaperMod or other themes via Git submodules, setting up Sveltia CMS or TinaCMS for content management, deploying to Cloudflare Workers or Pages, troubleshooting baseURL configuration, resolving theme installation errors, fixing frontmatter format issues (YAML vs TOML), preventing date-related build failures, setting up PostCSS with Hugo, or setting up CI/CD with GitHub Actions. Keywords: hugo, hugo-extended, static-site-generator, ssg, go-templates, papermod, goldmark, markdown, blog, documentation, docs-site, landing-page, sveltia-cms, tina-cms, headless-cms, cloudflare-workers, workers-static-assets, wrangler, hugo-server, hugo-build, frontmatter, yaml-frontmatter, toml-config, hugo-themes, hugo-modules, multilingual, i18n, github-actions, version-mismatch, baseurl-error, theme-not-found, tailwind, tailwind-v4, tailwind-css, hugo-pipes, postcss, css-framework, utility-css, hugo-tailwind, tailwind-integration, hugo-assets
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
Set up and configure Google's release-please for automated versioning, changelog generation, and publishing via GitHub Actions. Covers pipeline creation, Conventional Commits formatting, pre-release workflows, monorepo configuration, and troubleshooting release pipelines. Use this skill whenever the user wants to automate releases, set up CI/CD for publishing, configure version bumping, write release-please-compatible commit messages, tag versions automatically, publish to npm/PyPI/crates.io/Maven/Docker, or troubleshoot why a release PR wasn't created. Activate even if the user doesn't mention "release-please" by name — phrases like "automate my npm releases", "set up GitHub Actions for publishing", "how do I tag versions automatically", "changelog generation", "semver automation", or "pre-release workflow" all indicate this skill. For commit message guidance specifically, this skill focuses on release-please-compatible conventions; for broader multi-repo git operations with submodules, defer to multi-repo-git-ops instead.
UNNC AIM team's repository and code standards. Covers repository naming (competition / aim- academic-year / reusable), branch and Conventional Commits rules, AI-agent git behavior (never commit / push unless the user explicitly asks in the current task; never call the gh CLI without explicit permission; never add an AI Co-Authored-By trailer; suggest a commit message at the end of a code-changing task), and formatting standards for Python (autopep8 / PEP 8), C++ (clang-format / clang-tidy), TypeScript (Prettier + ESLint, pnpm), Go (gofmt), CMake, and Markdown / YAML / JSON, with ready-to-copy canonical rule files. Use when creating or naming a repository, validating a ROS2 package.xml name, creating a branch, writing a git commit message, on any task that could involve committing, pushing, or calling gh, composing a competition workspace (git submodules under src/), or setting up Python, C++ (.clang-format / setup.cfg / .clang-tidy), TypeScript (Prettier / ESLint / pnpm) or Go (gofmt) tooling, styling a CMakeLists.txt or Markdown / YAML / JSON files, or applying the team's recommended git configuration.
Clean up a git repository: delete branches whose PRs merged (incl. squash-merges), remove their safely removable linked worktrees, list or delete local branches past a confirmed age threshold, prune stale remote-tracking refs and worktree metadata, and optionally prune local tags absent from the remote, run gc, or delete merged remote branches. Use when asked to clean up / prune / tidy git branches or worktrees, remove merged or stale branches, delete old branches, prune origin/* refs, or clear out a repo's branch/worktree list, including from a directory containing worktrees from one or more repositories. Reports first (dry run); never touches current/default/kept branches or main, dirty, locked, detached, unavailable, or submodule-containing worktrees. Ignored node_modules and dist output is disposable; other ignored files remain protected.
Sub-skill for the intake phase of README-first AI repo reproduction. Use when the task is specifically to scan a repository, read README and common project files, extract documented commands, classify inference or evaluation or training candidates, and return a minimum trustworthy plan to the main skill. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
Manages context layer domains, tasks, and documentation via the ctx CLI. Use when the user mentions context layer (e.g. "using context layer", "in the context layer", "in the context") ctx commands, context layer projects or tasks, or requests you to write any form of documentation -- such as documenting implemented features, research findings, or drawing diagrams. Also use when the user asks to clone a repo as context layer context or access context layer's "data" folder.