Loading...
Loading...
Found 1,623 Skills
Use when one ready GitHub issue or one explicitly confirmed conversation specification needs a repository-aware implementation plan for a later implementation workflow.
Use this skill when testing a RevenueCat Android integration. Covers the RevenueCat Test Store (test_ API key prefix, in dialog Success/Fail/Cancel choice), mockk based unit testing with an interface wrapper around Purchases, and a GitHub Actions CI pattern. Avoids Google Play sandbox for day to day test iteration.
Automated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue end-to-end → review with /review-it → ship with /ship-it → repeat. Persists state to .loop-state.json for crash recovery. Triggers on: loop-it, loop issues, auto implement, 批量实现, 循环实现, 实现所有issue, 恢复循环, resume loop.
Upgrade an installed Next Move Theory setup to the latest published canon + skills by re-running the official one-command installer, which clones the public GitHub repo (zamesin/Next-Move-Theory-Canon-and-Skills, branch main) and refreshes the canon, the nmt-* skills (both Claude and Codex), the injected rules block in CLAUDE.md / AGENTS.md, and the README — all in place. Idempotent and safe: it never touches your own files and never deletes unrelated skills. Use when the user says "update NMT", "upgrade the skills", "get the latest canon", runs /nmt-upgrade, or when another skill reports that a newer version is available. Defaults to English.
Delegate a coding task to the GitHub Copilot CLI (`copilot`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Copilot - phrasings like "have Copilot implement X", "delegate this to copilot", "run it through Copilot CLI", or "use copilot to implement/fix/refactor" - or wants to run a queue of coding tasks through Copilot while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Sets up GitHub repositories, links Vercel projects, and collects credentials via a secure local web form. Installs environment variables directly into Vercel and GitHub without shell leakage.
Look up conventions, patterns, and concrete implementations from your own GitHub repositories checked out locally under ~/projects/referenzen/. Use this skill whenever there is uncertainty about how something is done in your codebase family — e.g. Helm chart structure, Kubernetes manifests, framework configuration patterns, Docker Compose conventions, CI/CD pipeline setup, or any other recurring architectural decision. Invoke it proactively before guessing at a convention; always cite the source project and path when a pattern is adopted. Also use when the user asks to check out, update, or search reference repositories.
Review one or all open pull requests in saadeghi/daisyui using the GitHub MCP server and isolated base-versus-PR verification. Use when Codex must fact-check a daisyUI PR, verify that it solves its stated problem or linked issue, test concrete regression risks, explain developer experience before and after, decide whether it is safe to merge, and write a concise report under tmp/pr/. Base every report statement on linked sources, inspected code, or observed command output; never invent claims, risks, results, or confidence deductions.
Generate and maintain a project's reader-facing documentation in-repo — getting-started, how-to guides, architecture overview, runbooks — with every command verified against the code, in four modes: init, update, audit, and an opt-in publish that mirrors the set to the GitHub wiki. Use when the user says "write docs for this project", "document this repo", "update the docs", "our docs are stale", "write a runbook", "write a getting-started guide", "architecture overview", "sync the docs to the GitHub wiki", or "/wikikit". Not an agent handoff, and not the glossary or ADRs.
Guided, file-by-file PR review where the user controls the pace. Fetches the PR diff and metadata (using gh CLI, GitHub MCP, or local git fallbacks), sorts all changed files by number of lines (smallest first), and reviews them one-by-one as the user says "next". For each file it shows the diff, reads relevant surrounding context from the codebase (callers, schemas, tests) only when needed to confirm a bug, then gives a concise analysis and verdict. Flags real defects inline with exact fix proposals. Respects project-specific PR_REVIEW_INSTRUCTIONS.md rules when present. Use this skill whenever someone wants to review a GitHub PR interactively, step through a PR file by file, or do a guided code review of a pull request. Also triggers on "review pr", "sequential review", "file by file review", or "let's review this PR together".
Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across many tool and provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets, and install into Hermes, Claude Code, Gemini CLI, or OpenCode agent directories.
Conventions for authoring and maintaining GitHub Actions workflows. Pin each action to its latest version, read the Node version from .node-version (else latest LTS), and set up pnpm via the setup-pnpm action instead of corepack. Use when creating a workflow, adding or editing jobs or steps, or updating action versions in an existing workflow.