بنقرة واحدة
github-toolkit
// GitHub issue triage, issue creation, PR review, and CI check-fix workflows using gh CLI.
// GitHub issue triage, issue creation, PR review, and CI check-fix workflows using gh CLI.
| name | github-toolkit |
| description | GitHub issue triage, issue creation, PR review, and CI check-fix workflows using gh CLI. |
Use this skill for GitHub-specific workflows.
When invoked, choose one mode:
If intent is unclear, ask for the mode before acting.
Use when the user provides raw notes, logs, dictation, or screenshots and wants a ready-to-file GitHub issue.
/issues/ as YYYY-MM-DD-short-description.md unless the user
requests another destination.## Summary
## Environment
- **Product/Service**:
- **Region/Version**:
- **Browser/OS**: (if relevant)
## Reproduction Steps
1. [Step]
## Expected Behavior
## Actual Behavior
## Error Details
`[error text / logs if present]`
## Visual Evidence
[attachment references]
## Impact
[Critical/High/Medium/Low + short rationale]
## Additional Context
Use when the user asks to find issues, recommend issues to work on, audit open issues, compare labels, or inspect issue activity in a GitHub repository.
Read issue-triage.md before running searches. It
contains the current gh command patterns, field-name quirks, and reporting
checklist for efficient issue discovery.
Use for review-comment triage or high-signal review of the PR associated with the current branch.
gh auth statuspython "<path-to-skill>/scripts/fetch_comments.py"AGENTS.md, CONTRIBUTING.md, CLAUDE.md, and any changed-path
local instruction files that exist.If auth/rate limiting fails, ask the user to rerun gh auth login and retry.
When asked to provide a review, prioritize only issues that are highly likely to matter:
Do not flag style, subjective quality, pre-existing problems, speculative edge cases, or issues a normal linter would catch unless the repository instructions explicitly require it. Validate each issue against the diff and relevant local instructions before posting. Treat contribution and commit standards as review inputs when they are documented in repository guidance.
For inline comments:
If no issues are found and commenting is requested, post:
## Code review
No issues found. Checked for bugs and repository instruction/contribution
compliance.
Use for failing checks in the PR linked to the current branch (or provided PR).
gh auth statusgh pr view --json number,url or user-provided PR
number/URL.python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<num-or-url>"--json when machine-friendly output is needed.If gh pr checks field shape changes, rerun with reported accepted fields.
Nix operational playbooks for package diffs, build debugging, closure analysis, dependency forensics, flake maintenance, and evaluation performance tuning. Use when comparing Nix build outputs, diagnosing derivation failures, finding unexpected runtime/build dependencies, inspecting closure size, maintaining flakes, or profiling slow NixOS/Home Manager/Nixvim evaluation.
Write idiomatic and maintainable Nix code. Use when creating or refactoring Nix expressions, Home Manager or NixOS modules, overlays, packages, and flake outputs, especially when deciding module merge semantics, binding locality, option defaults, and conditional structure.
Neovim Lua plugin development playbooks — project architecture, self lazy-loading, vim.g configuration, scoped commands and <Plug> keymaps, health checks, type-safe tooling, busted testing, and LuaRocks distribution. Use when writing or refactoring a Neovim Lua plugin, designing vim.g/setup config, deciding command/keymap APIs, adding checkhealth, configuring lua-ls/luacheck/stylua/LuaCATS, or setting up busted/nlua tests and SemVer LuaRocks releases.
Use for working with Jujutsu (jj) history workflows, including hunk-level split/squash/diffedit/restore via `jj-hunk-tool`.
Consolidates ultra-compressed communication, commit-message generation, PR review notes, and memory compression into one progressive-disclosure skill.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).