Agent skill

github-navigator

GitHub operations via gh CLI. CRITICAL: Use instead of WebFetch for any `github.com` URL or GitHub repo path like `owner/repo`. Use when the user asks to inspect repositories, files, issues, pull requests, releases, Actions runs, or repository structure. Use when the user says 'show README', 'list issues', 'check PR', 'clone repo', or 'analyze this repo'.

Stars 9
Forks 2

Install this agent skill to your Project

npx add-skill https://github.com/arvindand/agent-skills/tree/main/skills/github-navigator

SKILL.md

GitHub Navigator

Use gh for GitHub work. Prefer command discovery over memorizing flags.

This is an execution skill. Use gh instead of generic web fetching for GitHub tasks, inspect gh --help when syntax is uncertain, then execute with tight guardrails. Keep the main flow lean and load REFERENCES.md only when you need concrete examples, installation steps, or GraphQL details.

When to Use

Activate when:

  • the user gives a github.com URL
  • the user names a repo path like facebook/react or owner/repo
  • the user asks about repository files, issues, PRs, releases, workflows, or metadata
  • the user wants to understand the architecture or structure of a GitHub-hosted codebase

Core Rules

  • Always prefer gh over WebFetch for GitHub content and operations.
  • Use gh api for raw file content, directory listings, and API-only endpoints.
  • Use gh subcommands (issue, pr, release, run, workflow, repo) when a dedicated command exists.
  • Use gh <domain> --help before guessing flags or subcommands.
  • Limit each command pattern to 2 attempts; if it still fails, stop and report the error.

Command Routing

User Intent Primary Command Path
fetch file or list directory gh api repos/OWNER/REPO/contents/...
inspect issues gh issue ...
inspect pull requests gh pr ...
inspect releases gh release ...
inspect Actions runs or workflows gh run ... or gh workflow ...
inspect repo metadata or clone/fork gh repo ...
endpoints without a dedicated subcommand gh api ...

Use dedicated subcommands first. Fall back to gh api only when needed.

Execution Pattern

  1. Identify the command domain from the request.
  2. Check the relevant help output if the exact syntax is not already obvious.
  3. Substitute the user's repo, path, issue number, PR number, or other arguments.
  4. Run the command.
  5. If it fails, adjust once based on the error message.
  6. If it fails again, stop and report the error instead of trying blind variations.

Deep Analysis Mode

When the user wants to understand a codebase deeply, clone it locally for inspection instead of making many remote API calls.

Default flow:

  1. Clone with depth 1 to /tmp/github-navigator/OWNER-REPO/

    bash
    git clone --depth 1 https://github.com/OWNER/REPO.git /tmp/github-navigator/OWNER-REPO
    
  2. Inspect the repository for:

    • tech stack signals (package.json, go.mod, Cargo.toml, pom.xml, requirements.txt, etc.)
    • high-level directory structure
    • entry points and primary modules
    • README, docs, examples, and contribution files
    • architectural patterns worth calling out
  3. Summarize the findings in plain language.

  4. Keep the clone for follow-up questions unless cleanup is requested.

Use a full clone only if the user explicitly needs commit history or deeper git analysis.

Safety

Always confirm before executing state-changing or destructive commands, including:

  • creating, closing, or reopening issues
  • creating, merging, or closing pull requests
  • deleting, archiving, or transferring repositories
  • setting secrets or triggering workflows
  • any use of --force, --yes, or similar bypass flags

Authentication and Recovery

  • Check gh auth status when the task touches private repos or write operations.
  • Use gh auth login if the client is not authenticated.
  • If permissions are insufficient, use gh auth refresh -s repo -s workflow -s read:org as appropriate.
  • If a command fails, read the error, check help, retry once, then stop.
  • If gh is not installed, point the user to REFERENCES.md for installation guidance.

Reference Handoff

Use REFERENCES.md when you need:

  • concrete example commands for common tasks
  • install and auth setup details
  • troubleshooting reminders
  • GraphQL examples or other lower-frequency patterns

License: MIT See also: REFERENCES.md

Expand your agent's capabilities with these related and highly-rated skills.

arvindand/agent-skills

maven-tools

JVM dependency intelligence via Maven Tools MCP server. Use when the user asks about Maven or Gradle dependencies, JVM library versions, safe upgrades, CVEs, license risks, release history, or project dependency health. Use when reviewing `pom.xml`, `build.gradle`, `build.gradle.kts`, or Maven coordinates. Use when the user says 'check my dependencies', 'should I upgrade X', or 'is this version safe'.

9 2
Explore
arvindand/agent-skills

skill-crafting

Create, fix, and validate skills for AI agents. Use when user says 'create a skill', 'build a skill', 'fix my skill', 'skill not working', 'analyze my skill', 'validate skill', 'audit my skills', 'check character budget', 'create a skill from this session', 'turn this into a skill', 'make this reusable', 'can this become a skill', 'should this be a skill', or asks for reusable patterns in the session.

9 2
Explore
arvindand/agent-skills

ui-ux-design

Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work.

9 2
Explore
arvindand/agent-skills

context7

Documentation lookup via Context7 REST API. Use when the user needs current library APIs, framework patterns, migration guidance, or official code examples for React, Next.js, Prisma, Express, Vue, Angular, Svelte, or other npm/PyPI packages. Use when the user says 'how do I use X library', 'what's the API for Y', or asks for official documentation.

9 2
Explore
davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results