github-ops
Original:🇺🇸 English
Translated
3 scripts
Workflow for repository reconnaissance and operations using GitHub CLI (gh). Optimizes token usage by using structured API queries instead of blind file fetching.
2installs
Sourceoimiragieo/agent-studio
Added on
NPX Install
npx skill4agent add oimiragieo/agent-studio github-opsTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →GitHub Ops Skill
Provides structured guidance for repository reconnaissance using and .
gh apigh searchOverview
Repository reconnaissance often fails when agents guess file paths or attempt to fetch large files blindly. This skill enforces a structured sequence using the GitHub CLI to minimize token waste and improve reliability.
Map -> Identify -> Fetch⚡ Essential Reconnaissance Commands
Use these commands to understand a repository structure before fetching content.
1. List Repository Root
bash
gh api repos/{owner}/{repo}/contents --jq '.[].name'2. List Specific Directory
bash
gh api repos/{owner}/{repo}/contents/{path} --jq '.[].name'3. Fetch File Content (Base64 Decoded)
bash
gh api repos/{owner}/{repo}/contents/{path} --jq '.content' | base64 -d4. Search for Pattern in Repository
bash
gh search code "{pattern}" --repo {owner}/{repo}5. Get Repository Metadata
bash
gh repo view {owner}/{repo} --json description,stargazerCount,updatedAt🔄 Token-Efficient Workflow
- Map Tree: List the root and core directories (,
commands,src).docs - Identify Entrypoints: Look for ,
README.md,gemini-extension.json, orpackage.json.SKILL.md - Targeted Fetch: Download only the entrypoints first.
- Deep Dive: Use to find logic patterns rather than reading every file.
gh search code
🛡️ Platform Safety (Windows)
- When using , ensure the output is redirected to a file using the
base64 -dtool if it's large.Write - Avoid Linux-style patterns in complex pipes.
/dev/stdin - Use native paths for any local storage.
Assigned Agents
- artifact-integrator: Lead agent for repository onboarding.
- developer: PR management and exploration.
Memory Protocol (MANDATORY)
Before starting:
Read
.claude/context/memory/learnings.mdAfter completing:
- New pattern ->
.claude/context/memory/learnings.md - Issue found ->
.claude/context/memory/issues.md - Decision made ->
.claude/context/memory/decisions.md
ASSUME INTERRUPTION: If it's not in memory, it didn't happen.