Gitcrawl provides a freshness-aware GitHub archive workflow for finding issues, triaging pull requests, and identifying duplicate discussion clusters safely.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gitcrawl
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install gitcrawl using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Gitcrawl?
Gitcrawl is an Openclaw Skills utility for searching local GitHub issue and pull request archives before querying GitHub live. It checks archive freshness, finds related threads, searches open issues, and groups similar discussions into duplicate clusters.
The skill also provides a cached and live pull request status workflow through a gh-compatible shim. It helps developers make better triage decisions by combining repository history with live verification, while requiring explicit evidence before commenting, labeling, closing, reopening, merging, or filing reviews.
Gitcrawl Use Cases
- Search archived GitHub issues and pull requests before performing a live repository search.
- Check whether a local archive is fresh enough for reliable issue or PR triage.
- Find neighboring issues and pull requests related to a known thread.
- Identify duplicate or highly similar issue clusters and inspect cluster details.
- Review cached pull request status before deciding whether live verification is necessary.
- Confirm live PR, issue, review, comment, file, and status-check data before mutation or merge decisions.
- Produce traceable reports containing repository names, issue or PR numbers, cluster IDs, absolute dates, and source gaps.
How Gitcrawl Works
- Run
gitcrawl doctor --jsonto inspect archive health and freshness before relying on local data. - Search the local archive for candidate issues or pull requests using thread lookup, neighboring-thread discovery, or issue search.
- Use
gitcrawl clustersandgitcrawl cluster-detailto identify and inspect groups of potentially duplicate discussions. - Start PR triage with cached
gitcrawl gh pr statusorgitcrawl gh pr viewdata to minimize unnecessary live requests. - Escalate to
gitcrawl gh --liveand the liveghCLI when status, merge state, comments, reviews, files, or checks must be current. - Compare the candidate discussion's intent with live repository evidence; similarity alone is not sufficient for an action.
- Report exact repository names, issue or PR numbers, cluster IDs, absolute dates, and any missing or stale sources.
- Perform comments, labels, closures, reopenings, merges, or PR reviews only after live verification and checkout or repository-state proof.
Gitcrawl Setup
Install Gitcrawl through Go using the module declared by the skill:
go install github.com/openclaw/gitcrawl/cmd/gitcrawl@latest
Confirm that the binary is available on your PATH, then validate the archive before searching:
gitcrawl doctor --json
For live verification workflows, install and authenticate the GitHub CLI separately, then use gh pr view or gh issue view for authoritative mutation and merge decisions:
gh auth status
gh pr view <number> --json number,title,state,mergedAt,body,files,comments,reviews,statusCheckRollup
gh issue view <number> --json number,title,state,body,comments,closedAt
The skill requires the gitcrawl executable. Its declared project homepage is https://github.com/openclaw/gitcrawl.
Gitcrawl Data Schema & Taxonomy
Gitcrawl organizes repository intelligence around archived threads, search results, PR status, and similarity clusters.
| Data area | Key fields or identifiers | Purpose |
|---|---|---|
| Freshness diagnostics | Doctor status and JSON diagnostics | Establish whether local archive data is safe to use |
| Threads | Repository, issue or PR number, title, URL, state | Retrieve a known discussion, including closed items when requested |
| Search results | Query, repository, state, number, title, URL | Find candidate issues from the local archive |
| Neighbors | Repository, source number, related thread results, limit | Discover nearby or contextually related discussions |
| Clusters | Repository, cluster ID, size, sort order | Group potentially duplicate issues or PRs |
| PR status | Number or URL, title, state, draft status, head ref, head SHA | Support cached or live pull request triage |
| Live verification | Body, files, comments, reviews, merge timestamp, status checks | Provide authoritative evidence before repository mutations |
Commands support JSON output for structured processing, including --json number,title,url and detailed PR fields. Reports should preserve absolute dates, repository names, issue or PR numbers, cluster IDs, and explicit source gaps rather than relying on ambiguous relative descriptions.
Gitcrawl Advanced Features
- Freshness-first archive diagnostics with
gitcrawl doctor --json. - Local-first issue and PR search that reduces unnecessary live GitHub requests.
- Neighbor discovery for contextual thread analysis.
- Duplicate detection through sortable clusters and cluster-detail inspection.
- Cached PR status through the
gitcrawl ghshim, with explicit--liveescalation. - Structured JSON output suitable for automation, indexing, and downstream agent workflows.
- Separate evidence paths for read-only triage and high-risk repository mutations.
- Live GitHub CLI verification covering PR state, merge timestamps, files, comments, reviews, and status checks.
- Guardrails that reject closing or labeling based on similarity alone and require matching intent plus live verification.
- Reporting conventions that expose stale data, missing sources, exact identifiers, and date context for reliable Openclaw Skills automation.
SKILL.md
Loading
Related Openclaw Skills
Frontend UI Engineer
Frontend UI Engineer automates production-quality, accessible, responsive UI development and related engineering workflows with structured outputs and built-in error recovery.
Publish Webpage
Publish Webpage turns a user's idea into a polished, shareable static website and deploys it to goclawgo without requiring code or hosting knowledge.
idea-refine
idea-refine transforms raw, ambiguous ideas into structured, actionable concepts through automated analysis, assumption testing, and refinement.
interview-me
Interview-me turns vague requests into structured, actionable intent through an adaptive one-question-at-a-time interview.
doc-consistency
An offline document QA skill that finds internal consistency errors in long DOCX, Markdown, and TXT files and produces a repeatable re-check command.
A-Share Financial Literacy Q&A
An AI-powered A-share financial literacy assistant that explains market concepts, personalizes learning, analyzes risk, and supports simulation-based investment research.
Featured*
