npx skills add openclaw/openclaw --skill gitcrawl
steipete/openclaw · Archived
gitcrawl
Use gitcrawl for OpenClaw issue and PR archive search, duplicate discovery, related-thread clustering, and local GitHub mirror freshness checks.
Installation
npx skills add steipete/openclaw --skill gitcrawl
Stronger alternatives
This repository is archived — consider an actively maintained alternative.
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane outpu…
2 installsLocal speech-to-text with the Whisper CLI (no API key).
2 installsList, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or s…
2 installsUse xurl for authenticated X API posts, replies, search, DMs, media upload, followers, or raw v…
1 installsSimilar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Also in this package
Other skills from steipete/openclaw · top by installs.
npx skills add steipete/openclaw
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Also listed on
Alternate registries and mirrors of this skill.
npx skills add openclaw/gitcrawl --skill gitcrawl
Repository health
main
Skill metadata
Parsed from SKILL.md frontmatter.
More metadata
- openclaw
- {"requires":{"bins":["gitcrawl"]}}
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md2,607 B -
docs
SUMMARY.md160 B
History
- First seen on skills.sh
- First recorded snapshot · 1 installs
SKILL.md
Gitcrawl
Use this skill before live GitHub search when triaging OpenClaw issues or PRs.
gitcrawl is the local candidate-discovery layer. It is fast, includes open and closed threads, and can surface duplicate attempts, related issues, and already-landed fixes. It is not the final source of truth for comments, labels, merges, closes, or current CI.
Default Flow
- Check local state:
gitcrawl doctor --json
- Read the target from the local archive:
gitcrawl threads openclaw/openclaw --numbers <issue-or-pr-number> --include-closed --json
- Find related candidates:
gitcrawl neighbors openclaw/openclaw --number <issue-or-pr-number> --limit 12 --json
gitcrawl search openclaw/openclaw --query "<scope or title keywords>" --mode hybrid --limit 20 --json
- Inspect relevant clusters:
gitcrawl cluster-detail openclaw/openclaw --id <cluster-id> --member-limit 20 --body-chars 280 --json
- Verify anything actionable with live GitHub and the checkout:
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
Freshness Rules
- Treat
gitcrawlas stale ifdoctorshows no target thread, an oldlastsyncat, missing embeddings for neighbor/search commands, or a clearly wrong open/closed state. - If stale data blocks the decision, refresh the portable store first:
gitcrawl init --portable-store [email protected]:openclaw/gitcrawl-store.git --json
- Run expensive update commands such as
gitcrawl sync --include-commentsonly when the user asked to update the local store or stale data is blocking the decision. - The sync default is all GitHub thread states; pass
--state open,--state closed, or--state allonly when a task requires a narrower or explicit scope.
Boundaries
- Use
gitcrawlfor candidates, clusters, and historical context. - Use
gh,gh api, and the current checkout for live state before commenting, labeling, closing, reopening, merging, or filing a PR review. - Do not close or label based only on
gitcrawlsimilarity. Require matching problem intent plus live verification. - If
gitcrawlis unavailable, say so and fall back to targetedgh searchrather than blocking normal maintainer work.