ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

cross-ref

Cross-reference GitHub PRs and issues to find duplicates and missing links. Spawns parallel Sonnet subagents to semantically analyze the last N PRs and issues, finding PRs that solve the same problem (duplicates) and issues resolved by open PRs but not yet linked. Groups findings into thematic clusters, scores them by actionability, and offers rate-limited commenting or bulk actions (close, label). Use this skill when the user wants to find duplicate PRs, link issues to PRs, clean up a repo's cross-references, or audit PR/issue relationships. Also useful when the user says things like "find related PRs", "which PRs fix this issue", "are there duplicate PRs", "link issues and PRs", or "audit cross-references".

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/glucksberg/cross-ref
Or

Cross-Ref: PR & Issue Linker

You find hidden connections between PRs and issues that humans miss at scale. The core loop is: fetch → analyze in parallel → cluster → verify → report → act.

Before doing anything, read references/principles.md. Those rules override everything in this file when there's a conflict.

Overview

Repos accumulate duplicate PRs and orphaned issue→PR links over time. Manual cross-referencing doesn't scale past a few dozen items. This skill uses parallel Sonnet subagents to analyze up to 1000 PRs and 1000 issues simultaneously, finding two kinds of links:

  1. Duplicate PRs — PRs that address the same bug or feature (even with different approaches or wording)
  2. Issue→PR links — Open issues that already have a PR solving them but no explicit "fixes #N" reference

Results are grouped into thematic clusters, scored by actionability, and presented with available actions (comment, close, label) — not just as a flat list of pairs.

Configuration

The user provides these at invocation time (ask if not given):

ParameterDefaultDescription
repo(ask)GitHub owner/repo to analyze
pr_count1000How many recent PRs to scan
issue_count1000How many recent issues to scan
pr_stateallPR state filter: open, closed, all
issue_stateopenIssue state filter: open, closed, all
batch_size50PRs per subagent batch
confidence_thresholdmediumMinimum confidence to include in report: low, medium, high
modeplanplan = report only (default, always start here). execute = act on findings.

Default mode is plan (dry-run). The skill always starts by generating the report. The user must explicitly choose to execute actions after reviewing the findings. This matters because actions can't be undone.

Workflow

Phase 1: Data Collection

Fetch PR and issue metadata from the GitHub API. This phase is deterministic and uses the shell script — no AI needed.

scripts/fetch-data.sh <owner/repo> <workspace_dir> [pr_count] [issue_count] [pr_state] [issue_state]

This produces:

  • workspace/prs.json — Full PR metadata
  • workspace/issues.json — Full issue metadata (PRs filtered out)
  • workspace/existing-refs.json — Pre-extracted explicit cross-references
  • workspace/pr-index.txt — Compact one-line-per-PR index
  • workspace/issue-index.txt — Compact one-line-per-issue index

The existing references map captures what's already linked (via "fixes #N", "closes #N", etc.) so subagents can focus on what's missing.

Phase 2: Parallel Analysis (Sonnet Subagents)

This is where the intelligence happens. Split PRs into batches and spawn parallel Sonnet subagents. Each subagent receives:

Metadata

Stars2387
Views1
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-glucksberg-cross-ref": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

issue-prioritizer

Prioritize GitHub issues by ROI, solution sanity, and architectural impact. Use when triaging or ranking issues to identify quick wins, over-engineered proposals, and actionable bugs. Don't use when managing forks (use fork-manager) or general GitHub queries (use github). Read-only — never modifies repositories.

glucksberg 2387

fork-manager

Manage forks with open PRs - sync upstream, rebase branches, track PR status, and maintain production branches with pending contributions. Supports automatic conflict resolution via --auto-resolve flag (spawns AI subagents to resolve rebase conflicts). Use when syncing forks, rebasing PR branches, building production branches that combine all open PRs, reviewing closed/rejected PRs, or managing local patches kept outside upstream. Requires Git and GitHub CLI (gh).

glucksberg 2387

pr-ship

Pre-ship risk report for OpenClaw PRs. Dynamically explores the codebase to assess module risk, blast radius, and version-specific gotchas. Scores each finding by severity (🟢/🟡/🔴). Updated frequently with the latest OpenClaw version context — run `clawhub update pr-ship` regularly to stay current.

glucksberg 2387

anti-pattern-czar

Detect and fix TypeScript error handling anti-patterns with state persistence and approval workflows. Use when scanning a codebase for silent error failures, empty catches, promise swallowing, or unlogged errors. Supports five modes — scan (detect all issues), review (interactive fix session), auto (batch fix with guardrails), resume (continue from last session), report (show progress). Triggers on phrases like 'scan for anti-patterns', 'fix error handling', 'find empty catches', 'anti-pattern czar', or 'check error handling'.

glucksberg 2387

pr-review

Find and fix code issues before publishing a PR. Single-pass review with auto-fix. Use when reviewing code changes before submission or auditing existing code for bugs/security. Don't use when running a coding agent to write code (use coding-agent) or checking GitHub CI status (use github).

glucksberg 2387