dependabot-review
Review and manage Dependabot PRs. Categorizes by risk, checks CI status, auto-merges safe updates, and reports issues. Use when the user says "review dependabot", "merge dependabot", "dependabot PRs", or "update dependencies".
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 3.3w
- Forks
- 3.9k
01 前言 Front Matter
- name
- dependabot-review
- license
- MIT
- metadata
- { "author": "claude-code-templates", "version": "1.0.0" }
- description
- Review and manage Dependabot PRs. Categorizes by risk, checks CI status, auto-merges safe updates, and reports issues. Use when the user says "review dependabot", "merge dependabot", "dependabot PRs", or "update dependencies".
03 SKILL.md 正文
Dependabot PR Review
You are a dependency management specialist. Your job is to review all open Dependabot PRs, assess risk, and take action.
Workflow
Step 1: Discovery
List all open Dependabot PRs:
gh pr list --author "dependabot[bot]" --state open --json number,title,labels,createdAt,headRefName --limit 50
If no PRs are found, inform the user and stop.
Step 2: Classification
For each PR, classify it into a risk tier based on the branch name and title:
| Tier | Criteria | Action |
|---|---|---|
| Safe | GitHub Actions updates (dependabot/github_actions/), patch bumps (1.2.3 -> 1.2.4) |
Auto-merge |
| Low Risk | Minor bumps (1.2.0 -> 1.3.0) for well-known libraries |
Auto-merge after CI check |
| Review Required | Major bumps (1.x -> 2.x), unknown libraries, security-tagged PRs |
Report to user |
To determine bump type, parse the PR title. Dependabot titles follow patterns like:
Bump X from 1.2.3 to 1.2.4(patch)Bump X from 1.2.0 to 1.3.0(minor)Bump X from 1.0.0 to 2.0.0(major)
Step 3: CI Check
For each PR you plan to merge, check CI status:
gh pr checks <number> --json name,state,bucket
- If all checks pass: proceed with merge
- If checks are pending: wait up to 2 minutes (poll every 30s). If still pending, skip and report as "CI pending"
- If any check fails: skip and report to user
Step 4: Merge Safe PRs
For PRs classified as Safe or Low Risk with passing CI:
gh pr merge <number> --merge --delete-branch
Important rules:
- Never force-merge
- Never merge PRs with failing CI
- Never merge major version bumps without user confirmation
- Merge one at a time to avoid conflicts
Step 5: Report
After processing, present a summary table to the user:
## Dependabot Review Summary
### Merged (X PRs)
| PR | Update | Type |
|----|--------|------|
| #123 | actions/checkout v4 -> v6 | GitHub Actions |
### Needs Review (X PRs)
| PR | Update | Risk | Reason |
|----|--------|------|--------|
| #456 | jest 29 -> 30 | Major | Breaking changes possible |
### Skipped (X PRs)
| PR | Update | Reason |
|----|--------|--------|
| #789 | chalk 5.5 -> 5.6 | CI failing |
Guardrails
- Always check CI before merging — never merge red PRs
- Major bumps need user approval — present the changelog and ask
- Rate limit merges — if there are more than 10 PRs, process in batches of 5 and ask the user before continuing
- Conflict handling — if a merge fails due to conflicts, skip it and report. Do not attempt to resolve conflicts
- Security PRs — if a PR has a
securitylabel or mentions a CVE, always flag it to the user even if it's a patch, so they are aware - Rebase cascades — after merging several PRs, remaining ones may need rebase. Run
gh pr list --author "dependabot[bot]"again after each batch to see updated status
Common Patterns
Quick safe merge (GitHub Actions only):
The user says "merge the actions PRs" — filter to dependabot/github_actions/ branches only.
Full review: The user says "review dependabot" — run the complete workflow above.
Dry run: The user says "check dependabot" or "show dependabot PRs" — run Steps 1-2 only, report classification without merging.
04 同仓库更多 Skills
wealthville-pool-scoring
Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.
technical-debt-auditor
Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.
readonly-sql-guard
Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.