Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Pr Audit

ASecurity

Triage open pull requests and issues: find easy-win PRs to merge, close stale or superseded ones, label and reply to issues. Use when the user says "audit open PRs", "triage PRs", "triage issues", "close stale PRs", "what can we merge", "clean up the issue tracker", or runs /theo-mode prs. Requires the gh CLI authenticated for the repo.

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashgitsecurity

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add al3rez/theo-mode --skill pr-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pr Audit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pr Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/al3rez-pr-audit/badge)](https://www.skillsdirectory.com/skills/al3rez-pr-audit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: pr-audit
description: >
  Triage open pull requests and issues: find easy-win PRs to merge, close
  stale or superseded ones, label and reply to issues. Use when the user says
  "audit open PRs", "triage PRs", "triage issues", "close stale PRs", "what
  can we merge", "clean up the issue tracker", or runs /theo-mode prs.
  Requires the gh CLI authenticated for the repo.
---

# PR / Issue Audit

Goal: a smaller, honest backlog. Every open item ends the session in one of
three states: merged, closed with a reason, or left open with a label that
says what it is waiting on.

## Step 0: inventory and scope

```bash
gh pr list --state open --limit 200 --json number,title,author,updatedAt,isDraft,mergeable,reviewDecision,labels
gh issue list --state open --limit 200 --json number,title,author,updatedAt,labels,comments
```

Report counts. If over ~50 items total, process in batches of 25, oldest
first, and report after each batch. Say this before starting.

## Step 1: bucket every PR

Read the diff (`gh pr diff N`) and the CI status (`gh pr checks N`). Put each
PR in exactly one bucket:

- **Easy win.** Small, green CI, does what the title says, no design
  decisions. Typo fixes, dep bumps, doc fixes, obvious bug fixes with a test.
- **Needs rebase.** Good change, conflicts with main. Try `gh pr checkout N
  && git rebase main`. If it rebases cleanly and CI passes, it becomes an
  easy win. If not, comment with the conflict summary and move on.
- **Superseded.** Another PR or a commit on main already did this. Link it.
- **Dead.** Author gone for 6+ months, no response to review, or the feature
  was rejected in discussion.
- **Real review needed.** Design change, security-relevant, large. Not for
  this session. Label it and list it for the human.

## Step 2: bucket every issue

- **Fixed already.** Search main and closed PRs for the symptom. Close with
  the commit or PR link.
- **Cannot reproduce / no info.** Older than 90 days, no repro, no response
  to a request for info. Close with a polite note inviting a reopen.
- **Duplicate.** Link the canonical one, close.
- **Easy fix.** Under an hour and you understand it. Fix it, open a PR,
  reference the issue. Cap this at 5 per session.
- **Real work.** Label (`bug`, `enhancement`, `needs-design`) and leave open.

## Step 3: present the plan, then execute

Print one table: number, title, bucket, action, one-line reason. Give the
user a chance to veto rows. Then execute every action with `gh`:

- Merge easy wins: `gh pr merge N --squash --delete-branch` (match the repo's
  existing merge style; check `git log` for merge vs squash).
- Close with reasons: `gh pr close N --comment "..."`, `gh issue close N
  --comment "..."`. The comment names the reason and how to reopen. Be kind;
  a real person wrote it.
- Label: `gh pr edit N --add-label ...`.

## Step 4: report

Counts per bucket, links for everything merged, and the "real review needed"
list for the human, ranked by how close to mergeable each one is.

## Do not

- Do not merge anything with red CI, no matter how small.
- Do not close a PR from an active contributor without a comment that tells
  them what would get it merged.
- Do not use a bot-sounding tone. Write the comment you would want to
  receive.

Attribution

al3rezal3rez
View sourceSee grades on GitHubMore from al3rez →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

697551 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →