pr-review-bot-loop
Drives your own PR to a clean automated-reviewer pass before you request human review: poll for the bot's verdict, triage what it posted and what it…
Skill by dgowrie
Chalk Labs
Need help deploying pr-review-bot-loop?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dgowrie-pr-review-bot-loop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/pr-review-bot-loop
What's inside
- Skill name
pr-review-bot-loop- Description
- Drives your own PR to a clean automated-reviewer pass before you request human review: poll for the bot's verdict, triage what it posted and what it suppressed, fix, push, re-request, repeat. Implements a five-signal adapter contract (re-request / pending? / landed? / clean? / suppressed?) against Copilot, whose real findings hide in a collapsed block in the review body where every other signal reports clean. Self-review only; it never touches someone else's PR and never merges. Trigger phrases: "drive this PR to a clean bot pass", "loop until Copilot is happy", "bot review loop", "did Copilot actually review the latest commit", "check for suppressed comments", "is this PR ready for human review", or explicit `/pr-review-bot-loop`.
- License
- unknown
- Instructions
- 399 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (3)
- SKILL.md
- copilot-signals.py · scripts/
- test_copilot_signals.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from dgowrie/claude-workflows
- 0.519score
github-api-mechanics
dgowrie
Non-obvious GitHub REST/GraphQL details that bite when scripting PRs and issues with `gh`: review-thread reply and resolve field names, sub-issue parent…
SkillBFreshness: BClaude Code +9 - 0.519score
pr-review
dgowrie
AI-assisted GitHub PR review that produces concise, copy-paste-ready draft comments with line references and code suggestions.
SkillBFreshness: BClaude Code +9 - 0.519score
author-review-guidance
dgowrie
Post review-guidance comments on your own PRs as a single review submission: a walkthrough as the review body, plus inline `:notebook:` comments threaded…
SkillBFreshness: BClaude Code +9 - 0.519score
codebase-design
dgowrie
Shared vocabulary for designing deep modules (module, interface, depth, seam, adapter, leverage, locality).
SkillBFreshness: BClaude Code +9 - 0.519score
pr-review-adversarial
dgowrie
Two-phase adversarial validation for PR review findings.
SkillBFreshness: BClaude Code +9 - 0.515score
pr-review-batching
dgowrie
Owns the submission lifecycle for PR review comments.
SkillBFreshness: BClaude Code +9 - 0.514score
explain-usage
dgowrie
Explain where this session's tokens went, with one simple chart in plain language.
SkillBFreshness: BClaude Code +9 - 0.511score
grilling
dgowrie
Decision-tree grilling loop for the architecture skills: walk a chosen candidate's decisions branch by branch, recommending an answer for each.
SkillBFreshness: BClaude Code +9 - 0.491score
domain-modeling
dgowrie
Build and sharpen a project's domain model (CONTEXT.md glossary, docs/adr/ decisions).
SkillBFreshness: BClaude Code +9 - 0.491score
improve-codebase-architecture
dgowrie
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillBFreshness: BClaude Code +9 - 0.469score
memory-audit
dgowrie
Review, consolidate, and prune a project's memory files.
SkillCFreshness: CClaude Code +9 - 0.469score
check-npm
dgowrie
Use when auditing a JavaScript/TypeScript repo's npm/yarn/pnpm package manager configuration for supply-chain hardening.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 67
- Last commit (this folder)
- Oct 9, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/dgowrie/claude-workflows
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dgowrie
- 0.519score
pr-review
dgowrie
AI-assisted GitHub PR review that produces concise, copy-paste-ready draft comments with line references and code suggestions.
SkillBFreshness: BClaude Code +9 - 0.519score
pr-review-adversarial
dgowrie
Two-phase adversarial validation for PR review findings.
SkillBFreshness: BClaude Code +9 - 0.519score
codebase-design
dgowrie
Shared vocabulary for designing deep modules (module, interface, depth, seam, adapter, leverage, locality).
SkillBFreshness: BClaude Code +9 - 0.519score
author-review-guidance
dgowrie
Post review-guidance comments on your own PRs as a single review submission: a walkthrough as the review body, plus inline `:notebook:` comments threaded…
SkillBFreshness: BClaude Code +9 - 0.519score
github-api-mechanics
dgowrie
Non-obvious GitHub REST/GraphQL details that bite when scripting PRs and issues with `gh`: review-thread reply and resolve field names, sub-issue parent…
SkillBFreshness: BClaude Code +9 - 0.515score
pr-review-batching
dgowrie
Owns the submission lifecycle for PR review comments.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get pr-review-bot-loop running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
pr-review-bot-loop skill. Agent Mart. https://agentmart.dev/skills/dgowrie-pr-review-bot-loop (last updated 2026-10-24)