approve-pr

Reviews pull requests against user stories, tests, and code quality checklists.

Updated May 1, 2026
One-click install
npx skills add https://github.com/ricardoo022/4dill --skill approve-pr-ricardoo022
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: approve-pr
Source: https://github.com/ricardoo022/4dill/tree/main/.gemini/skills/approve-pr
Command: npx skills add https://github.com/ricardoo022/4dill --skill approve-pr-ricardoo022

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Reviewing pull requests consistently is hard: reviewers must trace changes back to user story acceptance criteria, verify tests actually exercise real infrastructure instead of mocks, and catch security issues like SQL injection or LLM trust boundary violations. This Skill automates that entire review cycle and produces a structured APPROVE or REQUEST CHANGES verdict. ## Core Features & Use Cases - User Story Traceability: Extracts the US ID from the branch name, reads acceptance criteria and required tests from USER-STORIES.md, and verifies each item against the diff. - Real-Evidence Test Enforcement: Runs unit, integration, agent, and e2e pytest layers, blocking approval when runtime behavior is only validated with mocks instead of real PostgreSQL, Docker, Neo4j, or HTTP services. - Two-Pass Code Quality Review: Applies a critical pass (SQL safety, race conditions, LLM output trust, shell injection) and an informational pass (async/sync mixing, dead code, test gaps), auto-fixing mechanical issues. - Use Case: A developer opens PR #42 implementing US-055. Invoke the skill to fetch the diff, run the affected test layers, lint with ruff and mypy, check README co-changes, and receive a verdict with inline comments; on approval the user story is automatically marked DONE. ## Quick Start Ask the assistant to review PR 42 with the approve-pr skill and issue a verdict.

Frequently Asked Questions about approve-pr

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review a pull request against user story acceptance criteria?▼

Invoke the skill with a PR number or run it on the current branch. It extracts the US ID from the branch name, reads the acceptance criteria from docs/USER-STORIES.md, and checks each criterion against the diff before issuing a verdict.

How to verify PR tests use real infrastructure instead of mocks?▼

The skill enforces a real-evidence rule: runtime behavior must be validated with integration or e2e tests using real PostgreSQL, Docker, Neo4j, or HTTP services. Mock-only coverage for such behavior is recorded as a blocking finding unless justified as infeasible.

When are e2e tests required for a pull request?▼

E2e tests are required when a PR changes agent execution graphs, tool sets, controller flow, scan phases, or external system interactions. Documentation-only or pure refactoring PRs can mark e2e as N/A with justification.

What code quality issues does the review checklist catch?▼

The critical pass catches SQL injection, race conditions, LLM output trust boundary violations, and shell injection. The informational pass covers async/sync mixing, dead code, magic numbers, test gaps, and enum completeness.

What happens when a PR is approved?▼

On APPROVE, the skill automatically updates docs/USER-STORIES.md by adding (DONE) to the user story title and checking all acceptance criteria, required tests, and definition-of-done boxes.

Why was my PR rejected with REQUEST CHANGES?▼

REQUEST CHANGES is issued when any acceptance criterion is unmet, required tests are missing or failing, runtime behavior lacks real-infrastructure evidence, e2e tests are missing, ruff or mypy report errors, or critical checklist findings exist.