PDFCLOUD-5575 Add PR Review Auditor skill#23
Merged
datalogics-cgreen merged 6 commits intopdfrest:mainfrom Feb 10, 2026
Merged
Conversation
- Introduced a new skill, `pr-review-auditor`, for rigorous PR reviews. - Added `SKILL.md` with detailed guidelines, rules, and review workflow. - Configured agent interface with `openai.yaml` to standardize usage. - Provided a policy checklist (`review-checklist.md`) for compliance enforcement. - Implemented helper scripts: - `collect_pr_context.sh` for deriving PR context and policy inventory. - `review_range.sh` for in-depth commit and diff analysis. Assisted-by: Codex
- Updated `AGENTS.md` with `pytest -n auto` to simplify parallel test configuration. - Enhanced guidance for endpoint/server option testing: - Unit tests for `extra_query`, `extra_headers`, `extra_body`, and `timeout`. - Live tests only required for server-observable effects. - Expanded `TESTING_GUIDELINES.md` to clarify customization validation. - Mocked tests handle request customization. - Live tests validate server-specific behaviors when applicable. Assisted-by: Codex
- Updated `.agents/skills/pr-review-auditor/SKILL.md` to use canonical script paths (`.agents/skills/pr-review-auditor/scripts/*`) for consistency. - Clarified script usage instructions under "Workflow" and "Resources." - Added guidance to avoid emitting fallback path chatter during execution. Assisted-by: Codex
ab9717e to
75fc1b8
Compare
- Updated `SKILL.md` and `review-checklist.md` to replace `origin/<base>` references with `<base_remote>/<base>` for generality. - Adjusted `review_range.sh` usage example to illustrate `upstream/main..HEAD`. Assisted-by: Codex
- Updated AGENTS.md to allow private module imports in tests when required for validating request serialization or server-facing payload contracts. - Emphasized preference for public modules in tests whenever possible. Assisted-by: Codex
- Introduced a "Code Quality Checklist" with steps for formatting, linting, and type checking without runtime tests. - Added a "Test Validation Checklist" for running focused and full compatibility tests, including new coverage validation steps. - Clarified the distinction between code quality checks and runtime validations. Assisted-by: Codex
datalogics-cgreen
approved these changes
Feb 10, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PDFCLOUD-5575
Why
This PR introduces a reusable PR-audit skill and aligns repository guidance so reviews are more consistent, policy-aware, and easier to reproduce.
The goal is to reduce missed correctness/test/CI issues by standardizing both review workflow and validation expectations.
What This Delivers
.agents/skills/pr-review-auditor/with:SKILL.mdworkflow for findings-first, severity-ordered PR reviews*GUIDELINES*.mdbeforeAGENTS.md)collect_pr_context.shto detect PR/base/range, changed files, and policy filesreview_range.shto print full commit messages, file summaries, and patches for a range.agents/skills/pr-review-auditor/agents/openai.yamlfor discoverability/default invocation..agents/skills/pr-review-auditor/references/review-checklist.md.AGENTS.md: adds explicit code-quality and test-validation checklists, updates pytest parallelism guidance (-n auto), clarifies private-module import policy (strict in production, limited exceptions in tests), and clarifies customization validation placement.TESTING_GUIDELINES.md: clarifies that transport plumbing customization (extra_query,extra_headers,extra_body,timeout) is primarily a unit-test concern unless server-observable behavior is being validated live.Outcomes / Effect
CI / Workflow Impact
Risk
Low to medium.
Production runtime behavior is unchanged, but team workflow expectations become stricter, and the new scripts rely on local git/gh context for review automation.