Skip to content

PDFCLOUD-5575 Add PR Review Auditor skill#23

Merged
datalogics-cgreen merged 6 commits intopdfrest:mainfrom
datalogics-kam:pdfcloud-5575-add-pr-auditor-skill
Feb 10, 2026
Merged

PDFCLOUD-5575 Add PR Review Auditor skill#23
datalogics-cgreen merged 6 commits intopdfrest:mainfrom
datalogics-kam:pdfcloud-5575-add-pr-auditor-skill

Conversation

@datalogics-kam
Copy link
Copy Markdown
Contributor

@datalogics-kam datalogics-kam commented Feb 9, 2026

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

  • Adds a new skill: .agents/skills/pr-review-auditor/ with:
    • SKILL.md workflow for findings-first, severity-ordered PR reviews
    • policy precedence rules (*GUIDELINES*.md before AGENTS.md)
    • required review outputs (rule coverage matrix, extraction summary, remediation plan)
  • Adds helper scripts to automate review context and range inspection:
    • collect_pr_context.sh to detect PR/base/range, changed files, and policy files
    • review_range.sh to print full commit messages, file summaries, and patches for a range
  • Adds skill metadata in .agents/skills/pr-review-auditor/agents/openai.yaml for discoverability/default invocation.
  • Adds a compact checklist reference at .agents/skills/pr-review-auditor/references/review-checklist.md.
  • Updates contributor policy docs:
    • 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

  • Reviews can be run with a repeatable base..HEAD process and consistent evidence standards.
  • Review outputs are easier to action due to structured severity ordering and explicit policy citations.
  • Validation guidance is clearer on what belongs in mocked/unit tests vs. live tests.
  • No runtime API behavior changes to the client library are introduced by this branch.

CI / Workflow Impact

  • No GitHub Actions workflow files are changed.
  • This branch changes process/tooling/docs only:
    • adds local review scripts and skill assets
    • updates reviewer/contributor guidance for validation expectations.

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.

- 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
@datalogics-kam datalogics-kam force-pushed the pdfcloud-5575-add-pr-auditor-skill branch from ab9717e to 75fc1b8 Compare February 9, 2026 22:06
- 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 datalogics-cgreen merged commit 8563cd7 into pdfrest:main Feb 10, 2026
14 checks passed
@datalogics-kam datalogics-kam deleted the pdfcloud-5575-add-pr-auditor-skill branch February 10, 2026 16:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants