-
Notifications
You must be signed in to change notification settings - Fork 2
Development Workflow
A contributor-oriented navigation page for working on this
repository — not on either Skill's review behavior as a user. Every
rule here is owned by
AGENTS.md,
policies/,
and CONTRIBUTING.md —
this page links out rather than restating them.
Development of this repository has one canonical entrypoint:
AGENTS.md.
It states the global invariants (dedicated task branches, read-only Git
safety, clean task exit, one canonical home per rule) and routes each
task to the one focused policy under
policies/
that owns its detail.
CONTRIBUTING.md
defines three ownership classes, applied via GitHub Issue labels:
| Label | For |
|---|---|
good first issue |
A bounded task with an already-well-defined expected behavior — fixtures, docs, bounded tests, isolated tooling |
contributor-owned |
A whole capability whose boundaries/invariants/acceptance-criteria are defined but implementation approach is open |
maintainer-led |
Semantic/architectural contracts — finding identity, severity, decision derivation, evidence thresholds, cross-Skill contracts |
Full model:
policies/contribution-ownership-policy.md.
- Comment
/claimon an open, unclaimed issue with a contribution-ready label. - Fork, then create a branch named
<type>/<short-description>—feat/,fix/,docs/,test/,refactor/,chore/,research/. - Implement the issue without unrelated changes.
Full claim mechanics (bot behavior, churn protection, /unclaim):
CONTRIBUTING.md.
From the repository root:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements-dev.txt
python3 scripts/validate-skill-metadata.py skills/local-code-review --containment-root .
python3 scripts/validate-skill-metadata.py skills/github-pr-review --containment-root .
python3 scripts/validate-markdown-links.py
python3 -m unittest discover -s tests -t .
./scripts/package-skills.sh allRun one test module with, e.g.
python3 -m unittest tests.unit.review.test_decision_semantics. Test
suite layout (unit/, policy/, reference/, integration/) is
documented in tests/README.md.
Never edit CHANGELOG.md directly. A release-worthy change (it
touches shipped Skill content under skills//shared/, or the
packaging/distribution scripts) declares its intent as two lines in the
pull request description — Release category: and Release entry: —
checked by a deterministic classifier before merge. Everything else
declares Release category: none. Full convention:
docs/RELEASE.md,
policies/release-changelog-policy.md.
Opening a PR applies
.github/PULL_REQUEST_TEMPLATE.md
automatically. main is protected; every PR must satisfy repository
checks and review before an authorized maintainer merges it — claiming
an issue never bypasses that. Full merge/Git rules:
policies/git-pr-merge-policy.md.
- Documentation structure and layering (README vs.
docs/vs. policy):policies/documentation-policy.md - Skill packaging, runbook design, portability:
policies/skill-development-policy.md - Repository-owned Python style:
policies/python_scripts_coding_policy.md - Review orchestration boundaries (implementer/reviewer separation, the
local-review approval gate):
policies/review-orchestration-policy.md
See Repository-Documentation-Map for the full ownership breakdown — it answers exactly this question for any kind of change.
| Page | What it covers |
|---|---|
| Home | Wiki entry point: what the two Skills are and where to go next. |
| Getting-Started | First steps to package and run either Skill. |
| Choosing-a-Review-Skill | How to decide between local-code-review and github-pr-review. |
| How-the-Review-Model-Works | Concept-level walkthrough of the review pipeline shared by both Skills. |
| Architecture-Overview | Component-level map of how the repository's pieces fit together. |
| Specialist-Depth-Review | When and how a review goes deeper than its base pass. |
| Local-Code-Review-Guide | Usage guide for reviewing local, not-yet-PR'd Git changes. |
| GitHub-PR-Review-Guide | Usage guide for reviewing an existing GitHub Pull Request. |
| Review-Context-and-Existing-Evidence | How optional requirements/context and prior review evidence are supplied. |
| Feature-Pages | Index of per-feature capability pages and their shared template. |
| Feature-Delta-Re-Review | How a re-review scopes itself to only what changed since the last pass. |
| Feature-GitHub-Publication-and-Authorization | What a PR review publishes to GitHub and under what authority. |
| Feature-Human-Style-Review-Output | The senior-engineer-voice prose summary output option. |
| Feature-Requirement-Coverage | How supplied requirements are checked and reported as covered or not. |
| Feature-Runtime-Validation-Evidence | How a review can execute commands or reproductions as evidence. |
| Severity-and-Decision-Model | The P0/P1/P2 severity levels and how the merge decision is derived. |
| Packaging-and-Portability | How the Skills go from source repository to a standalone archive. |
| Development-Workflow | Contributor guide for working on this repository itself. |
| Benchmark-Testing | Orientation to this repository's own review-quality benchmark pipeline. |
| Repository-Documentation-Map | Where each concern's canonical, authoritative source lives. |
| AI-Code-Review-Landscape | Neutral snapshot comparing this project against other AI code-review products. |
| FAQ | Short, practical answers to common questions. |