Repository Documentation Map

Repository Documentation Map

This Wiki is explanatory and navigational material — never an authoritative runtime contract. Every normative rule has exactly one canonical home in the repository itself. This page answers: "I want to know or change X — where's the canonical source?"

Ownership at a glance

Concern	Canonical home
Shared review behavior (scope, severity, evidence, context, ownership) used identically by both Skills	shared/policies/
Specialist-depth composition contract and the domain-specific deepening capabilities (Security, Distributed Systems, Database/Migration, Performance, Dependency/Supply-Chain)	shared/policies/specialist-depth.md and its sibling *-deepening.md policies; see Specialist-Depth-Review
The canonical finding / review-summary output shape	shared/templates/
One Skill's own behavior (its identity, inputs, flow, boundaries)	that Skill's SKILL.md — local-code-review, github-pr-review
Semantics unique to one Skill (no cross-Skill analogue)	that Skill's own policies/ — e.g. local-code-review/policies/repository-state.md, github-pr-review/policies/review-action-authorization.md
Execution flow and phase ordering for one Skill (never a second copy of policy semantics)	that Skill's runbooks/ — local-code-review/runbooks/local-review.md, github-pr-review/runbooks/
Output shapes / rendering contracts for one Skill's delivery surface	that Skill's templates/ — e.g. github-pr-review/templates/inline-finding.md
Repository-development rules (branching, commits, PRs, merges, docs style, Skill packaging)	AGENTS.md + policies/
Architecture — components, pipeline, module map	docs/ARCHITECTURE.md
Why these Skills exist / comparison with other reviewers	docs/CODE_REVIEW_COMPARISON.md
Usage guidance for an optional/advanced capability	docs/features/
Release process, CHANGELOG, SemVer	docs/RELEASE.md, policies/release-changelog-policy.md
Contribution ownership / Issue classification	policies/contribution-ownership-policy.md, CONTRIBUTING.md
Test suite structure	tests/README.md
Repository-development design records not yet packaged (contextual-evidence model, finding-confidence model, finding-identity contracts, candidate-finding validation, benchmark)	docs/review-context/, docs/finding-confidence/, docs/findings/, docs/candidate-finding-validation/, docs/benchmark/

Canonical vs. explanatory

Per AGENTS.md, "Instruction precedence": AGENTS.md, everything under policies/ and shared/policies/, each SKILL.md, and each Skill's own policies//runbooks//templates/ are canonical — they define behavior. README.md files and everything under docs/ are explanatory — they describe and navigate, and never override a canonical source. This Wiki sits one further layer out than even docs/: it explains and links, and carries no normative authority of its own. If a Wiki page and a canonical repository file ever appear to disagree, the repository file is correct and the Wiki page has a bug — open an issue or fix the Wiki wording; never treat the disagreement as license to change the canonical file to match the Wiki.

Common "where do I…" questions

• …change what counts as a P0 vs. P1? → shared/policies/severity.md (maintainer-led — semantic contract).
• …add a new optional capability to one Skill? → reusable semantics go in shared/policies/; Skill-specific semantics go in that Skill's own policies/; the runbook is updated only enough to wire it into execution order. See policies/skill-development-policy.md, "Runbook Design."
• …understand how a repository-development change should be documented? → policies/documentation-policy.md.
• …find the exact packaging manifest? → scripts/package-manifest.json.
• …understand a benchmark fixture or metric? → docs/benchmark/.
• …understand the PR-time benchmark selection/gating pipeline or the nightly drift loop? → Benchmark-Testing, which mirrors docs/benchmark-measurement-architecture/.
• …find a per-feature at-a-glance Wiki page for an optional/advanced capability? → Feature-Pages, which mirrors docs/features/README.md and states the same canonical/Wiki boundary as this page, applied to the feature-page pattern specifically.

What this Wiki is for

Fast orientation, task-based navigation, and cross-linking of the repository's own canonical files — not a duplicate specification. Expect short explanations plus links; expect not to find long policy text copied here. If you find a page here that has drifted from what the linked file actually says, that's a Wiki bug.

---

Wiki Page Map

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.