Doc Navigator
npx machina-cli add skill georgekhananaev/claude-skills-vault/doc-navigator --openclawDoc Navigator
Navigate codebase documentation efficiently by checking known doc locations first, before resorting to grep/glob searches.
When to Use
- Finding architectural decisions (ADRs)
- Locating feature specs or API docs
- Researching codebase before implementation
- Suggesting documentation structure for new projects
- Alternative to grep/glob for doc discovery
Quick Start
- Check for docs directory at project root
- Scan for common doc file patterns
- If docs exist → map topics to locations
- If no docs → suggest documentation structure (see
references/doc-patterns.md)
Common Documentation Locations
Check these locations in order:
project-root/
├── docs/ # Primary documentation
│ ├── architecture/ # System design, ADRs
│ ├── features/ # Feature specs
│ ├── api/ # API documentation
│ └── guides/ # How-to guides
├── .github/ # GitHub-specific docs
│ └── docs/
├── README.md # Project overview
├── ARCHITECTURE.md # High-level architecture
├── CONTRIBUTING.md # Contribution guidelines
└── doc/ or documentation/ # Alternative doc folders
Topic-to-Location Mapping
| Looking for... | Check first |
|---|---|
| Project overview | README.md |
| Architecture/design | docs/architecture/, ARCHITECTURE.md, docs/adr/ |
| Feature specs | docs/features/, docs/specs/ |
| API reference | docs/api/, api-docs/, OpenAPI/Swagger files |
| Setup/installation | docs/guides/setup.md, INSTALL.md |
| Database schema | docs/database/, docs/schema/, prisma/schema.prisma |
| Data types/models | docs/types/, docs/models/, src/types/, src/models/ |
| Style guide | docs/style-guide.md, docs/conventions.md, .eslintrc, STYLE.md |
| Environment config | docs/config/, .env.example, docs/environment.md |
| Testing strategy | docs/testing/, tests/README.md |
| Deployment | docs/deployment/, docs/infrastructure/ |
| ADRs (decisions) | docs/adr/, docs/decisions/, architecture/decisions/ |
| ADRs (fallback) | CHANGELOG.md, git log, PR descriptions, code comments |
Discovery Workflow
1. ls docs/ (or doc/, documentation/)
↓ exists?
YES → scan structure, build topic map
NO → check for standalone doc files (*.md in root)
↓ found?
YES → use available docs
NO → suggest creating docs structure
(see references/doc-patterns.md)
Automated Discovery
Run the scanner script to map available documentation:
python3 scripts/scan_docs.py [project-path]
Output: JSON map of topics → file locations
When Docs Don't Exist
If the codebase lacks documentation:
- Inform user: "No documentation structure found"
- Offer to create starter docs:
view references/doc-patterns.md - Suggest minimal viable structure based on project type
Finding Decisions Without ADRs
If no formal ADRs exist, extract architectural context from:
CHANGELOG.md → Breaking changes, migration rationale
git log → Commits w/ "migrate", "refactor", "replace"
PR/MR descriptions → Discussion threads on major changes
Issue tracker → Closed RFCs, architecture proposals
Code comments → // DECISION:, // WHY:, // HACK:
See references/doc-patterns.md → "Fallback: When No ADRs Exist" for git commands & reconstruction templates.
Integration with Research Phase
Use doc-navigator BEFORE grep/glob when:
- Starting work on unfamiliar codebase
- Looking for architectural context
- Understanding feature implementations
- Finding API contracts or schemas
Fall back to grep/glob when:
- Docs don't cover the specific topic
- Need to find implementation details in code
- Searching for specific function/class usage
Ref: references/doc-patterns.md for documentation templates when establishing new docs.
Source
git clone https://github.com/georgekhananaev/claude-skills-vault/blob/main/.claude/skills/doc-navigator/SKILL.mdView on GitHub Overview
Doc Navigator helps you quickly locate architectural decisions, feature specs, and technical docs by checking known locations first before resorting to grep or glob searches. It maps topics to doc locations for fast context retrieval during the Research phase. If the project lacks documentation structure, it provides patterns to establish one.
How This Skill Works
It starts at the project root and looks for docs/ or doc/ or documentation/. If found, it scans the structure and builds a topic-to-location map, prioritizing ADRs and API docs. If not found, it suggests a documentation structure from references/doc-patterns.md. For automation, run the discovery script to generate a JSON map of topics to file locations: python3 scripts/scan_docs.py [project-path].
When to Use It
- Finding architectural decisions (ADRs)
- Locating feature specs or API docs
- Researching codebase before implementation
- Suggesting documentation structure for new projects
- Alternative to grep/glob for doc discovery
Quick Start
- Step 1: Check for a docs directory at the project root (docs/, doc/, or documentation/).
- Step 2: Scan for common doc file patterns (architecture, features, api, guides) to build a topic map.
- Step 3: If docs exist, map topics to locations; if not, refer to references/doc-patterns.md to bootstrap structure.
Best Practices
- Start at project root and check docs/, doc/, or documentation/ before searching with grep
- Leverage the topic-to-location mapping to jump to the right file quickly
- Keep ADRs in docs/adr/ or ARCHITECTURE.md and ensure mapping stays up to date
- If no docs exist, use references/doc-patterns.md to bootstrap structure
- Regularly run the automated discovery to refresh the topic map (python3 scripts/scan_docs.py [project-path])
Example Use Cases
- A new ADR is needed for a design decision; locate ADRs in docs/adr/ or ARCHITECTURE.md first.
- Onboarding a feature: map to docs/features/ and read related specs in docs/features.
- Review API surface before implementation by checking docs/api/ and api-docs/.
- No docs exist; run scan_docs.py to generate starter patterns.
- Suggest doc structure per project type using references/doc-patterns.md.