Creates comprehensive feature documentation for humans and AI to understand features, resolve bugs, and extend functionality. Use after complete feature implementation (may span multiple commits). Generates feature docs, updates godoc, and creates testable examples.
View on GitHubbuzzdan/ai-coding-rules
go-linter-driven-development
January 16, 2026
Select agents to install to:
npx add-skill https://github.com/buzzdan/ai-coding-rules/blob/main/go-linter-driven-development/skills/documentation/SKILL.md -a claude-code --skill documentationInstallation paths:
.claude/skills/documentation/<objective> Creates comprehensive feature documentation for humans and AI to use for future bug resolution, feature extensions, and codebase understanding. This is NOT a changelog - it's an introduction to the feature. **Reference**: See `reference.md` for complete documentation checklist and examples. </objective> <quick_start> 1. **Understand feature scope** - Review all commits related to the feature 2. **Analyze architecture** - Identify core types, data flow, design decisions 3. **Generate docs/[feature-name].md** - Problem/solution, architecture, usage 4. **Update package godoc** - Reflect feature's role 5. **Add type documentation** - Explain purpose and design decisions 6. **Create testable examples** - Example_* functions for complex types 7. **Validate** - Can future you/AI understand the feature without reading all code? </quick_start> <when_to_use> - After a complete feature is implemented (may span multiple commits) - When adding significant new functionality to the codebase - NOT for: individual commits, bug fixes, minor refactors </when_to_use> <purpose> Generate documentation that helps: - **Humans**: Understand what the feature does and how to use it - **AI**: Context for future bug fixes and feature extensions - **Team**: Onboarding and knowledge sharing </purpose> <workflow> <understand_feature_scope> - Review all commits related to the feature - Identify all modified/new files - Understand the problem being solved - Map out integration points with existing system </understand_feature_scope> <analyze_architecture> - Identify core domain types - Map data/control flow - Document design decisions (WHY choices were made) - Note patterns used (vertical slice, self-validating types, etc.) </analyze_architecture> <generate_documentation_artifacts> **Primary: Feature Documentation** (`docs/[feature-name].md`) - Problem & solution: What problem does this solve? - Architecture: How does it work? - Usage examples: How do I use it? - Integration: How