Documentation
Everything you need to read, without leaving the site.
These pages are rendered from the repository at build time, so they always match the release you would install. Every page links to its source file when you want the original.
Get started
- QuickstartThis path starts at a fresh checkout and ends with a first bounded engineering3 min read6 sections
- InstallationInstall only generated artifacts under dist/. Never copy src/, source6 min read8 sections
- Usagerd-skills coordinates engineering work through one control prompt, four5 min read6 sections
Operating model
- Operating Modelsrc/ contains authoring sources: the control model, control prompt, Profile9 min read7 sections
- Subagent and Review ModelSubagents are an internal execution method. A request to implement, repair, diagnose, validate, review, or release authorizes the bounded subagents needed to perform it. Ask the user only for a materi7 min read7 sections
- AI Control BoundariesThis document defines the authority, permission, evidence, and context boundaries2 min read4 sections
- Routing ExamplesEach task has one path, one primary Professional Skill, zero to a few triggered Layer 3 Skills, and one Review Skill.2 min read7 sections
Authoring skills
- Skill Content Governancerd-skills Skills are written for AI execution. The always-loaded root must provide the smallest complete decision contract; detailed or low-frequency material belongs in targeted references.33 min read8 sections
- Quality Modelrd-skills quality is the combination of control correctness, professional judgment, bounded context, observable evidence, and maintainable packaging.4 min read6 sections
- Marketplace IndexThe marketplace index and catalog are local, source-derived discovery views.2 min read4 sections
Assurance
- ValidationEvery completion or release claim needs evidence from the final material edit.19 min read8 sections
- Benchmarksrd-skills uses bounded, reproducible repository evaluations. Benchmarking is6 min read6 sections
- ScorecardThis handwritten table defines release expectations. It is not generated2 min read
- ReleaseRelease only from authored source, current evidence, generated build output,7 min read8 sections
In the repository
Generated inventories and governance files are large or change with every release, so they stay where they are produced.