speckit-docguard-fix
Skill1 starsChanged 3 days agoApache-2.0View on GitHub
Reverse-engineer canonical documentation from existing codebase
- Reads credentials
In this repository28 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- autopilot-supervisorSkill
- reclaim-diskSkill
- speckit-analyzeSkill
- speckit-autopilotSkill
- speckit-bugfix-patchSkill
- speckit-bugfix-reportSkill
- speckit-bugfix-switchSkill
- speckit-bugfix-verifySkill
- speckit-checklistSkill
- speckit-clarifySkill
- speckit-constitutionSkill
- speckit-convergeSkill
- speckit-docguard-diagnoseSkill
- speckit-docguard-generateSkill
- speckit-docguard-guardSkill
- speckit-docguard-reviewSkill
- speckit-docguard-scoreSkill
- speckit-implementSkill
- speckit-planSkill
- speckit-specifySkill
- speckit-tasksSkill
- speckit-taskstoissuesSkill
- speckit-tdd-planSkill
- speckit-tdd-runSkill
- speckit-tdd-setupSkill
- speckit-tdd-verifySkill
- visual-passSkill
The file
Files
Docguard Fix Skill
DocGuard Generate
Scans your codebase (JS/TS, Python, Rust, Go, Java/Kotlin, Ruby, PHP, C# — polyglot/monorepo-aware) and generates the canonical documentation memory: ARCHITECTURE.md, DATA-MODEL.md, TEST-SPEC.md, SECURITY.md, ENVIRONMENT.md, API-REFERENCE.md, SCREENS.md.
Two modes:
--plan(AI-powered, recommended) — emits a structured agent task manifest + writes the code-truth skeleton inside<!-- docguard:section -->markers. The AI agent then writes the prose grounded in scanned facts. Human prose is preserved.- default — purely deterministic generation: writes templated docs with TODO placeholders. Use when no AI agent is available.
User Input
$ARGUMENTS
Steps
- Preview the plan — what code-truth facts were captured + what the agent will write:
npx --yes docguard-cli@latest generate --plan $ARGUMENTS- Scaffold the skeleton docs (marked sections filled with code-truth, prose sections as agent-task placeholders):
npx --yes docguard-cli@latest generate --plan --write $ARGUMENTS- Or get the machine-readable manifest to drive an agent:
npx --yes docguard-cli@latest generate --plan --format json $ARGUMENTS- Fallback (no AI, deterministic generation):
npx --yes docguard-cli@latest generate $ARGUMENTS- Review the generated docs in
docs-canonical/. Each document includes:- Structured sections based on industry standards
- Data extracted from your actual codebase (routes, schemas, configs)
- Standards citation footer referencing relevant specifications
- DocGuard metadata headers for freshness tracking
- Customize with
--doc <name>to generate a specific document only.
Generated Documents
| Document | Source | Standard |
| ARCHITECTURE.md | Routes, configs, dependencies | arc42 / C4 Model |
| DATA-MODEL.md | Schema files, type definitions | C4 Component / ER |
| TEST-SPEC.md | Test files, test configs | ISO/IEC/IEEE 29119-3 |
| SECURITY.md | Auth modules, .gitignore, secrets | OWASP ASVS v4.0 |
| ENVIRONMENT.md | .env files, Docker, CI/CD configs | 12-Factor App |
| API-REFERENCE.md | Route handlers, OpenAPI specs | OpenAPI 3.1 |
Flags
--doc <name>— Generate a specific document only--dir <path>— Run on a different directory
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

