documentation-scaffold
Skill4 starsChanged 10 months agoMITView on GitHub
Use this skill when bootstrapping or migrating a repository to ensure the minimum documentation set (including AGENTS.md) is created and aligned before implementation work proceeds.
- Reads credentials
In this repository67 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agents-onboardingSkill
- agent-workitem-automationSkill
- architecture-testingSkill
- aspire-integration-testingSkill
- automated-standards-enforcementSkill
- best-practice-introductionSkill
- branching-strategy-and-conventionsSkill
- broken-windowSkill
- change-risk-rollbackSkill
- ci-cd-conformanceSkill
- component-boundary-ownershipSkill
- contract-consistency-validationSkill
- csharp-best-practicesSkill
- deployment-provenanceSkill
- documentation-as-codeSkill
- dotnet-bespoke-code-minimisationSkill
- dotnet-best-practicesSkill
- dotnet-domain-primitivesSkill
- dotnet-efcore-practicesSkill
- dotnet-healthchecksSkill
- dotnet-logging-serilogSkill
- dotnet-mapping-standardSkill
- dotnet-open-source-first-governanceSkill
- dotnet-source-generation-firstSkill
- dotnet-specification-patternSkill
- dotnet-testing-assertionsSkill
- environment-traceabilitySkill
- finishing-a-development-branch-iddSkill
- greenfield-baselineSkill
- impacted-scope-enforcementSkill
- incremental-change-impactSkill
- incremental-deploymentSkill
- innersource-governance-bootstrapSkill
- issue-driven-deliverySkill
- library-extraction-stabilisationSkill
- local-dev-experienceSkill
- markdown-authorSkill
- modern-csharp-coding-standardsSkill
- monorepo-orchestration-setupSkill
- observability-logging-baselineSkill
- pair-programmingSkill
- persona-switchingSkill
- process-skill-routerSkill
- quality-gate-enforcementSkill
- release-tagging-planSkill
- repo-best-practices-bootstrapSkill
- repository-foundation-bootstrapSkill
- requirements-gatheringSkill
- runtime-tooling-validationSkill
- safe-brownfield-refactorSkill
- scoped-colocationSkill
- security-processesSkill
- selective-build-testSkill
- semantic-version-impactSkill
- session-awareSkill
- skills-first-workflowSkill
- static-analysis-securitySkill
- structured-review-workflowSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Ensure every repository has a minimal, consistent documentation foundation that supports both humans and agents, with AGENTS.md as the …
- Distinctive: line 46
Create or update AGENTS.md as canonical context.
- Distinctive: line 47
Add a compatible CLAUDE.md only if the repo needs it.
- Distinctive: line 48
Ensure README contains setup and verification steps.
- Distinctive: line 49
Add ADRs for material decisions.
- Very specific: line 50
If local secrets are used, include a safe .env.example and ensure real secrets are excluded from version control.
- Very specific: line 52
Verification: Run doc quality gates (documentation-as-code).
- Distinctive: line 86
If documentation conflicts with implementation, implementation evidence wins and docs must be corrected before proceeding.
- Distinctive: line 106
Use AGENTS.md as the default context file for this repo.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Documentation Scaffold
Intent
Ensure every repository has a minimal, consistent documentation foundation
that supports both humans and agents, with AGENTS.md as the canonical assistant
context (and optional CLAUDE.md compatibility where required).
When to Use
- Starting a new repository (greenfield).
- Migrating a brownfield repo missing or inconsistent docs.
- Establishing or revising assistant context and onboarding docs.
Precondition Failure Signal
- No
AGENTS.mdor equivalent assistant context file exists. - README lacks setup, verification, or contribution guidance.
- ADRs or decision records are missing for major structural decisions.
Postcondition Success Signal
AGENTS.mdexists and reflects current repo expectations.- README provides accurate setup and verification instructions.
- ADRs are created for significant structural or tooling decisions.
- Documentation passes
documentation-as-codechecks.
Process
- Source Review: Inspect existing docs for accuracy and gaps.
- Scope: Decide whether this is greenfield bootstrap or brownfield cleanup.
- Authoring:
- Create or update
AGENTS.mdas canonical context. - Add a compatible
CLAUDE.mdonly if the repo needs it. - Ensure README contains setup and verification steps.
- Add ADRs for material decisions.
- If local secrets are used, include a safe
.env.exampleand ensure real secrets are excluded from version control.
- Create or update
- Verification: Run doc quality gates (
documentation-as-code). - Review: Tech Lead and Software Engineer validate doc accuracy and scope.
Example Test / Validation
- Documentation checks pass and onboarding steps are reproducible.
Common Red Flags / Guardrail Violations
- Writing new docs that contradict the actual repo state.
- Using
CLAUDE.mdas the only context file whenAGENTS.mdis required. - Skipping ADRs for structural decisions.
Recommended Review Personas
- Tech Lead - validates architectural intent and decision coverage.
- Software Engineer - validates onboarding clarity and accuracy.
Skill Priority
P2 - Consistency & Governance
Conflict Resolution Rules
- If documentation conflicts with implementation, implementation evidence wins and docs must be corrected before proceeding.
Conceptual Dependencies
- documentation-as-code
Classification
Governance Core
Notes
Use AGENTS.md as the default context file for this repo. Only add
CLAUDE.md when compatibility is explicitly required.
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.

