docs
/docs
Maintain the smallest durable software documentation surface for shipped behavior, architecture, decisions, operations, incidents, and non-obvious code reasons. Use when knowledge must outlive the current task; do not create documentation for routine reversible work or narrate self-explanatory code.
- Author
- woliveiras ↗
- Repository
- baseline ↗
- Licence
- MIT
- Last repository change
- 19.08.2026
Assessment and security
- Files in this package
- 11
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 19.08.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Maintain the smallest durable software documentation surface for shipped behavior, architecture, decisions, operations, incidents, and non-obvious code reasons. Use when knowledge must outlive the current task; do not create documentation for routine reversible work or narrate self-explanatory code.
Original author description
Maintain the smallest durable software documentation surface for shipped behavior, architecture, decisions, operations, incidents, and non-obvious code reasons. Use when knowledge must outlive the current task; do not create documentation for routine reversible work or narrate self-explanatory code.
How it works
SKILL.md has no level-two headings · 27 lines, 244 words
SKILL.md preview
--- name: docs description: Maintain the smallest durable software documentation surface for shipped behavior, architecture, decisions, operations, incidents, and non-obvious code reasons. Use when knowledge must outlive the current task; do not create documentation for routine reversible work or narrate self-explanatory code. --- # Docs Route to one smallest durable surface by default. | Need and timing | Load | | --- | --- | | Open material decision before implementation | [RFC guidance](./references/proposal.md) | | Accepted hard-to-reverse decision | [ADR guidance](./references/decision-record.md) | | Stable boundaries or shipped API/operations | [project documentation](./references/project-docs.md) | | Incident learning after threshold | [postmortem guidance](./references/postmortem.md) | | Non-obvious local reason in code or test | [code comments](./references/code-comments.md) | | Vocabulary or bounded contexts | Use `shape-domain` and the project's chosen vocabulary surface | Read the governing input, implemented behavior, existing docs, and repository convention. Do not create an RFC after implementation has made the choice effectively irreversible; record the accepted decision as an ADR when its threshold is met. Do not create an ADR for routine reversible work. Use C4 or the repository's architecture notation only when boundaries and responsibilities have stabilized. Synchronize API and operations documentation with shipped behavior. Use Git as the default historical archive. Remove a document from the current tree when it no longer guides a current decision, operation, contract, risk, or behavior and Git can reconstruct it completely. Do not create `archive/` directories for superseded snapshots, reviews, evidence logs, or completed task bundles. Validate filenames, indexes, local links, commands, examples, and version-sensitive claims. Report the selected mode, updated claims, checks, and limitations. When no stronger template exists, use the matching bundled asset: - [MADR decision record](./assets/adr-madr-template.md) - [C4 project architecture](./assets/project-c4-template.md) - [RFC proposal](./assets/rfc-template.md) - [blameless postmortem](./assets/postmortem-template.md)
Files in this package (11)
- SKILL.md 2 KB
- agents/openai.yaml 1 KB
- assets/adr-madr-template.md 1 KB
- assets/postmortem-template.md 2 KB
- assets/project-c4-template.md 2 KB
- assets/rfc-template.md 2 KB
- references/code-comments.md 1 KB
- references/decision-record.md 1 KB
- references/postmortem.md 1 KB
- references/project-docs.md 1 KB
- references/proposal.md 1 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · woliveiras/baseline | 96 | MIT |
| tanstack/ai | 100 | MIT |
| mthines/agent-skills | 100 | MIT |
| lilly-logic-labs/lll-skills | 100 | MIT |
| kriscard/kriscard-claude-plugins | 100 | MIT |
| imgly/agent-skills | 100 | MIT |
| kriscard/Skills | 100 | MIT |
| The01Geek/prflow | 100 | MIT |
| grimoire-rs/grimoire | 100 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version eb463ff167ae (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100documentation
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks. - 95documentation-architecture
Generate and maintain project feature catalogs and human docs from implementation evidence. Use for feature grouping, documentation setup, or stale capability and validation summaries. - 100documentation-guidelines
Create, audit, or consolidate durable project documentation, including feature rules, contracts, workflows, and runbooks. Use when documentation is the main deliverable; routine code changes can update their owning docs directly. - 90architecture
Architecture and documentation framing for cross-cutting repo decisions, docs taxonomy placement, ADRs, memos, PRDs, implementation plans, audits, measurements, runbooks, and source-grounded proposals. Use when deciding where durable docs belong, drafting or moving… - 100living-design-documents
Create and maintain structured design documentation that drives development. Use for new projects, design decisions, growing complexity, or when audit is due. Triggers: "design docs", "LDD", "core decisions", "taxonomy", "parked decisions". - 100code-comments
Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation—file headers, function docs, architectural decisions, or explanatory comments. Optimized for both human readers and AI…