docs-wg

Doctrine for drafting and keeping working-group docs under `docs/wg/**` — RFC/RFD specs and findings/research/glossary. A WG doc is a language-agnostic, code-agnostic study of a domain: it argues *why* and defines *what*, never *how in our code*. Use when writing or editing anything under `docs/wg/`, an RFC/RFD, a spec, a design note, a glossary, or research findings — including "write up the design", "document the spec", or "capture what we learned". Not for plans/TODOs (untracked `*.plan.md`), user docs, or SDK API refs — use `docs` to route those.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable doctrine that appropriately externalizes operational detail and sibling-skill routing. Its only weakness is conciseness: the rhetorical, manifesto-like framing earns a 2 rather than a 3, though it never pads with knowledge Claude already has.

Suggestions

Tighten the manifesto passages (e.g. 'That is the bar.', 'don't let one wear another's costume', the 'Code moves... rots into a lie' paragraph) to declarative rules — the doctrine lands the same with less prose and would lift conciseness to a 3.

Consider moving the extended 'One concept, one home' rationale into a referenced companion note, keeping SKILL.md to the rule and the test, so the overview stays lean while the reasoning remains accessible one level deep.

Dimension	Reasoning	Score
Conciseness	The doctrine is accurate and free of concepts Claude already knows, but the manifesto-style prose carries rhetorical flourish and repetition ("That is the bar.", "don't let one wear another's costume", "Code moves... rots into a lie") that could be tightened, fitting the 'mostly efficient but could be tightened' anchor rather than the lean one.	2 / 3
Actionability	Gives concrete, specific guidance: two named genres with their shapes, exact placement paths (`docs/wg/platform/`, `feat-*` clusters), required frontmatter fields (`tags: [internal, wg...]`, `format: md`), and a literal review checklist with searchable terms (`crates/`, `editor/`, `packages/`) — copy-paste-ready rules for an instruction-only skill.	3 / 3
Workflow Clarity	Sequences the work end-to-end (name genre → draft to genre rules → place in owning cluster → update index.md → run review checklist), and the "Before you save — review" checklist supplies explicit validation checkpoints against the doc-rot failure modes.	3 / 3
Progressive Disclosure	Defers operational mechanics to `docs/AGENTS.md` ("read it once") and routes to sibling skills (`grounding`, `links`, `naming`, `research`) under a clear 'Related skills' section, all one level deep and clearly signaled; no deep reference nesting and well-organized sections.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all dimensions: it states concrete capabilities, includes natural trigger phrases, explicitly covers both what and when, and sharply distinguishes itself from adjacent skills. Voice is appropriately third person with no over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and artifacts — "drafting and keeping working-group docs under docs/wg/*", "argues why* and defines what", and enumerates RFC/RFD specs and findings/research/glossary — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ("doctrine for drafting and keeping working-group docs... argues why and defines what") and when ("Use when writing or editing anything under docs/wg/..."), with a clear 'Use when...' clause plus explicit exclusions sharpening the trigger.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would actually say — "write up the design", "document the spec", "capture what we learned" — alongside RFC/RFD, spec, design note, glossary, and research findings, giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Clear niche (working-group docs under docs/wg/**) with distinct triggers and explicit disambiguation against `docs`, plans/TODOs, user docs, and SDK API refs, making conflict with sibling skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 14 suspicious	Warning

	Total	15 / 16 Passed

Repository: gridaco/grida
Path: .agents/skills/docs-wg/SKILL.md
Commit: 2e0d276

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.