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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/docs-wg/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

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

A well-organized, actionable doctrine skill with strong progressive disclosure and concrete placement/frontmatter/checklist guidance. Its main weakness is conciseness: manifesto-style rationale paragraphs could be trimmed without losing instructional value.

Suggestions

Tighten the rhetorical rationale paragraphs (e.g. 'Code moves; a file path… rots into a lie' and the closing 'throughline' paragraph) into terse doctrinal statements so every token instructs rather than persuades.

Consider consolidating the implicit genre → draft → place → frontmatter → index → review flow into one short ordered checklist near the top, keeping the detailed genre rules as reference below.

Move or compress the 'What a good WG doc is' / 'What a bad WG doc is' prose into the existing 'Before you save — review' checklist so the criteria are evaluated as actionable checks rather than read as essay.

Dimension	Reasoning	Score
Conciseness	The doctrine is substantive and well-written, but several passages are rhetorical essay rather than instruction ('Code moves; a file path or a function name is stale within months… rots into a lie', the 'throughline' paragraph), spending tokens on persuasion that could be tightened.	3 / 5
Actionability	Gives concrete placement rules (docs/wg/platform/, docs/wg/ai/, docs/wg/desktop/, feat-* clusters), a specific frontmatter spec (title, description, tags from docs/tags.yml, format: md), and a 'Before you save — review' checklist with concrete search targets (crates/, editor/, packages/).	4 / 5
Workflow Clarity	A recognizable sequence is implied across sections (name genre → draft → place in cluster → set frontmatter → update index.md → run review checklist), with the checklist acting as a validation gate, but it is not presented as a single ordered workflow and lacks explicit error-recovery loops.	4 / 5
Progressive Disclosure	No bundle files exist; the body appropriately keeps doctrine in SKILL.md and offloads operational mechanics to docs/AGENTS.md ('read it once') with one-level-deep, well-signaled links to sibling skills and a 'Related skills' navigation section.	5 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

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

A strong, well-scoped description that clearly states what the skill does, when to use it with natural trigger phrases, and where it does not apply. Minor room to broaden trigger-term synonyms, but it is otherwise exemplary.

Dimension	Reasoning	Score
Specificity	Names the WG-docs domain and multiple concrete artifact genres ('RFC/RFD specs and findings/research/glossary', 'a spec, a design note, a glossary, or research findings') plus the doctrine stance, but the core actions ('drafting and keeping') are coarser than a list of distinct operations, so it stops short of comprehensive.	4 / 5
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 concrete trigger phrases, and adds a negative boundary ('Not for plans/TODOs… use docs to route those').	5 / 5
Trigger Term Quality	Includes natural user phrases ('write up the design', 'document the spec', 'capture what we learned') alongside genre synonyms (spec, design note, glossary, research findings, RFC/RFD); good coverage but lacks file-extension/synonym breadth, so not a 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche scoped to docs/wg/** with distinct genre triggers, and it explicitly routes overlapping cases (user docs, SDK API refs) to the docs skill, minimizing conflict risk.	5 / 5
	Total	18 / 20 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: 8ef5e53

Reviewed: about 11 hours 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.