docs-decisions

Work on Composio documentation content, Fumadocs configuration, changelogs, docs automation prompts, docs decisions, ADR-style records, and docs review guidance. Use for files under docs/, documentation workflows, or requests to record or update a docs decision. Do not use for SDK runtime changes unless docs are the main deliverable.

Quality

89%

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

86%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 model router-style SKILL.md body: minimal, uncluttered, and correctly structured for progressive disclosure, with both referenced bundle files verified present and one level deep. The residual gaps are in actionability and workflow clarity, where 'Read the relevant reference' defers file selection and next steps to the references themselves.

Suggestions

Replace 'Read the relevant reference' with an explicit decision rule, e.g., 'For docs commands, content rules, or automation, read references/docs-workflow.md; for decisions and ADR-style updates, read references/decision-records.md.'

Add one concrete first step after routing (e.g., 'Before editing docs content, read docs/AGENTS.md first' or a single canonical verification command like 'bun run lint:links') so the body carries at least one immediately executable action.

Optionally state when both references apply (a docs change that also alters a recorded decision) so the routing covers the combined case instead of implying a single choice.

Dimension	Reasoning	Score
Conciseness	Six lean lines with zero padding: a one-sentence purpose statement plus two one-line reference pointers. No explanation of concepts Claude already knows and every token earns its place — the anchor 5 example of assuming Claude's competence.	5 / 5
Actionability	Concrete routing guidance: each reference is paired with its scope ('docs-workflow.md for docs commands, content rules, and automation'; 'decision-records.md for decisions and ADR-style updates'). It falls short of anchor 5 because 'Read the relevant reference' leaves file selection implicit and the body offers no inline quick-start guidance, leaving a minor gap rather than copy-paste-ready coverage.	4 / 5
Workflow Clarity	As a single-purpose router skill, its one action (pick and read a reference) is nearly unambiguous since the bullets map task to file, but 'the relevant reference' still requires the model to infer which file applies and no post-read step is given — between anchor 4 and the simple-skill exception at 5, and clearly above anchor 3's implicit checkpoints.	4 / 5
Progressive Disclosure	A clear overview pointing to two well-signaled, one-level-deep references; both referenced files (references/docs-workflow.md and references/decision-records.md) exist in the bundle and carry the detail appropriately split out of SKILL.md — exactly the anchor 5 structure of easy navigation with no nesting.	5 / 5
	Total	18 / 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 description: it scopes a clear niche, lists the concrete deliverables it covers, provides explicit 'Use for...' triggers including a path prefix (docs/), and closes with a negative boundary to prevent mis-triggering. Its only weakness is the generic 'Work on' verb in place of sharper action verbs.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete deliverables ('Composio documentation content, Fumadocs configuration, changelogs, docs automation prompts, docs decisions, ADR-style records, and docs review guidance'), but the governing verb 'Work on' is generic rather than a concrete action verb, matching anchor 4 ('lists several specific actions; minor gaps') rather than the comprehensive concrete-action coverage of 5.	4 / 5
Completeness	Explicitly answers both questions: what ('Work on Composio documentation content, Fumadocs configuration, changelogs, docs automation prompts, docs decisions, ADR-style records, and docs review guidance') and when ('Use for files under docs/, documentation workflows, or requests to record or update a docs decision'), with concrete trigger phrases and a negative boundary — exactly the anchor 5 pattern.	5 / 5
Trigger Term Quality	Includes strong natural trigger phrases users would say — 'files under docs/', 'documentation workflows', 'record or update a docs decision', 'changelogs', 'Fumadocs' — matching anchor 4 ('good keyword coverage; a few natural terms missing'). It stops short of anchor 5's comprehensive synonym coverage (e.g., 'write/update documentation', 'decision record', file extensions) but clearly exceeds anchor 3's partial coverage.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Composio docs site, Fumadocs config, ADR-style decision records) with an explicit exclusion ('Do not use for SDK runtime changes unless docs are the main deliverable'), giving distinct triggers and minimal conflict risk per anchor 5.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ComposioHQ/composio
Path: .agents/skills/docs-decisions/SKILL.md
Commit: 98b10d7

Reviewed: 4 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.