CtrlK
BlogDocsLog inGet started
Tessl Logo

good-docs-writing

Writing style guide derived from Modal's documentation voice. Apply when writing or editing docs, guides, tutorials, or technical prose that should read direct, second-person, confident, low-jargon, and example-first. Use to draft new docs in this voice or to revise existing prose toward it.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The SKILL.md body is a tight, well-structured overview that points to one real reference file and surfaces the highest-value rules inline, appropriate for a simple single-purpose skill. It is nearly ideal, with only minor gaps in inline examples and reference linking.

Suggestions

Add a short inline runnable example (one before/after sentence pair) so the voice is demonstrated without requiring the reader to open the reference.

Link the reference as `references/style-guide.md` markdown rather than naming it in prose, making navigation explicit.

Show a one-line pointer to `good-docs-audit` as a sibling skill link if available, so the review path is navigable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, opening with a one-breath rationale then concrete rules; it does not re-explain what docs or code are, and every line earns its place.

5 / 5

Actionability

Rules are concrete imperatives ("Address the reader as 'you'", "Remove every em-dash", "Backtick every code identifier"), but the body lacks a runnable example demonstrating the voice, deferring all examples to the reference.

4 / 5

Workflow Clarity

For a simple single-purpose skill the workflow is unambiguous: read `references/style-guide.md`, apply every rule while drafting, and use `good-docs-audit` to review instead, with the key rules surfaced before opening the reference.

5 / 5

Progressive Disclosure

The body is a concise overview that signals a single one-level-deep reference (`references/style-guide.md`, confirmed to exist) and surfaces the most important rules inline, though the reference is named in prose rather than linked.

4 / 5

Total

18

/

20

Passed

Description

83%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.

The description clearly answers both what the skill does and when to use it, with concrete actions and natural trigger terms tied to a specific voice (Modal's). It is concise and confident without over-claiming.

Suggestions

Add common synonyms users might actually say, such as "documentation", "README", or "how-to", to broaden natural trigger coverage.

Mention the specific voice traits as trigger terms (e.g. "second-person", "example-first") so users needing that style match more reliably.

DimensionReasoningScore

Specificity

It names the domain ("writing style guide") and several concrete actions ("writing or editing docs, guides, tutorials, or technical prose", "draft new docs", "revise existing prose toward it"), giving clear coverage with minor gaps.

4 / 5

Completeness

It explicitly states what it does ("Writing style guide derived from Modal's documentation voice") and when to use it ("Apply when writing or editing docs...", "Use to draft new docs... or to revise existing prose"), covering both what and when with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Natural terms like "docs", "guides", "tutorials", and "technical prose" are present, but common synonyms a user might say (e.g. "documentation", "README", "how-to") are missing.

4 / 5

Distinctiveness Conflict Risk

The Modal-derived voice framing and the explicit handoff to `good-docs-audit` for reviewing carve a distinct niche, with only minor overlap risk against general writing skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ComposioHQ/composio
Reviewed

Table of Contents

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.