writing-guide

Use when writing or editing any Spacebot copy — README sections, docs, release notes, marketing text, design doc summaries. Covers voice, tone, patterns to avoid, and what good Spacebot writing sounds like.

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/writing-guide/SKILL.md

Quality

Content

76%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 tight, highly actionable style guide with concrete bad/good pairs and no padding. Its only real gap is workflow clarity — as a reference guide it has no sequenced workflow or validation checkpoints, which the rubric specifically rewards.

Suggestions

Add a short 'How to use this guide' workflow at the top (e.g., 1. Draft the copy, 2. Scan against Patterns to Avoid, 3. Check Words to Avoid, 4. Re-read the opening for prose structure) to give the guide a sequenced application process.

Consider splitting the long 'Patterns to Avoid' and 'Words to Avoid' lists into a separate REFERENCES.md so the SKILL.md body stays a lean overview with one-level-deep navigation.

Tighten the tagline/rationale sentences in the Voice section to push conciseness toward fully lean.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no basic-concept padding; the bad/good pairs earn their place as core teaching material. Minor elaboration (the tagline rationale) could be trimmed, so it sits just below the score-5 anchor.	4 / 5
Actionability	Highly actionable for an instruction-only skill: concrete bad→good pairs for every pattern, a specific words-to-avoid list, and specific differentiator examples cover the common cases copy-paste ready.	5 / 5
Workflow Clarity	This is a reference style guide with no multi-step workflow or validation checkpoints; it is organized by pattern but lacks a sequenced process, and at ~105 lines the simple-skill exception to score 5 does not apply.	3 / 5
Progressive Disclosure	A single well-organized file with clear section headers (Voice, Patterns to Avoid, Differentiators, etc.) and no external references; content is appropriately cohesive, but at over 50 lines it is not a clean score-5.	4 / 5
	Total	16 / 20 Passed

Description

82%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 that explicitly covers both what the skill does and when to use it, with concrete trigger artifacts and a distinct Spacebot-scoped niche. The only weakness is that the named actions are generic ('writing or editing') rather than multiple distinct verbs.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete artifact targets ('README sections, docs, release notes, marketing text, design doc summaries'), but the actions are only two generic verbs ('writing or editing') rather than multiple distinct concrete actions, matching the score-3 anchor.	3 / 5
Completeness	Explicitly answers both 'what' ('Covers voice, tone, patterns to avoid, and what good Spacebot writing sounds like') and 'when' ('Use when writing or editing any Spacebot copy — README sections, docs, release notes...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would actually say ('README sections', 'release notes', 'marketing text', 'design doc summaries') with good coverage; a few common synonyms are missing, fitting the score-4 anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped specifically to 'Spacebot copy' — a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: spacedriveapp/spacebot
Path: .agents/skills/writing-guide/SKILL.md
Commit: ab2c160

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.