cw-line-edit

Revise prose at the sentence and word level while preserving voice, meaning, source accuracy, and useful weirdness. Use when the structure is stable and the user asks for a line edit, polish, tightening pass, or usable rewrite.

Quality

77%

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 ./skills/cw-line-edit/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 instruction skill with a clear editorial workflow and concrete flagging guidance. Its main weakness is reliance on external references (context-contract, cw-ai-check) that are not part of this skill's bundle, leaving navigation and full actionability slightly incomplete.

Suggestions

Inline a brief summary of what 'cw-ai-check' contributes (or its required order) so the skill is actionable when that companion skill is absent.

Resolve the '../../references/context-contract.md' reference: either ship the file in references/ or replace it with a concise inline note on what context to load.

Add an explicit verification checkpoint (e.g. 're-read the revised draft to confirm voice and citations are intact before presenting') to make the workflow's validation step explicit.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean: bulleted checklists of concrete things to flag (hedge words, AI-scent vocabulary) with no padding about what editing is. Minor trimming is possible in the output template block, so it sits just below fully efficient.	4 / 5
Actionability	Concrete, specific guidance throughout — named vocabulary to flag ('delve, leverage, utilize'), explicit output format with a copy-ready template, and revert mechanics. It is not a 5 because key execution details depend on external artifacts ('cw-ai-check', '../../references/context-contract.md') that are not present in the bundle.	4 / 5
Workflow Clarity	A clear sequence is laid out (load context → apply check categories → output revised draft + summary → offer revert → transition to Final Pass), with the revert offer as a soft checkpoint. It is not a 5 because validation checkpoints are implicit rather than explicit, though the destructive/batch cap does not apply to prose editing.	4 / 5
Progressive Disclosure	Section structure is clear and well-organized, but the body references files outside the bundle ('../../references/context-contract.md', 'cw-ai-check') that do not exist here, so navigation is not clean and one referenced layer is missing, landing it at the mid anchor rather than above.	3 / 5
	Total	15 / 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.

A strong description: it answers both what and when with concrete, natural trigger phrases and a distinct editorial niche. The only weakness is that action and keyword coverage, while good, stops short of comprehensive.

Suggestions

Add one or two more trigger synonyms (e.g. 'copy edit', 'proofread') to lift trigger_term_quality and specificity toward comprehensive coverage.

Clarify the boundary from developmental/copy editing in a half-clause to further reduce conflict risk with adjacent editing skills.

Dimension	Reasoning	Score
Specificity	Names the domain (prose) and several concrete actions via 'line edit, polish, tightening pass, or usable rewrite', plus concrete preservation constraints (voice, meaning, source accuracy). It falls short of 5 because coverage is a handful of synonyms rather than a comprehensive enumeration of capabilities.	4 / 5
Completeness	Explicitly states both what ('Revise prose at the sentence and word level while preserving voice, meaning, source accuracy, and useful weirdness') and when ('Use when the structure is stable and the user asks for a line edit, polish, tightening pass, or usable rewrite') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural phrases a user would actually say ('line edit', 'polish', 'tightening pass', 'usable rewrite') with good synonym coverage, but a few common variants ('copy edit', 'proofread') are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	'Line edit' and 'tightening pass' denote a distinct editorial stage clearly separated from developmental editing, giving a clear niche; minor overlap risk remains with broader copy-editing or general rewrite skills, so it is not a clean 5.	4 / 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: EveryInc/compound-writing
Path: skills/cw-line-edit/SKILL.md
Commit: 18702f0

Reviewed: 2 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.