Name: writing-clearly-and-concisely
Rating: 80 (1 reviews)
Author: softaworks

writing-clearly-and-concisely

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

1.01x

Quality

71%

Does it follow best practices?

Impact

96%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./dist/plugins/writing-clearly-and-concisely/skills/writing-clearly-and-concisely/SKILL.md

The canonical home for this skill is writing-clearly-and-concisely in softaworks/agent-toolkit

Quality

Content

63%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 lean, well-structured skill body that points readers to per-section reference files with token budgets and flags the most-useful one. Its effectiveness is undercut because none of the referenced bundle files are actually present, leaving the core rules without their examples.

Suggestions

Include the referenced bundle files (elements-of-style/02-elementary-rules-of-usage.md, 03-elementary-principles-of-composition.md, 04-a-few-matters-of-form.md, 05-words-and-expressions-commonly-misused.md, and signs-of-ai-writing.md) so the one-level-deep pointers resolve.

Add a brief before/after example inline for at least the highest-leverage rules (active voice, positive form, omit needless words) so the body is actionable even before a reference file is loaded.

If the bundle is intentionally absent, note that in the body or restructure so the essential examples live inline rather than behind missing references.

Dimension	Reasoning	Score
Conciseness	The body is efficient—compact rule one-liners, a lean reference table with token estimates, and targeted AI-pattern lists—assuming Claude's competence throughout; only minor trims (the Wikipedia provenance note, the "LLMs regress to statistical means" aside) keep it from a 5.	4 / 5
Actionability	The AI-patterns section gives concrete, usable word lists and the limited-context strategy is a clear 3-step process, but the core Strunk rules are bare one-liners (e.g. "Put statements in positive form") with no in-body examples, and the example-bearing reference files they point to are absent.	3 / 5
Workflow Clarity	The limited-context strategy is a clear, ordered sequence (draft → dispatch subagent with section file → receive revision); no validation checkpoints are required for a non-destructive copyedit task, so the simple-skill guidance applies and the sequence reads cleanly.	4 / 5
Progressive Disclosure	The body is well organized with a clearly signaled one-level-deep reference table (file, ~tokens) and a recommended default file, but every referenced bundle path (elements-of-style/02–05, signs-of-ai-writing.md) is missing from the bundle, so the disclosure points to files that do not exist.	3 / 5
	Total	14 / 20 Passed

Description

78%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 clearly states both capability and trigger conditions with natural, varied keywords. Its main weakness is specificity: it names the method (Strunk's rules) without enumerating the concrete writing actions it performs.

Dimension	Reasoning	Score
Specificity	Names the domain and method ("Applies Strunk's timeless rules for clearer, stronger, more professional writing") but offers only one action rather than a comprehensive list of concrete actions; not minimal enough for 2 yet lacking the several specific actions required for 4.	3 / 5
Completeness	It explicitly answers both what ("Applies Strunk's timeless rules for clearer, stronger, more professional writing") and when ("Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms a user would actually say are well represented ("documentation, commit messages, error messages, explanations, reports, or UI text") with good coverage, but a few common variations (e.g. emails, release notes, blog posts) are missing, keeping it short of fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The Strunk/clear-writing niche is mostly distinct and the trigger is specific to human-facing prose, but the broad list of contexts (docs, commits, UI text, reports) carries minor overlap risk with dedicated documentation or commit-message skills.	4 / 5
	Total	16 / 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: softaworks/agent-toolkit
Path: dist/plugins/writing-clearly-and-concisely/skills/writing-clearly-and-concisely/SKILL.md
Commit: 3027f20

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.