writing-clearly-and-concisely

Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.

1.02x

Quality

66%

Does it follow best practices?

Impact

94%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-mikeastock/skills/writing-clearly-and-concisely/SKILL.md

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.

The body is a tidy, well-organized overview that mostly respects token budget and gives one clear subagent workflow. Its core weakness is that it leans on a referenced `elements-of-style.md` that is absent from the bundle, leaving both actionability and progressive disclosure incomplete.

Suggestions

Ship the referenced `elements-of-style.md` in `references/` (or inline the essential rules) so the skill is self-contained and the progressive-disclosure reference resolves.

Expand the terse rule one-liners into at least one concrete before/after example so the guidance is executable without the missing file.

Drop the 'Bottom Line' section or merge it into 'When to Use' to remove the duplicated take-away and tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean — terse rule one-liners, a one-line framing of Strunk, and a token-cost warning — and mostly assumes Claude's competence. The 'Bottom Line' section and the bolded 'If you're writing sentences for a human to read, use this skill' partly restate 'When to Use', which is minor over-explanation that could be trimmed.	4 / 5
Actionability	Rules like 'Use active voice' and 'Omit needless words' are actionable directives and the Limited Context Strategy is a concrete subagent process, but the rules are abstract reminders and the body defers all real detail to `elements-of-style.md`, which is not present in the bundle — leaving the guidance incomplete rather than copy-paste ready.	3 / 5
Workflow Clarity	The Limited Context Strategy gives a clear numbered 3-step sequence (draft → dispatch subagent with the guide → receive revision), and the default flow ('read the file and apply the rules') is unambiguous for a simple skill. There are no validation checkpoints, but the task is non-destructive so none are required, leaving only minor gaps.	4 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and signals a single one-level-deep reference (`elements-of-style.md`) with a clear token-cost warning, but no bundle directories or referenced file exist in the skill, so the disclosure points to a missing file — a broken reference that undermines the otherwise good structure.	3 / 5
	Total	14 / 20 Passed

Description

70%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 is clear and covers both what the skill does and a broad range of when-to-use contexts with natural trigger terms. Its main weakness is that the action side is a single generic verb ('apply rules') rather than multiple concrete actions, and it lacks a standalone 'Use when' clause.

Suggestions

Lead with 2-3 concrete actions (e.g. 'Tighten verbose drafts, fix passive voice, and cut needless words') instead of the single generic 'apply rules'.

Add an explicit standalone trigger clause such as 'Use when writing or editing any prose for humans — commit messages, docs, error messages, UI copy, or reports.'

Narrow 'ANY prose humans will read' or pair it with sharper triggers to reduce overlap with general writing/editing skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Apply Strunk's timeless writing rules') and enumerates concrete target types (documentation, commit messages, error messages, UI text), but the only action offered is 'apply rules' — a single generic action rather than the multiple distinct concrete actions a 4 or 5 would list.	3 / 5
Completeness	It answers both 'what' (apply Strunk's writing rules) and 'when' (ANY prose humans will read, with an explicit enumerated list of contexts), but the 'when' is embedded in the 'what' sentence rather than a standalone 'Use when...' clause, so it stops short of the explicit, separated trigger phrasing of a 5.	4 / 5
Trigger Term Quality	Natural user-facing terms like 'documentation, commit messages, error messages, explanations, reports, or UI text' plus 'prose' give good keyword coverage; a few common synonyms (e.g. emails, blog posts, copywriting) are missing, keeping it just below a 5.	4 / 5
Distinctiveness Conflict Risk	'Writing clearly and concisely' via Strunk's rules is a recognizable niche with concrete, distinguishing triggers (commit messages, error messages, UI copy), but the very broad 'ANY prose humans will read' scope leaves minor overlap risk with general writing or editing skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-mikeastock/skills/writing-clearly-and-concisely/SKILL.md
Commit: 6453c0b

Reviewed: about 10 hours 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.