CtrlK
BlogDocsLog inGet started
Tessl Logo

professional-proofreader

Use when a user asks to "proofread", "review and correct", "fix grammar", "improve readability while keeping my voice", and to proofread a document file and save an updated version.

59

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/professional-proofreader/SKILL.md

The canonical home for this skill is professional-proofreader in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 is well-structured with clear mode separation and real reference files, but the body over-lists grammar concepts Claude already knows, delegates most executable detail to references, and omits a validation checkpoint in the file-processing (save) workflow. Tightening the editing-standards lists and adding a validation step to file mode would lift the weaker dimensions.

Suggestions

Replace the Grammar/Spelling/Punctuation/Style concept lists with a concise directive (e.g. 'Correct grammar, spelling, punctuation, and tense while preserving voice') — Claude already knows these mechanics.

Add an explicit validation/feedback-loop step to the file-processing workflow (e.g. after regenerating the file, verify formatting integrity and that no content was dropped before confirming to the user), matching the validation pass already present in inline mode.

Move the bulk of the editing-standards detail into a reference file and keep the body as a lean overview, so the main SKILL.md earns its token budget more strictly.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids library tutorials, but the Grammar/Spelling/Punctuation/Style editing-standards sub-lists enumerate basic concepts Claude already knows (subject-verb agreement, commas, apostrophes), which is unnecessary padding that could be tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the leaner 4.

3 / 5

Actionability

Concrete guidance exists (supported file types, the UPDATED_ naming example), but the core executable workflow is delegated to the reference files and the body itself stays high-level, fitting the 'some concrete guidance but incomplete' anchor rather than the mostly-executable 4.

3 / 5

Workflow Clarity

Steps are sequenced in the reference files and inline mode has a validation pass, but file-processing mode — a save/overwrite operation — has no validation or feedback-loop checkpoint, so per the destructive/batch cap workflow clarity cannot exceed 3 even though the inline flow is reasonably clear.

3 / 5

Progressive Disclosure

The body is an overview pointing to two real, one-level-deep reference files (inline-text-mode.md, file-processing-mode.md) with clearly signaled links, giving good structure; the inlined Best Practices section is a minor split imperfection that keeps it just below the cleanly-split 5.

4 / 5

Total

13

/

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, trigger-rich description that clearly states both capability and when to use it with natural user phrases. It could reach a perfect score by surfacing file-extension triggers (.docx/.pdf) and 'polish this text' into the description itself.

DimensionReasoningScore

Specificity

The description names the domain and several concrete actions — 'proofread', 'fix grammar', 'improve readability while keeping my voice', and 'save an updated version' — giving good coverage with only minor gaps, matching the 'several specific actions; minor gaps' anchor rather than the less comprehensive 3 or the fully comprehensive 5.

4 / 5

Completeness

It explicitly answers both 'what' (proofread, fix grammar, improve readability, save an updated version) and 'when' via a clear 'Use when a user asks to...' clause with concrete trigger phrases, matching the 'clearly and explicitly answers both what AND when' anchor; the 'when' is explicit enough that it is not the weaker-when 4.

5 / 5

Trigger Term Quality

It includes natural phrases users would actually say ('proofread', 'review and correct', 'fix grammar', 'improve readability while keeping my voice'), giving good keyword coverage; a few natural terms and file extensions (e.g. .docx, .pdf, 'polish this text') appear only in the body, so it stops just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The proofreading/voice-preservation niche is mostly distinct with only minor overlap risk against general writing skills; the absence of file-type specifics in the description itself keeps it just below the minimal-conflict 5 anchor.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.