CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-anti-ai

This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's "Signs of AI writing" guide, detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive phrases.

63

Quality

75%

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 ./skills/writing-anti-ai/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 skill body with good bilingual examples and real reference files, weakened by redundant restating of the same patterns across sections and by broken example-file references. Adding a meaning-preservation validation step and either creating or removing the missing examples/ paths would lift the lower dimensions.

Suggestions

Add an explicit validation checkpoint to the workflow (e.g., re-read the edited text and confirm the original meaning survives) to turn the destructive rewrite loop into a validate->fix->retry cycle.

Create the referenced examples/english.md and examples/chinese.md files, or remove the dangling 'examples/' references from the Examples section to keep navigation intact.

Consolidate the repeated pattern/fix lists (Core Rules, Common AI Patterns, Quick Reference, Best Practices) into a single source and reference it, and drop or move the self-scoring rubric to a reference file to reduce token redundancy.

DimensionReasoningScore

Conciseness

Mostly efficient tables/examples, but the same patterns and fixes are restated across 'Core Rules', 'Common AI Patterns', 'Quick Reference', and 'Best Practices', and the self-scoring rubric is tangential to acting on the skill.

2 / 3

Actionability

Concrete before/after pairs and pattern→fix tables are present, but guidance is illustrative rather than an exhaustive, copy-paste-ready procedure, and some rules stay abstract ('Break formulaic structures', 'Vary rhythm').

2 / 3

Workflow Clarity

The 5-step workflow is sequenced, but text editing is destructive to the original prose and there is no validation/checkpoint verifying meaning was preserved after rewrites, capping destructive-edit workflows at 2.

2 / 3

Progressive Disclosure

Overview points to real one-level-deep reference files with clear navigation, but the body references examples/english.md and examples/chinese.md that do not exist in the bundle, leaving broken navigation paths.

2 / 3

Total

8

/

12

Passed

Description

100%

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, third-person description that covers capabilities, natural trigger phrases, and use conditions comprehensively while remaining concise. It distinguishes the skill clearly and is unlikely to conflict with others.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and detection targets ('detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive phrases').

3 / 3

Completeness

Explicitly states both what it does ('detects and fixes...') and when to use it ('should be used when the user asks to...'), with explicit triggers.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say ('humanize this text', 'make this sound more natural', 'fix robotic writing') rather than jargon.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (AI-writing-pattern removal, EN/ZH) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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
Galaxy-Dawn/claude-scholar
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.