CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ai-writing-detector

Use when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local detector result when the host can execute Node.

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, executable skill body: copy-paste commands verified against the bundled detector script, a clearly sequenced preferred path with a fallback and stop conditions, and bulk detail properly delegated to bundle files. Remaining weaknesses are a slightly redundant evidence-lens restatement of the canonical cautions and no error-recovery guidance for detector failures.

DimensionReasoningScore

Conciseness

No padding or explanations of known concepts; every section carries operational instructions, and the heavy rulebook and 193KB pattern data are correctly kept out of the body. Minor over-explanation exists: the evidence-lens bullets ("consider false positives and genre/register effects", "never convert pattern detection into an authorship classifier claim") partially restate the canonical cautions already invoked in the Authority section, so it does not reach the 5 anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready commands covering the common input cases — stdin ("printf '%s' \"$TEXT\" | node scripts/detect.js --context general"), file input, and frontmatter-bearing Markdown (--source-mode rendered-markdown) — with flags that match the actual bundled script, plus an explicit no-Node fallback. This matches the 5 anchor's coverage of common cases with ready-to-run commands.

5 / 5

Workflow Clarity

The Preferred path is a clear numbered sequence with explicit flag-selection conditionals, an execution-status checkpoint ("Never claim execution unless the command actually ran"), a fallback branch for missing Node, and explicit stop conditions. It falls short of the 5 anchor because there is no error-recovery guidance if the detector command itself fails; it is above the 3 anchor since a real checkpoint (execution evidence) is present.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep references: scripts/detect.js is a real bundled file, and cross-skill pointers (../avoid-ai-writing/SKILL.md, router references) are named explicitly rather than buried. It does not reach 5 because a sizable inline connection-contract section could live in a reference file, and several referenced paths sit outside this bundle where their content cannot be verified.

4 / 5

Total

17

/

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 with an explicit 'Use when...' trigger clause, five concrete action verbs, and a clear detect-only boundary that distinguishes it from rewriting skills. The main gaps are missing natural noun synonyms and no hint of what the detector's output looks like.

DimensionReasoningScore

Specificity

Lists several concrete actions ("detect, scan, audit, score, or flag AI-writing patterns") plus a "deterministic local detector result" capability, but never states what the output includes (score, label, issue types), leaving minor gaps in coverage. It exceeds the 3 anchor's 1-2 actions but falls short of the 5 anchor's comprehensive coverage.

4 / 5

Completeness

Explicitly answers both questions: what it does ("detect, scan, audit, score, or flag AI-writing patterns without rewriting the text") and when to use it ("Use when the user asks to...") with concrete trigger phrases. Both halves are explicit and concrete, matching the 5 anchor rather than the 4 anchor's merely adequate 'when'.

5 / 5

Trigger Term Quality

"detect, scan, audit, score, or flag" are natural verbs a user would say when requesting this skill, giving good keyword coverage. A few natural noun phrases are missing (e.g., "AI-generated", "AI-written", "sounds like ChatGPT"), so it does not reach the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"without rewriting the text" and "deterministic local detector" clearly carve out a detect-only niche distinct from sibling rewriting and model-only review skills. Minor overlap risk remains with closely related skills in the same AI-writing family (e.g., a companion rulebook or rewriter skill sharing the "AI-writing" trigger vocabulary).

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.

Validation — 15 / 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

conorbronsdon/avoid-ai-writing

Path

skills/ai-writing-detector/SKILL.md

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.