CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-noslop

Rewrite, check, or draft prose so it carries no AI writing tells, reads plainly on the first read, and keeps every source fact. Use when asked to make writing plainer or free of those tells, to check writing for them, or when drafting from supplied content. Use ce-promote for channel-specific marketing copy.

Quality

87%

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

86%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.

An exemplarily lean instruction-only skill: crisp mode dispatch, concrete sentence-level tests, and clean one-level reference structure. Its only weaknesses are a few opaque sentences and the absence of an explicit final verification pass against its own Done criteria.

Suggestions

Rewrite the garbled scope sentence "Note that the pattern catalog did not apply inside detect findings or inside a change line the caller asked for, and nowhere else" as a plain rule, e.g. "Do not apply the pattern catalog inside detect findings or inside a change line the caller asked for; nowhere else."

Clarify the author-mode instruction "Hold the tests below while the caller writes; return nothing" — state plainly that author mode constrains in-progress writing and produces no output of its own.

Add an explicit final step for edit mode: re-check the returned text against the Done criteria (all facts survive, nothing added) before returning it.

DimensionReasoningScore

Conciseness

Forty lean lines with zero concept explanation; every line is a dispatch rule, test, or boundary ("Rewrite only the sentences a test fails on", "Keep exact identifiers, paths, commands, and thresholds"), fully assuming Claude's competence.

5 / 5

Actionability

Concrete guidance throughout: explicit mode-dispatch heuristics ("no draft means author; an imperative on a draft means edit; a question about a draft means detect") and seven named tests with decision criteria. A few cryptic passages ("Hold the tests below while the caller writes; return nothing") and one garbled sentence about where the pattern catalog applies keep it below fully executable.

4 / 5

Workflow Clarity

Clear sequence (mode dispatch, apply tests, consult patterns.md when tests don't settle it, output per contract) with real checkpoints: the Done criteria ("every fact, number, name, quote, and citation in the input survives") and edit idempotency ("a second pass on the returned text changes nothing"). Minor gap: no explicit verify-against-Done step before returning.

4 / 5

Progressive Disclosure

Lean overview body with two one-level-deep references (references/patterns.md, references/terminology.md), both verified to exist, each clearly signaled at the point of need; the 10KB pattern catalog is correctly split out of SKILL.md.

5 / 5

Total

18

/

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 explicit what and when clauses, natural trigger phrasing, and a rare explicit de-confliction pointer to a sibling skill. The only gaps are a few missing synonyms and slightly broad drafting triggers.

DimensionReasoningScore

Specificity

Lists three concrete actions ("Rewrite, check, or draft prose") with explicit success constraints ("carries no AI writing tells", "reads plainly on the first read", "keeps every source fact"), but coverage is less comprehensive than the top anchor's per-action detail.

4 / 5

Completeness

Clearly answers both: what ("Rewrite, check, or draft prose so it carries no AI writing tells...") and when ("Use when asked to make writing plainer or free of those tells, to check writing for them, or when drafting from supplied content") with three concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases users would say are present ("make writing plainer", "free of those tells", "check writing for them", "drafting from supplied content"), though common synonyms like "AI slop" or "humanize" are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers and explicit de-confliction ("Use ce-promote for channel-specific marketing copy"), but "drafting from supplied content" is broad enough to overlap with general writing-assistance skills, so minor overlap risk remains.

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

EveryInc/compound-engineering-plugin

Path

skills/ce-noslop/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.