CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

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

The canonical home for this skill is ce-noslop in EveryInc/compound-engineering-plugin

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 lean, well-structured instruction skill: unambiguous mode dispatch, concrete per-mode outputs, explicit done-criteria and idempotency validation, and clean one-level references to a real pattern catalog and terminology guide. The main defect is one garbled boundary sentence about where the pattern catalog applies.

Suggestions

Rewrite the sentence "Note that the pattern catalog did not apply inside detect findings or inside a change line the caller asked for, and nowhere else." — its meaning is ambiguous; state plainly where pattern findings may and may not appear.

Add one short before/after sentence pair under 'The tests' showing a failing sentence and its fix, so the checks are executable without opening references/patterns.md.

DimensionReasoningScore

Conciseness

The ~46-line body is lean throughout: no concept explanations Claude already knows, no padding, and every rule earns its place (e.g. "A sentence that passes stays as written, so a second pass on the returned text changes nothing"). It matches the 'every token earns its place' anchor.

5 / 5

Actionability

Concrete, executable guidance for an instruction-only skill: an unambiguous mode-dispatch rule ("no draft means author; an imperative on a draft means edit; a question about a draft means detect"), per-mode outputs, and seven named checks. Not 5 because one sentence is hard to parse ("Note that the pattern catalog did not apply inside detect findings or inside a change line the caller asked for, and nowhere else.") and no pass/fail sentence examples are given, leaving minor execution gaps.

4 / 5

Workflow Clarity

Clear sequence (dispatch mode → apply tests → edit or detect → return), with explicit validation checkpoints: a "Done:" definition acting as a completion checklist ("every fact, number, name, quote, and citation in the input survives") and an idempotency check for edit mode ("a second pass on the returned text changes nothing"). Not destructive or batch, so no cap applies.

5 / 5

Progressive Disclosure

The body is a well-organized overview with two clearly signaled, real, one-level-deep references ("read `references/patterns.md`", "read `references/terminology.md`"), each loaded only when the inline tests do not settle a case; both files exist and are appropriately split out of the main body.

5 / 5

Total

19

/

20

Passed

Description

92%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: concrete actions with success criteria, an explicit and multi-condition 'Use when' trigger clause, third-person voice, and an explicit boundary to a sibling skill. The only minor gap is a few natural synonyms users might phrase differently.

DimensionReasoningScore

Specificity

"Rewrite, check, or draft prose" names three concrete actions mapping to the skill's three modes, each with concrete success criteria ("carries no AI writing tells, reads plainly on the first read, and keeps every source fact"). Coverage is comprehensive within its domain; not 4 because no capability area of the skill is left unlisted.

5 / 5

Completeness

It explicitly answers 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 concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Natural phrases like "make writing plainer", "free of those tells", and "check writing for them" match what a user would say. A few common synonyms are missing (e.g. "sound less AI", "humanize", "robotic writing"), so it falls just short of the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (AI-tell-free prose with fact preservation) and even disambiguates a neighboring skill ("Use ce-promote for channel-specific marketing copy"), minimizing overlap risk; not 4 because the trigger conditions are specific to this skill's purpose rather than generic editing.

5 / 5

Total

19

/

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
crdant/compound-engineering-plugin
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.