CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deslop

Remove AI-generated code slop and clean up code style

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/deslop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 body is a tight, well-organized instruction skill: one concrete command, specific slop patterns, and clear guardrails, with no wasted tokens. Its main weaknesses are the absence of any validation checkpoint backing the behavior-preservation guardrail and a dangling `LICENSE.txt` reference.

Suggestions

Add a verification step supporting the "Keep behavior unchanged" guardrail, e.g. "After edits, run the project's tests/typecheck to confirm behavior is unchanged."

Ship the referenced `LICENSE.txt` (or drop the reference) so the body's only file mention is not dangling.

Add one short before/after example of a slop pattern (e.g., a defensive try/catch around trusted code) to make the focus categories concrete.

DimensionReasoningScore

Conciseness

The ~20-line body is lean throughout: a single concrete diff command, terse focus-area bullets, and three one-line guardrails, with zero explanation of concepts Claude already knows (it never defines 'slop' or 'merge base' pedantically). Not 4 because nothing beyond the one-line provenance footer could be trimmed, and that footer is standard attribution rather than over-explanation.

5 / 5

Actionability

Provides the concrete command `git diff origin/next...HEAD` and specific, executable pattern categories ("Casts to `any` used only to bypass type issues", "Deeply nested code that should be simplified with early returns") — 'mostly executable guidance with minor gaps'. Not 5 because there are no before/after examples of the slop patterns or concrete fixes, and not 3 because the guidance is specific and directly actionable, not pseudocode-level.

4 / 5

Workflow Clarity

The sequence is only implicit (diff → identify slop → apply minimal edits → summarize) and, critically, the guardrail "Keep behavior unchanged unless fixing a clear bug" has no verification checkpoint (e.g., run tests/typecheck after edits) — matching 'steps listed but validation gaps; checkpoints missing or implicit'. Not 4 because a whole-PR edit pass without any behavior-verification step is a real validation gap; not 2 because the flow is coherent and the guardrails define clear boundaries.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no content that belongs in separate files, and the Focus Areas / Guardrails sections are cleanly organized (which would justify a 5 under the simple-skill note) — but the body references `LICENSE.txt`, which does not exist in the bundle, a dangling reference that is a minor organization gap. Not 3 because the in-body structure itself is clean and well-signaled.

4 / 5

Total

16

/

20

Passed

Description

50%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.

The description states a clear, distinctive core action (removing AI-generated code slop) but is thin: only two action phrases, no trigger/usage guidance, and no synonym coverage. It reads as a minimal working description rather than a well-optimized one.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions AI slop, asks to deslop or tidy AI-generated code, or wants AI-added comments/defensive code removed."

Enumerate 1-2 more concrete capabilities from the body (e.g., removing unnecessary comments, defensive try/catch in trusted paths, `any` casts used to bypass typing) to raise specificity.

Include natural synonyms such as "deslop", "simplify", or "clean up AI code" to improve trigger-term coverage and reduce misses on variant phrasings.

DimensionReasoningScore

Specificity

"Remove AI-generated code slop" is one concrete action and "clean up code style" is a generic second action — matching the anchor 'names domain and 1-2 concrete actions, but not comprehensive'. It is not 4 because no several specific actions are enumerated (e.g., removing redundant comments, defensive try/catch, `any` casts), and not 2 because a real, concrete action is stated beyond merely naming the domain.

3 / 5

Completeness

The description clearly answers 'what' ("Remove AI-generated code slop and clean up code style") but contains no 'when' clause whatsoever — no "Use when..." or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than just implicit or imprecise.

3 / 5

Trigger Term Quality

"AI-generated code slop" and "clean up code style" are relevant, natural phrases users would say, but common variations and synonyms ("deslop", "simplify", "tidy up", "refactor AI code") are missing — 'some relevant keywords but missing common variations'. Not 4 because keyword coverage is thin (two phrases), not 2 because 'code slop' is a term users genuinely use when they need this.

3 / 5

Distinctiveness Conflict Risk

"AI-generated code slop" carves a recognizable niche, but "clean up code style" is broad and overlaps with formatting, linting, and code-simplification skills — 'somewhat specific but could still overlap with similar skills'. Not 4 because the generic style-cleanup half invites conflicts; not 2 because the AI-slop framing is distinctive, not merely 'helps with code'.

3 / 5

Total

12

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

novuhq/novu

Path

.agents/skills/deslop/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.