CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aislop-sweep

Thin Codex skill shim for node_aislop_sweep. Use when scanning OmniNode repos for AI-generated quality anti-patterns or AI slop.

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 ./src/omnimarket/adapters/codex/skills/aislop-sweep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, largely executable adapter skill with a clear dispatch workflow and error handling. Its weaknesses are redundancy — contract metadata appears in both the Runtime truth and Contract sections — and minor gaps like the missing example JSON payload and the structurally split Arguments section.

Suggestions

Deduplicate the contract metadata: the "Contract" section repeats the command name, topics, backing node, and wrapper already stated in the generated "Runtime truth" block — keep only one copy or reduce the Contract section to a pointer.

Add a concrete example JSON payload for --payload (e.g., {"target_dirs": ["/abs/repo"], "checks": [...], "severity_threshold": "WARNING"}) so the dispatch command is copy-paste ready.

Reposition the generated "Runtime truth" block so the "## Arguments" header sits directly above its argument table, or move the dense generated metadata into a reference file referenced from the body.

DimensionReasoningScore

Conciseness

The "Runtime truth" block and the "Contract" section duplicate the same metadata (command name, command topic, terminal topic, backing node, request wrapper), a section-level redundancy beyond minor trimming, though the rest of the body is efficient with no concept over-explanation.

3 / 5

Actionability

Provides an executable dispatch command with flags, explicit argument-to-payload mapping, error handling ("surface error.code and error.message"), and output interpretation; the "<json-payload>" placeholder without a concrete example payload keeps it from being copy-paste ready.

4 / 5

Workflow Clarity

The sequence is clear (resolve paths, map payload, optional --compile-only preflight, dispatch, interpret ok/error, render) with a described validation option and explicit error path, but the preflight is optional rather than a mandated validate-then-proceed checkpoint.

4 / 5

Progressive Disclosure

Sections are well-organized (Arguments, Runtime truth, Dispatch, Contract, Output) with the generated block clearly delimited, but the "## Arguments" header is orphaned from its table by the ~40-line generated block, and dense inline contract metadata is duplicated rather than split into a reference file.

4 / 5

Total

15

/

20

Passed

Description

73%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 concise, distinctive description with an explicit "Use when" trigger clause and natural trigger terms. Its main weakness is specificity: it describes what the skill is (a shim over node_aislop_sweep) more concretely than what it does.

DimensionReasoningScore

Specificity

"scanning OmniNode repos for AI-generated quality anti-patterns or AI slop" names the domain and one concrete action, but "Thin Codex skill shim for node_aislop_sweep" describes the skill's form rather than enumerating its concrete capabilities.

3 / 5

Completeness

Both elements are present: an explicit "Use when scanning OmniNode repos for..." trigger clause and a what-statement, but the "what" is indirect (a shim over a node) rather than a clear enumeration of actions, keeping it below a 5.

4 / 5

Trigger Term Quality

Includes natural phrases users would say — "AI slop", "AI-generated", "anti-patterns", "scanning" — giving good keyword coverage, though common variations like "LLM-generated code" or "slop detection" are missing.

4 / 5

Distinctiveness Conflict Risk

"AI slop" and "AI-generated quality anti-patterns" in OmniNode repos form a clear niche with distinct trigger terms and minimal overlap risk with generic quality or lint skills.

5 / 5

Total

16

/

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

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

OmniNode-ai/omnimarket

Path

src/omnimarket/adapters/codex/skills/aislop-sweep/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.