CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

local-review

Thin Codex skill shim for node_local_review. Use to run the OmniMarket local review loop through the runtime adapter.

Quality

70%

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 ./plugins/onex/skills/local-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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, operational dispatch guide with a concrete runnable command, a fully specified payload, preflight validation, and explicit output/error handling. Remaining gaps are minor: slight duplication of contract metadata, a placeholder payload requiring assembly, and an implicit rather than ordered step sequence.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanations of concepts Claude already knows; the trimmable parts are the command name and both topics restated in the "Contract" section after the "Runtime truth" block, plus the overlap between the arguments table and the payload JSON. That is minor over-explanation fitting anchor 4, not the lean-everything-earns-its-place of anchor 5.

4 / 5

Actionability

A concrete executable command ("env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py --command-name \"local_review\" ..."), a fully specified payload shape, and explicit ok/error handling make this mostly executable. It falls short of anchor 5 only because '<json-payload>' must be assembled from the shape below rather than being copy-paste ready.

4 / 5

Workflow Clarity

The single-dispatch flow is clear (build payload, run wrapper, interpret output_payloads[0] or surface error.code/error.message) with a real validation checkpoint in "--compile-only" and a dry_run option for the side-effectful review-commit loop. It is 4 rather than 5 because the sequence is implicit (payload construction is documented after the run command) and preflight is offered as optional rather than directed.

4 / 5

Progressive Disclosure

This is a single-file skill (no references/, scripts/, or assets/ bundle exists) with well-organized sections and a clearly delimited generated block. Structure is good and content is appropriately placed; the ~39-line generated "Runtime truth" block could arguably live in a separate reference file, which keeps it at anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

53%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 is specific to its niche and clearly states its purpose, but it reads as internal engineering shorthand rather than a trigger-optimized skill description. It lacks a 'when to use' clause and natural trigger phrases, and it does not enumerate the loop's concrete capabilities.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to run, start, or kick off the OmniMarket local review / review-fix loop, or mentions node_local_review."

Enumerate what the loop actually does in the description (review, fix, commit, clean-check, completion) so the 'what' is concrete rather than a single 'run the loop' action.

Include natural phrasings users would say (e.g. "local review", "review loop", "review and fix cycle") alongside the technical identifiers to improve trigger term coverage.

DimensionReasoningScore

Specificity

"Use to run the OmniMarket local review loop through the runtime adapter" names the domain and one concrete action, but does not enumerate what the loop covers (review, fix, commit, clean-check). It matches anchor 3 (domain plus 1-2 concrete actions) rather than 4, which requires several specific actions.

3 / 5

Completeness

The 'what' is clear (run the local review loop through the runtime adapter), but there is no 'Use when...' clause or equivalent trigger guidance; "Use to run..." states purpose, not invocation conditions. Per the judging guideline, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant in-project terms like "local review loop", "OmniMarket", and "Codex" are present, but "thin shim", "runtime adapter", and "node_local_review" are technical jargon and no synonyms or common user phrasings are covered. This is 'some relevant keywords but missing common variations', not the good coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

Highly specific identifiers ("node_local_review", "OmniMarket", "Codex", "runtime adapter") give this a clear niche with minor conflict risk. It sits at 4 rather than 5 because the phrase "local review" could mildly overlap with generic code-review skills since no distinct trigger phrases are given.

4 / 5

Total

13

/

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

plugins/onex/skills/local-review/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.