CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bus-audit

Thin Codex skill shim for node_bus_audit_compute. Use when auditing OmniNode event-bus topic registry and contract wiring health.

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 ./plugins/onex/skills/bus-audit/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.

The body delivers concrete, executable dispatch guidance with real validation machinery (compile-only preflight, runtime evidence checks, explicit error surfacing), reading as reference documentation for a single-action adapter skill rather than a step-by-step workflow. Its main weaknesses are structural redundancy — the Contract section and payload field list repeat facts already stated — and the absence of a worked example payload. Organization is good but the generated block is misplaced under '## Arguments'.

Suggestions

Delete the '## Contract' section or trim it to only new information (the backing node path 'src/omnimarket/nodes/node_bus_audit_compute/'); the command name, request wrapper, and both topics are already stated verbatim in the generated runtime-truth block.

Replace the 10-line payload field list with a single line ('use the same field names as the arguments table') plus one concrete example JSON payload, which also closes the actionability gap left by the '<json-payload>' placeholder.

Move the generated runtime-truth block out from under '## Arguments' into its own section (e.g. '## Runtime contract') so the arguments table directly follows its header.

DimensionReasoningScore

Conciseness

The body is mostly efficient operational detail with no concept over-explanation, but the '## Contract' section restates the command name, request wrapper, and both topics verbatim from the generated runtime-truth block, and the payload field list ('scope', 'registry_path', ... 'dry_run') duplicates the argument table's field names.

3 / 5

Actionability

The dispatch command ('env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py --command-name "bus_audit_compute" ...') is concrete and nearly copy-paste ready with explicit error handling ('surface error.code and error.message directly'), but '--payload <json-payload>' is a placeholder and no example JSON payload is provided.

4 / 5

Workflow Clarity

The flow (map arguments to payload, optional '--compile-only' preflight, dispatch, check 'ok'/'output_payloads' or surface the error) is discernible and validation checkpoints exist (compile-only preflight, 'runtime_evidence' inspection), but the sequence is implicit rather than explicitly ordered and evidence inspection appears only in the generated metadata.

4 / 5

Progressive Disclosure

A well-organized single-file skill with clear section headers and no nested references, but the ~40-line generated runtime-truth block sits oddly between the '## Arguments' header and its table, and the redundant '## Contract' section is a minor organization gap.

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.

The description is concise, in third person, and explicitly answers 'when' with concrete domain triggers, occupying a clearly distinct niche. Its main weakness is the 'what': leading with 'Thin Codex skill shim for node_bus_audit_compute' describes implementation structure rather than the concrete audit capabilities the node performs, leaving specificity and completeness just short of the top anchors.

Suggestions

Replace the structural 'what' ('Thin Codex skill shim for node_bus_audit_compute') with the node's concrete capabilities — parsing the event registry, checking contract wiring, classifying findings — to lift both specificity and completeness.

Add one or two natural trigger variations (e.g. 'bus audit', 'event registry health check') so the description matches more phrasings a user would actually say.

DimensionReasoningScore

Specificity

'Use when auditing OmniNode event-bus topic registry and contract wiring health' names the domain and one concrete action with specific targets, but the description lists only a single verb rather than several concrete actions (e.g. registry parsing, wiring checks, finding classification).

3 / 5

Completeness

The 'Use when auditing...' clause explicitly answers 'when' with concrete trigger phrases, and 'Thin Codex skill shim for node_bus_audit_compute' states what it is — but the 'what' is structural jargon ('shim', node id) rather than a clear capability statement, so it is not a full 5.

4 / 5

Trigger Term Quality

'auditing', 'event-bus', 'topic registry', and 'contract wiring' are terms a user in this domain would naturally say, giving good keyword coverage; a few natural variations (e.g. 'bus audit', 'registry check') are missing, so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

'OmniNode event-bus topic registry and contract wiring health' pins a clear niche with distinct triggers tied to a specific backing node, making conflict with other skills minimal.

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

plugins/onex/skills/bus-audit/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.