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

72%

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/bus-audit/SKILL.md

The canonical home for this skill is bus-audit in OmniNode-ai/omnimarket

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, dispatch-oriented shim document: the executable command, argument table, and output-handling rules make it directly actionable, and the compile-only preflight supplies a validation checkpoint. The main costs are duplicated transport metadata between the generated block and the Contract section, and evidence-schema detail that inflates the token budget without being needed at dispatch time.

Suggestions

Deduplicate the metadata repeated between the generated 'Runtime truth' block and the 'Contract' section (command name, contract command topic, terminal topic) — keep one authoritative location and reference it.

Move the runtime-evidence wire-schema and binding-field details into a references/ file, keeping only the dispatch-critical facts (how to check runtime_observation, compile-only semantics) inline, to tighten conciseness.

Add one concrete example JSON payload built from the documented fields so the dispatch command is fully copy-paste ready and the argument-to-payload mapping needs no assembly.

DimensionReasoningScore

Conciseness

The body is mostly project-specific and free of explanations of concepts Claude already knows, but it could be tightened: the command name and both contract topics appear twice (in the generated 'Runtime truth' block and again verbatim in the 'Contract' section), and the evidence wire-schema / binding-field detail (~15 lines) is operational depth that could be trimmed or moved out of the main file. This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') better than anchor 4, where such redundancy would be only minor.

3 / 5

Actionability

The Dispatch section gives a concrete, executable command ("env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py --command-name \"bus_audit_compute\" ..."), enumerates payload field names, documents the --compile-only preflight, and specifies output handling for both the ok and error paths. It falls short of anchor 5 only because there is no worked example payload JSON, leaving the user to assemble '<json-payload>' from the field list.

4 / 5

Workflow Clarity

The flow is clearly sequenced — map arguments to payload fields, dispatch via the wrapper (optionally validating first with --compile-only), then interpret output_payloads[0] or surface error.code/error.message. The compile-only preflight and explicit error path provide most checkpoints; what keeps it at anchor 4 rather than 5 is the absence of a retry/feedback loop after a failed dispatch and no numbered step order for the argument-to-payload mapping.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so this scores on structure alone: the single file is well organized into Arguments, Dispatch, Contract, and Output sections with a clearly delimited generated block. It sits at anchor 4 ('good structure; most content is appropriately placed') — the ~38-line generator-owned transport metadata is a candidate for a reference file, which is the minor organization gap that prevents a 5 for a file of this length (~112 lines).

4 / 5

Total

15

/

20

Passed

Description

66%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, third-person description with an explicit 'Use when' clause and a highly distinctive niche. Its main weakness is thin capability coverage: it names the audit domain but not the concrete actions the node performs, and it offers few trigger synonyms.

Suggestions

Enumerate the node's concrete actions (e.g., 'parses the event registry, checks contract wiring, classifies findings') instead of the single phrase 'auditing ... contract wiring health', to lift specificity.

Add natural trigger variations users might say, such as 'bus audit', 'event registry check', or 'topic contract health', to broaden trigger-term coverage.

Vary the 'when' clause beyond restating the 'what' — e.g., 'Use when the user asks to audit or health-check the OmniNode event bus, its topic registry, or contract wiring.'

DimensionReasoningScore

Specificity

The description names the domain ("auditing OmniNode event-bus topic registry and contract wiring health") and one or two concrete audit actions, but does not enumerate the node's specific capabilities (registry parsing, wiring checks, finding classification). It lists a domain with 1-2 actions rather than several specific actions, matching anchor 3 and falling short of anchor 4's 'several specific actions; minor gaps'.

3 / 5

Completeness

Both parts are explicit: the 'what' ("Thin Codex skill shim for node_bus_audit_compute") and the 'when' ("Use when auditing OmniNode event-bus topic registry and contract wiring health"). The trigger clause is present but narrow — a single domain phrase that largely mirrors the 'what' — so it does not reach anchor 5's 'concrete trigger phrases' with varied coverage; it is comfortably above anchor 3, where 'when' would be missing or only implied.

4 / 5

Trigger Term Quality

Relevant keywords are present ("auditing", "event-bus", "topic registry", "contract wiring") and would naturally appear in a request for this skill, but common variations and synonyms (e.g., "bus audit", "event registry check", "contract health check") are missing. This fits anchor 3 ('some relevant keywords but missing common variations or synonyms') better than anchor 4's fuller keyword coverage.

3 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche — a named backing node ("node_bus_audit_compute") and a specific OmniNode event-bus audit scope — so it is unlikely to trigger for unrelated skills. This matches anchor 5 ('clear niche with distinct triggers; minimal conflict risk'); anchor 4's 'minor overlap risk with closely related skills' would understate how scoped the triggers are.

5 / 5

Total

15

/

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/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.