cli-policy-audit

Inspect audit logs, manage access policies, view telemetry data, and review request history from the CLI. Filter by event type, user, or time range for compliance workflows.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Risky

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/cli-policy-audit/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an auto-generated CLI reference that is concrete but shallow: examples are placeholder-laden, flags are undocumented, destructive operations lack validation steps, and the whole catalog is inline rather than split into referenced files. It is serviceable but not executable-ready.

Suggestions

Replace placeholder examples with real, copy-paste-ready invocations (e.g., 'omniroute audit search "login" --actor user-42 --since 2026-07-01') and document valid values for flags like --format and --source.

Add a short workflow for destructive/batch operations with a validation checkpoint (e.g., 'policy list' to confirm the id, then 'policy delete <id> --yes', then verify with 'policy get <id>').

Move the long per-subcommand flag reference into a separate REFERENCE.md and keep SKILL.md as a concise overview with one-level-deep links, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The catalog is mostly terse, but every subcommand repeats identical 'Example:' boilerplate showing only the bare command (no added value over the heading), and flags like '--combo', '--status', '--duration-min' are listed with no explanation, leaving inefficient repetition and cryptic flag soup.	2 / 3
Actionability	Real commands and flags are present (not vague), but examples use literal placeholders ('audit search <query>', 'policy create') with no real values, and flags like '--format <f>' and '--source <s>' give no valid values, so guidance is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	It is a flat reference catalog with no sequencing or validation guidance; destructive/batch commands ('policy delete', 'policy import --overwrite', 'audit export') lack verification steps, so per the rubric workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the ~240-line body is a single monolithic command catalog with everything inline and no overview-to-detail split or external references, matching the anchor where content that should be separate is inline despite some section organization.	2 / 3
	Total	8 / 12 Passed

Description

82%

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 and well-targeted with good natural trigger terms and a clear niche, but it omits an explicit 'Use when...' clause, which caps completeness. Adding an explicit usage-trigger sentence would raise it to a top-tier description.

Suggestions

Append an explicit trigger clause such as 'Use when the user needs to review audit trails, manage or evaluate access policies, or pull telemetry for compliance reporting.'

Add common natural variations users might say (e.g., 'who changed this policy', 'policy violations', 'access review') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Inspect audit logs, manage access policies, view telemetry data, and review request history') plus filter capabilities ('Filter by event type, user, or time range'), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the 'for compliance workflows' phrase only implies when, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	Includes natural user-facing terms ('audit logs', 'access policies', 'telemetry data', 'request history', 'compliance workflows') that a user would plausibly say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The CLI audit/policy/compliance niche with distinct triggers (audit logs, access policies, telemetry, compliance) is unlikely to overlap with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: diegosouzapw/OmniRoute
Path: skills/cli-policy-audit/SKILL.md
Commit: 3070925

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.