Name: audit-report
Rating: 72.8 (1 reviews)
Author: harness

audit-report

Generate audit reports and compliance trails using Harness audit trail data via MCP v2 tools. Track user actions, resource changes, authentication events, and access patterns across accounts, organizations, and projects. Use when asked to audit activity, generate compliance reports, investigate security incidents, review user actions, check change logs, or produce SOC2/GDPR/HIPAA audit evidence. Trigger phrases: audit report, audit trail, compliance audit, user activity log, change log, access audit, security investigation, who changed what, audit events.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 content is well-structured and actionable with a clear sequenced workflow, appropriate validation for the batch pagination operation, and good progressive disclosure via a single clearly-signaled reference file. The main gaps are minor: redundant reference pointing in Step 6 and placeholder-based code examples.

Suggestions

Consolidate the two sentences in Step 6 that both point to references/report-templates.md into a single clear pointer to remove redundancy.

Add at least one fully-resolved harness_list example with realistic values (not <org>/<project> placeholders) to lift actionability toward copy-paste-ready.

Move the pagination feedback loop ("if size returned equals size requested, increment page") into the main Step 2 workflow as an explicit checkpoint rather than relegating it to Troubleshooting.

Dimension	Reasoning	Score
Conciseness	The body uses lean tables and code blocks and avoids explaining concepts Claude already knows, but Step 6 redundantly points to references/report-templates.md in two near-identical sentences, a minor over-explanation that keeps it below 5.	4 / 5
Actionability	Concrete harness_describe and harness_list calls with parameters plus action/resource/error tables give mostly executable guidance, but the placeholder-filled examples (<org>, <project>) leave minor gaps versus copy-paste-ready code at 5.	4 / 5
Workflow Clarity	Steps 1-6 are clearly sequenced with validation present (pagination completeness check, "verify every claim against actual audit data"), satisfying the batch-operation requirement; it stays at 4 rather than 5 because the pagination feedback loop lives in Troubleshooting rather than inline in the main workflow.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview that delegates templates and compliance mappings to the real, one-level-deep references/report-templates.md (verified to exist), with the reference clearly signaled in Step 6, matching the score-5 anchor.	5 / 5
	Total	17 / 20 Passed

Description

100%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 strong across all dimensions: it states concrete capabilities, includes a rich set of natural trigger phrases, answers both what and when explicitly, and occupies a distinct niche. Voice is correctly third-person imperative with no first/second-person usage.

Dimension	Reasoning	Score
Specificity	"Generate audit reports and compliance trails" and "Track user actions, resource changes, authentication events, and access patterns" list multiple concrete actions with comprehensive coverage, matching the score-5 anchor rather than the minor-gaps anchor at 4.	5 / 5
Completeness	It explicitly states both what ("Generate audit reports and compliance trails...") and when ("Use when asked to audit activity, generate compliance reports, investigate security incidents...") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	The "Trigger phrases:" list (audit report, audit trail, compliance audit, user activity log, change log, access audit, security investigation, who changed what, audit events) provides comprehensive natural-term coverage including synonyms, matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	"Harness audit trail data via MCP v2 tools" carves a clear niche (Harness audit/compliance) with distinct triggers and minimal conflict risk, matching the score-5 anchor.	5 / 5
	Total	20 / 20 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: harness/harness-ai
Path: plugins/claude/skills/audit-report/SKILL.md
Commit: e554080

Reviewed: 21 hours 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.