audit-log

Durable, access-scoped, append-only record of who changed what app data, when, and whether it was the agent or a human. Use when adding an activity feed or change history, declaring what a mutating action targets, auditing sensitive reads, or answering "what did the agent change / who edited this".

Quality

91%

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

83%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 tight, highly actionable reference that shows concrete config and the available query/export actions with minimal padding. Its main gap is the absence of explicit validation checkpoints for the batch export path, which caps workflow clarity.

Suggestions

Add a short numbered sequence for the batch export path (e.g. filter -> export-audit-events -> verify row count / spot-check format) with an explicit verification step before relying on the output for compliance.

For export-audit-events, note how to confirm the export itself was audited via onRead and how to validate maxRows truncation so callers detect incomplete pulls.

Consider extracting the three action signatures and their filter parameters into a one-level-deep reference file so the SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: no padding of basic concepts, every section (Rule, defaults, reading the log, Never) earns its place, and the brief distinction from observability/tracking is useful context rather than fluff.	5 / 5
Actionability	Provides a complete, copy-paste-ready defineAction example with audit.target/ownerEmail/visibility/summary, names the exact config keys (onRead, enabled, recordInputs), the three available actions with their filters, and the relevant env vars.	5 / 5
Workflow Clarity	Guidance is well-organized and the 'Never' guardrails act as a partial checklist, but there are no explicit numbered steps or validation/verification checkpoints for the batch export-audit-events operation, capping this dimension at 3 per the destructive/batch rule.	3 / 5
Progressive Disclosure	Well-organized single-file skill with clear section headers and no nested references; not a 5 because nothing is split into one-level-deep reference files, but the inline content is appropriately sized and easy to navigate.	4 / 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.

A strong, third-person description that pairs a precise 'what' with an explicit, multi-trigger 'Use when...' clause and natural user phrasing. It is concise, concrete, and unlikely to conflict with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities and use cases — recording who/what/when and agent-vs-human attribution, adding an activity feed, declaring a mutating action's target, auditing sensitive reads, and answering 'what did the agent change / who edited this' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both 'what' (durable, access-scoped, append-only record of who changed what app data, when, and whether agent or human) and 'when' via a concrete 'Use when...' clause enumerating trigger scenarios.	5 / 5
Trigger Term Quality	Covers natural phrases users actually say — 'activity feed', 'change history', 'auditing sensitive reads', 'what did the agent change', 'who edited this' — including synonyms rather than only technical jargon.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (audit/change-history logging) with distinct triggers like 'who edited this' that are unlikely to fire for unrelated skills; the append-only, access-scoped framing further narrows it.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/audit-log/SKILL.md
Commit: b0df876

Reviewed: 19 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.