CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

74

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A dense, actionable, token-efficient skill body that assumes Claude's competence and gives concrete framework specifics. The one gap is workflow clarity: it touches batch/destructive operations without an explicit validation checkpoint or feedback loop.

Suggestions

Add an explicit verify step for bulk export (export-audit-events) — e.g., check the returned row count or re-run with maxRows before a compliance pull — so the destructive/batch path has a feedback loop.

For destructive audited actions like the 'Delete a recording' example, show a verify-after pattern (confirm the event landed via get-audit-event) to make the capture → verify loop explicit.

Consider a short numbered lifecycle sequence (action fires → framework captures at defineAction seam → event scoped to actor/owner → queryable via list-audit-events) to surface the implicit flow as an explicit, checkable process.

DimensionReasoningScore

Conciseness

Lean and framework-specific throughout — it jumps straight to defineAction seams, audit config keys, named actions, and env vars without explaining generic concepts Claude already knows; the observability/tracking contrast is domain disambiguation, not padding.

3 / 3

Actionability

Provides an executable TS defineAction example, concrete config keys (audit: { onRead: true }, { enabled: false }, { recordInputs: false }), named actions with their filter parameters, and exact env vars — copy-paste ready guidance.

3 / 3

Workflow Clarity

Sections are well-organized (Rule, Declare target, Defaults, Reading the log, Never) with a guardrail checklist, but there is no explicit validation/feedback-loop checkpoint, and it discusses batch export and destructive delete operations without a reader-side verify step — which caps clarity at 2 per the rubric guideline.

2 / 3

Progressive Disclosure

Self-contained with no nested or external references, organized into clearly signaled sections and a 'Never' list; nothing here would benefit from being split into a separate file, so the single-file structure is appropriate.

3 / 3

Total

11

/

12

Passed

Description

100%

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 description: third-person, concrete, with explicit 'Use when…' trigger guidance and a well-delineated niche that distinguishes it from adjacent concepts. It satisfies every dimension at the top anchor.

DimensionReasoningScore

Specificity

Names concrete capabilities and use-cases — 'adding an activity feed or change history, declaring what a mutating action targets, auditing sensitive reads' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' ('Durable, access-scoped, append-only record of who changed what app data, when…') and 'when' via a 'Use when…' clause with concrete triggers.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would actually say — 'activity feed', 'change history', 'who edited this', 'what did the agent change', 'auditing sensitive reads' — with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (append-only audit log scoped to app-data mutations) with distinct triggers and an explicit contrast against observability/tracking, making it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.