CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/audit-trail-test-author

Build-an-X for audit-log tests across compliance frameworks - required-events catalog (auth events / privilege change / data access / admin action / config change / export / impersonation); structured-log-format assertions per OWASP A09:2021; tamper-evident chain (hash-chain + signed-batch patterns) for HIPAA §164.312(b) + PCI Req 10 + SOC 2 CC7.3; immutability + retention per framework; query-replay tests for forensic reconstruction. Use when authoring audit log tests for any compliance framework (HIPAA / PCI / SOC 2 / GDPR / etc.).

73

Quality

92%

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

Overview
Quality
Evals
Security
Files

Quality

Content

80%

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

A highly actionable, code-dense audit-log test recipe with a clear sequenced workflow. Its weaknesses are the absence of an explicit test-run/verify feedback loop and a monolithic single-file structure with no progressive disclosure to reference files.

Suggestions

Add an explicit validation feedback loop for the test suite — e.g., 'Run the full audit-log test suite; on failure, diff the emitted event against the expected schema/hash, fix the logging code, and re-run' — to satisfy the checkpoint expectation for DB-backed workflows and raise workflow_clarity.

Split detailed per-framework material (retention tables, full hash-chain/signed-batch recipes) into one-level-deep reference files such as references/retention-by-framework.md and link them inline at the relevant steps to improve progressive_disclosure.

Signal references inline at the point of use (e.g., 'See OWASP A09:2021' inside Step 2) rather than only listing them in the trailing References section, so navigation is clear within the body.

DimensionReasoningScore

Conciseness

The body is code- and table-forward with no preamble explaining concepts Claude already knows (e.g., what HIPAA or audit logging is); though long, the 8-step coverage means each section earns its place rather than padding the context.

3 / 3

Actionability

Each step ships copy-paste-ready, executable Python test functions with concrete assertions (e.g., test_audit_log_hash_chain_integrity, test_pan_not_in_audit_logs), not pseudocode or vague direction.

3 / 3

Workflow Clarity

The 8-step sequence and Step 8 end-to-end checklist are clear, but there is no explicit run→verify→fix feedback loop; because audit logs are database-backed, the rubric's guidance caps such workflows at 2 when feedback loops are absent.

2 / 3

Progressive Disclosure

Sections are well-organized with headers, but everything is inline in one ~277-line file with no bundle files; references (external URLs and sibling skills) appear only in a trailing section and are not signaled inline at the point of use, and the under-50-line shortcut does not apply.

2 / 3

Total

10

/

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, specific description that names concrete actions, includes natural framework trigger terms, and provides an explicit 'Use when' clause. It is distinctive and unlikely to conflict with adjacent skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'required-events catalog (auth events / privilege change / data access / admin action / config change / export / impersonation)', 'structured-log-format assertions', 'tamper-evident chain (hash-chain + signed-batch patterns)', 'immutability + retention', 'query-replay tests' — far beyond naming a domain.

3 / 3

Completeness

Answers both what (the enumerated test capabilities) and when, with an explicit trigger: 'Use when authoring audit log tests for any compliance framework (HIPAA / PCI / SOC 2 / GDPR / etc.).'

3 / 3

Trigger Term Quality

Natural terms a user would say are well covered: 'audit log tests', 'compliance framework', and the explicit framework list 'HIPAA / PCI / SOC 2 / GDPR' that users actually invoke; the only non-natural token is the authoring jargon 'Build-an-X'.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (compliance-grade audit-log test authoring) and explicitly differentiates from generic logging and from sibling compliance skills, making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents