CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openclaw-audit-watchdog

Automated daily security audits for OpenClaw agents with DM delivery and optional email reporting. Runs deep audits, creates or updates a recurring cron job, and sends formatted reports to configured recipients.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/openclaw-audit-watchdog/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 body is highly concrete and operational — executable verification code, exact cron parameters, idempotency checks, and a realistic report sample — but it is a 490-line monolith that ignores its own bundle: none of the 9 shipped scripts are referenced, and the suppression material is stated twice. Tightening duplication and wiring the scripts into the payload instructions would lift both conciseness and progressive disclosure.

Suggestions

Reference the shipped scripts by path (e.g. scripts/setup_cron.mjs, scripts/runner.sh, scripts/render_report.mjs) instead of re-describing their behavior in prose, and state where they are installed so the payload instructions are executable as written.

Deduplicate the suppression documentation: Example 7 and the 'Suppression / Allowlist' section repeat the same config JSON and matching semantics — keep one canonical section and trim the other to a pointer.

Trim the promotional 'Installation Options' advantages bullets and move the long release-verification script to a reference file, keeping the body as an overview.

DimensionReasoningScore

Conciseness

Mostly dense operational content, but the suppression config JSON and matching rules are duplicated (Example 7 vs. the 'Suppression / Allowlist' section), the 'Installation Options' advantages bullets are promotional padding, and the hardcoded VERSION="0.1.9" plus example dates are time-sensitive values outside any 'old patterns' section. Not lower because no space is spent explaining concepts Claude already knows.

3 / 5

Actionability

The release-verification bash script is complete and executable, and env vars, exact cron parameters (schedule.expr="0 23 * * *", sessionTarget="isolated"), and a sample report format give concrete guidance. Not 5 because the payload runner's behavior is described only in prose while the 9 shipped scripts in scripts/ are never named or wired into the instructions, leaving an execution gap.

4 / 5

Workflow Clarity

The sequence (verify release → configure env → preflight review → idempotency check via cron.list → create/update job → deliver with email fallback error handling) has most checkpoints present. Not 5 because there is no validate→fix→retry loop around cron creation and section ordering is loose (installation options and verification precede the Goal).

4 / 5

Progressive Disclosure

Scored against the actual bundle: the skill ships 9 script files (runner.sh, setup_cron.mjs, render_report.mjs, etc.) but the body references none by path; the verification script, suppression details, and 7 usage examples are all inlined monolithically. Content that clearly belongs in separate files — or should at least be signaled as shipped scripts — is inlined with no navigation to it.

2 / 5

Total

13

/

20

Passed

Description

58%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 clearly and concretely states what the skill does — running audits, creating/updating a recurring cron job, and delivering formatted reports — but it omits any 'when to use' trigger guidance, which limits discoverability and caps completeness. Keyword coverage is decent but lacks common synonyms users would naturally say.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for scheduled, recurring, or automated security audits or daily security reports for OpenClaw agents.'

Include natural trigger synonyms such as 'security scan', 'vulnerability scan', 'scheduled audit', or 'security monitoring' so the description matches how users actually phrase the need.

Briefly mention the report content (summary of critical/warn/info findings) so the 'what' covers what recipients actually receive.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Runs deep audits, creates or updates a recurring cron job, and sends formatted reports' with DM and optional email delivery — but coverage has minor gaps (finding summarization and the standard-vs-deep audit split are not named).

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps this dimension at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains relevant keywords ('security audits', 'daily', 'cron job', 'DM', 'email reporting') but misses common natural variations and synonyms a user would say, such as 'scan', 'vulnerability', 'scheduled', or 'monitoring'.

3 / 5

Distinctiveness Conflict Risk

'Automated daily security audits for OpenClaw agents' carves a distinct niche with a specific harness qualifier, leaving only minor overlap risk with generic security-audit or scheduling skills.

4 / 5

Total

14

/

20

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.

Validation — 13 / 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

prompt-security/clawsec

Path

skills/openclaw-audit-watchdog/SKILL.md

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.