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

72%

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

Fix and improve this skill with Tessl

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

Quality

Content

77%Weight 40%Scale 1-3

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

The body is strongly actionable with concrete commands, tool parameters, and validation checkpoints, but it is verbose and fails to leverage the bundled scripts — reinventing their logic inline rather than pointing to them. Tightening redundancy and referencing the scripts would materially improve it.

Suggestions

Reference the bundle scripts at the relevant sections (e.g. "cron setup: scripts/setup_cron.mjs", "report rendering: scripts/render_report.mjs", "email: scripts/send_smtp.mjs / sendmail_report.sh") instead of re-describing their logic inline.

Deduplicate the env-var listings — keep one canonical table and drop the repeated lists in Operational requirements and Installation flow.

Trim illustrative transcript/mockup examples and the "Advantages" marketing bullets, and move version/date-sensitive content into a dedicated versioned section.

Dimension	Reasoning	Score
Conciseness	The ~460-line body is mostly operational but padded with redundant env-var listings (frontmatter, Operational requirements, and Installation flow each re-list them), marketing-style "Advantages" bullets, illustrative transcript/mockup examples, and a long inline release-verification script — and version/date literals (0.1.9, 2026-02-16) sit outside any deprecated section, which the guidelines penalize.	2 / 3
Actionability	It provides copy-paste-ready bash (release verification with set -euo pipefail), concrete env exports, exact cron tool parameters (schedule.kind, payload.kind, sessionTarget), an exact suppression-config JSON, and literal audit commands, meeting the executable/examples anchor.	3 / 3
Workflow Clarity	Multi-step flows carry explicit checkpoints: release verification fails closed (exit 1 on mismatch, "Only install after verification succeeds"), a preflight review checklist before persisting the job, idempotency via cron.list before adding, and an email sendmail→SMTP→NOTE fallback — matching the explicit-validation/feedback-loop anchor.	3 / 3
Progressive Disclosure	The body has clear section organization but never references the 8 bundled scripts in scripts/ (setup_cron.mjs, render_report.mjs, send_smtp.mjs, load_suppression_config.mjs, runner.sh, etc.), instead re-describing cron setup, report rendering, suppression loading, and SMTP sending inline — content that should be offloaded to those files with signaled one-level-deep navigation.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 concretely names several actions and carves out a distinctive niche, but it omits an explicit "Use when..." trigger and relies on technical vocabulary over natural user phrasing. Adding a trigger clause would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when scheduling recurring security audits for OpenClaw agents or when the user asks for daily audit reports via DM/email."

Swap jargon ("DM delivery", "recurring cron job") for natural phrasing users would actually say, and add common variations like "security report" or "audit report".

Lead with the user-facing outcome (daily security audit reports delivered to you) before the cron/DM mechanics.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Runs deep audits", "creates or updates a recurring cron job", and "sends formatted reports to configured recipients" — matching the multi-action anchor rather than the single-domain score-2 anchor.	3 / 3
Completeness	The "what" is clearly answered, but there is no "Use when..." clause or equivalent explicit trigger guidance, which the guidelines cap at 2; it is not a 1 because the capability is concretely stated.	2 / 3
Trigger Term Quality	It contains some natural terms ("daily security audits", "deep audits") but leans technical ("OpenClaw agents", "recurring cron job", "DM delivery") and misses common variations like "security report" or "vulnerability scan", so it stops short of broad natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	The OpenClaw + daily-audit + cron + DM/email niche is narrow and unlikely to trigger for the wrong skill, satisfying the clear-niche/low-conflict anchor despite the missing explicit trigger.	3 / 3
	Total	10 / 12 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: prompt-security/clawsec
Path: skills/openclaw-audit-watchdog/SKILL.md
Commit: c6194eb

Reviewed: 14 days 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.