soul-guardian

Drift detection + baseline integrity guard for agent workspace files with automatic alerting support

Quality

57%

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/soul-guardian/SKILL.md

Quality

Content

65%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 highly actionable with copy-paste commands and clear quick-start steps, but it carries a large inline verification script and lacks a validation checkpoint around the destructive auto-restore path. Splitting the verification block into a reference file and adding a restore validation step would improve both conciseness and workflow clarity.

Suggestions

Move the Release Artifact Verification bash block into a separate references file (e.g. references/verify-release.md) and link to it from SKILL.md to reduce inline token weight.

Add an explicit validation/checkpoint step before auto-restore (e.g. confirm drift via check, review the saved diff, then restore) to satisfy the destructive-operation feedback-loop requirement.

Replace the hardcoded VERSION="0.0.9" in the verification script with a parameterized note or move version-sensitive content to a release-notes section.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the large inline Release Artifact Verification script (~70 lines, with a hardcoded version 0.0.9) is heavy for an overview and could be tightened or moved out, so it is not fully lean.	2 / 3
Actionability	Commands are concrete, executable, and copy-paste ready (init, enable-monitoring, check, watch, approve, status, verify-audit, demo), and the verification block is a complete runnable bash script.	3 / 3
Workflow Clarity	The Quick Start is sequenced and the verification block has checksum validation checkpoints, but the destructive auto-restore workflow lacks an explicit validate-before-restore feedback loop, which caps workflow clarity at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	Bundle scripts exist and are referenced (soul_guardian.py, demo.sh) and sections are well organized, but the sizable release-verification script is inline in SKILL.md rather than split into a reference file, leaving structure that could be improved.	2 / 3
	Total	9 / 12 Passed

Description

50%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 is a compact what-only statement with a clear security niche, but it omits any 'when to use it' trigger guidance and leans on jargon over natural user terms. Adding an explicit 'Use when...' clause with concrete triggers would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when an agent's SOUL.md, AGENTS.md, or identity files have been modified unexpectedly, or when you need baseline drift detection and auto-restoration.'

Replace abstract phrasing like 'baseline integrity guard' with concrete actions ('detects sha256 drift, auto-restores protected files, alerts the user').

Add common user-facing keywords such as 'file integrity', 'tamper detection', 'unauthorized changes', and 'restore baseline'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('agent workspace files') and a few actions ('drift detection', 'baseline integrity guard', 'automatic alerting'), but 'baseline integrity guard' is abstract rather than a concrete enumerated action list, so it falls short of the multiple-specific-actions anchor.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like 'drift detection' and 'baseline integrity' are relevant but technical/jargon-leaning and miss common user phrasings; there are no natural trigger variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	The 'agent workspace files' niche is somewhat specific, but without explicit triggers the description could still overlap with general file-integrity or backup skills.	2 / 3
	Total	8 / 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/soul-guardian/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.