soul-audit

6-phase interactive interview that generates the agent's identity (SOUL.md), user profile (USER.md), access control (ACCESS_POLICY.md), and operational cadence (HEARTBEAT.md). Re-runnable anytime to update any section.

Quality

66%

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-audit/SKILL.md

Quality

Content

65%

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

The content is concise and clearly sequenced across its six phases, but it stops short of being fully executable: it references a templates/ bundle that is not present and includes no validation step before declaring files generated. Supplying the template scaffolds and a verification checkpoint would move actionability and workflow clarity up.

Suggestions

Provide the actual templates/ directory with SOUL.md.template, USER.md.template, ACCESS_POLICY.md.template, and HEARTBEAT.md.template so the default-mode install and generation steps are concrete rather than referenced-but-missing.

Add an explicit validation checkpoint after generation — e.g. verify each of the four files exists and is non-empty before reporting 'Soul audit complete'.

Show a minimal concrete example of one generated section (e.g. a populated SOUL.md identity block) so the generation step is unambiguous instead of described.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized — each phase gives only the exact interview prompt and the file it produces, without explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	It supplies concrete interview prompts and named outputs per phase, but references template files (e.g. templates/SOUL.md.template) whose content is never shown and provides no executable code or commands, leaving the generation step abstract.	2 / 3
Workflow Clarity	The six phases are clearly sequenced with explicit independence and re-run semantics, but this mutating skill writes four files with no validation/verification checkpoint that outputs were generated correctly or that referenced templates exist, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	References to templates/ are one level deep but the bundle directories (templates/, references/, scripts/, assets/) are absent, so the skill leans on files that do not exist; scored against the actual (empty) bundle structure it has structure intent but no realized references.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and distinctive about its four-file output and re-run semantics, but it omits an explicit 'Use when' trigger clause and pushes natural keywords into a separate triggers field, capping completeness and trigger-term quality. Adding a sentence naming the natural situations in which to invoke it would lift both dimensions.

Suggestions

Append an explicit 'Use when...' clause to the description, e.g. 'Use when the user wants to set up or re-run the agent's identity, profile, or access configuration.'

Weave natural trigger phrasing the user would actually say (e.g. 'customize my agent', 'set up who the agent is') into the description itself rather than relying solely on the triggers field.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and named outputs — 'generates the agent's identity (SOUL.md), user profile (USER.md), access control (ACCESS_POLICY.md), and operational cadence (HEARTBEAT.md)' — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' but has no explicit 'Use when...' or equivalent trigger guidance in the description, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	The description text itself contains no natural-language trigger phrases; the keywords ('soul audit', 'customize agent', etc.) live only in the separate triggers field rather than flowing through the description users would read.	2 / 3
Distinctiveness Conflict Risk	The agent-identity-setup niche with distinct SOUL/USER/ACCESS_POLICY/HEARTBEAT outputs is clearly distinguishable and unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: garrytan/gbrain
Path: skills/soul-audit/SKILL.md
Commit: 3fafb69

Reviewed: about 20 hours 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.