CtrlK
BlogDocsLog inGet started
Tessl Logo

soul-audit

Re-run or deepen the agent's identity interview. Drives the SHARED bootstrap answer bank (state/interview.json) via `gbrain bootstrap interview --set/--show/--confirm`, then re-renders the identity files with `gbrain bootstrap render --only <FILE> --force`. One answer store, two surfaces: first-boot bootstrap and this re-run skill write the same bank, so an updated answer flows into SOUL.md, USER.md, ACCESS_POLICY.md, and HEARTBEAT.md without hand-editing rendered files. Every answer is the user's own words — never invented.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

92%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 actionable and well-structured, with concrete commands, a clearly sequenced multi-phase workflow, and an explicit validation gate for the mutating render step; only minor conciseness trimming is warranted.

DimensionReasoningScore

Conciseness

Mostly efficient with copy-paste commands and tight phase lists, though the intro paragraph restates the description and includes some rationale ('That keeps one source of truth...') that could be trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands (the command loop block) plus exact keys and render targets per phase, covering the common cases concretely.

5 / 5

Workflow Clarity

Clear phased sequence with an explicit validation checkpoint (the read-back ritual: --show, mirror to user, --confirm <hash>) and a structural gate that fails by design, plus backup-before-overwrite safety for a mutating operation.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is well-organized into clear sections (Contract, command loop, Phases, Output Format, Anti-Patterns) with no nested or buried references.

5 / 5

Total

19

/

20

Passed

Description

67%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 is highly specific and distinct, naming exact commands and target files, but it lacks an explicit 'Use when...' trigger clause and relies on technical jargon over the natural phrases a user would actually say.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user wants to customize their agent, change its personality, or re-run the identity interview after bootstrap').

Surface a few user-natural keywords ('customize agent', 'personality', 'who am I') in the description rather than only the technical terms ('bootstrap', 'render', 'answer bank').

Trim the explanatory rationale ('One answer store, two surfaces...') to keep the description lean while preserving the concrete actions.

DimensionReasoningScore

Specificity

Names multiple concrete actions with exact commands ('gbrain bootstrap interview --set/--show/--confirm', 'gbrain bootstrap render --only <FILE> --force') and the specific files affected (SOUL.md, USER.md, ACCESS_POLICY.md, HEARTBEAT.md), giving comprehensive coverage.

5 / 5

Completeness

The 'what' is clearly and thoroughly stated, but there is no explicit 'Use when...' clause; the 'when' is only weakly implied by 'Re-run or deepen', which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Contains some relevant natural terms ('agent's identity', 'interview') but leans on technical jargon ('bootstrap answer bank', 'render', 'gbrain') and omits the natural phrases users would say ('customize my agent', 'change personality', 'who am I').

3 / 5

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (gbrain identity re-audit via a shared answer bank) with tool-specific triggers, making conflict with other skills minimal.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
garrytan/gbrain
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.