CtrlK
BlogDocsLog inGet started
Tessl Logo

bootstrap

Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make you mine", or when a SOUL.md is missing. Also trigger for updates: "update my SOUL.md", "change my AI's personality", "tweak the soul".

69

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A tight, well-sequenced onboarding skill with strong workflow clarity and an explicit validation/feedback loop. Its main weakness is a missing bundle file: templates/SOUL.template.md is treated as a required input but is absent, which hurts both actionability and progressive disclosure.

Suggestions

Add the missing templates/SOUL.template.md to the bundle, or inline the output structure so the generation step is self-contained.

De-duplicate the 'behavioral rules not adjectives' guidance, which appears in both Ground Rules and Generation rules, to tighten conciseness.

Provide an inline fallback for the SOUL.md structure in SKILL.md so generation can proceed even if the template file is unavailable.

DimensionReasoningScore

Conciseness

Lean and well-structured with dense tables and no lecturing of concepts Claude already knows; held at 4 rather than 5 by minor redundancy between the phase table, the referenced conversation guide, and the behavioral-rules note that appears in both ground rules and generation rules.

4 / 5

Actionability

Highly concrete guidance — phase table, required-field extraction tracker, a 6-step generation checklist, an explicit setup_agent call signature, and crisp generation rules; capped at 4 because the output template (templates/SOUL.template.md) that the generation steps depend on is referenced but not present in the bundle.

4 / 5

Workflow Clarity

Clear 4-phase sequence with explicit checkpoints: a required-fields gate before generating, an iterate-until-confirmed feedback loop, and tool-error handling ('If setup_agent returns an error, report it... do not claim success'), matching the level-5 anchor for explicit validation and feedback loops.

5 / 5

Progressive Disclosure

Structure and signaling are good — an architecture diagram, a one-level-deep real reference (references/conversation-guide.md), and clear 'read both' instructions — but templates/SOUL.template.md is referenced in the diagram, the pre-response read list, and Generation step 1 yet does not exist in the bundle, a broken reference that is more than the 'minor organization gap' allowed at level 4.

3 / 5

Total

16

/

20

Passed

Description

90%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.

A strong description that clearly states its single concrete action and provides rich, natural trigger phrases covering both initial creation and updates. The only soft spot is specificity, since the skill performs one main action rather than a suite of concrete actions.

DimensionReasoningScore

Specificity

Names a concrete action ('Generate a personalized SOUL.md through a warm, adaptive onboarding conversation') but it is essentially a single action rather than the several specific actions the level-4 anchor requires, while 'warm, adaptive' adds mild fluff that keeps it short of level 4.

3 / 5

Completeness

Explicitly answers both 'what' (generate a personalized SOUL.md via onboarding conversation) and 'when' ('Trigger when...') with concrete trigger phrases, matching the level-5 anchor directly.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases with synonyms ('create/set up/initialize/bootstrap my agent', 'define who you are', 'make you mine') plus update variants ('update/change/tweak') and a missing-file condition — broad coverage of what users would naturally say.

5 / 5

Distinctiveness Conflict Risk

A clear niche (AI-partner identity onboarding via SOUL.md) with distinct, niche-specific triggers that are unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
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.