CtrlK
BlogDocsLog inGet started
Tessl Logo

create-agent

Creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use when the user wants to configure an agent, create agent.yaml, write SOUL.md, set up agent directory structure, or customize agent settings.

80

Quality

100%

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

100%

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

The body is a concise, highly actionable reference with executable code throughout and a Quick Start that sequences the setup with an explicit validation step. Organization is clean and self-contained with no problematic reference nesting, though the Quick Start lacks an explicit error-recovery loop.

Suggestions

Add a brief feedback loop to the Quick Start validation step (e.g., 'If validation fails, review the error, fix the offending field, and re-run opengap validate') to fully match the score-3 workflow anchor.

Provide at least one minimal filled SOUL.md example alongside the section-name template so the 'Writing a Good SOUL.md' guidance is as copy-paste-ready as the agent.yaml reference.

Consider noting the spec_version source/version authority, since '0.1.0' is a time-sensitive value that could benefit from a pointer to where the current spec version is defined.

DimensionReasoningScore

Conciseness

The body is lean and reference-oriented — mostly executable YAML/markdown blocks with terse inline comments and brief section templates — and avoids explaining concepts Claude already knows, fitting the score-3 'every token earns its place' anchor rather than the padded score-2 example.

3 / 3

Actionability

It provides complete, copy-paste-ready blocks for agent.yaml, model config, skills/tools, sub-agents, tool input_schema, and knowledge/index.yaml plus concrete commands like 'mkdir -p my-agent/skills' and 'opengap validate -d ./my-agent', matching the score-3 fully-executable anchor.

3 / 3

Workflow Clarity

Quick Start gives a clear 5-step sequence with an explicit validation checkpoint ('Validate: opengap validate -d ./my-agent'); because scaffolding a directory is non-destructive, the absence of a fix-and-retry feedback loop does not drop it to the score-2 'checkpoints missing or implicit' anchor.

3 / 3

Progressive Disclosure

No bundle files exist and the body contains no nested/deep references; content is organized into well-labeled sections (Quick Start, agent.yaml Reference, SOUL.md, RULES.md, Adding Skills/Tools/Knowledge) and is appropriately self-contained for a config reference, so it clears the score-3 bar rather than the monolithic score-1 case.

3 / 3

Total

12

/

12

Passed

Description

100%

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, third-person, and pairs concrete capabilities with an explicit 'Use when' trigger clause covering natural user phrasings. It closely matches the rubric's good-overall examples and carries no over-claims or padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge' — matching the score-3 anchor of several specific concrete actions rather than a single named action.

3 / 3

Completeness

It explicitly answers both what (the creating/configuring/writing actions) and when ('Use when the user wants to configure an agent, create agent.yaml, write SOUL.md...'), matching the score-3 anchor with an explicit trigger clause; it is not the score-2 case where 'when' is only implied.

3 / 3

Trigger Term Quality

The 'Use when' clause surfaces natural phrasings a user would say — 'configure an agent, create agent.yaml, write SOUL.md, set up agent directory structure, or customize agent settings' — giving good coverage rather than the partial set of the score-2 anchor.

3 / 3

Distinctiveness Conflict Risk

It occupies a clear niche — agent.yaml/SOUL.md/directory scaffolding — with distinct triggers unlikely to fire for unrelated skills, so it is above the score-2 'could still overlap' anchor.

3 / 3

Total

12

/

12

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
open-gitagent/opengap
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.