CtrlK
BlogDocsLog inGet started
Tessl Logo

a0-create-agent

Create Agent Zero profiles with agent.yaml, prompt overrides, tools and extensions.

58

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/a0-create-agent/SKILL.md
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.

The skill body is highly actionable with a clearly sequenced workflow, validation checkpoints, and troubleshooting guidance. Its weaknesses are redundancy in the prompt-override tables and the absence of any progressive-disclosure bundle to keep the main file lean.

Suggestions

Merge the duplicated "High-value inherited prompt levers" and "Secondary overrides" tables in Step 5 into a single table.

Move the full AgentProfileBlueprint schema example into a references/ file (e.g. references/blueprint-schema.md), keeping only the rules and a minimal example inline.

Trim the blueprint JSON example so it does not restate the agent.yaml contents already shown in Steps 2-3.

DimensionReasoningScore

Conciseness

The body is dense with framework-specific, non-obvious information, but Step 5 presents two overlapping tables covering the same prompt-override levers (agent.system.main.role.md, communication.md, environment.md each appear twice), and the full blueprint JSON duplicates material from Steps 2-4 — "mostly efficient but could be tightened".

3 / 5

Actionability

Fully executable guidance throughout: a complete blueprint JSON schema with strict output rules, a concrete agent.yaml example, copy-paste-ready Python tool and extension classes, directory trees, and exact file paths — covering the common cases end to end.

5 / 5

Workflow Clarity

Steps 0-8 are explicitly sequenced with a confirmation checkpoint before writing files, a dedicated test step, and an error-recovery feedback loop ("If the profile does not appear, check..."), plus a quick checklist; the skill is not destructive or batch, so no cap applies.

5 / 5

Progressive Disclosure

Sections are well-organized, but there is no bundle structure at all — the long blueprint schema example and the multi-row reference tables are inlined in a ~420-line body where a references/ file would fit, matching anchor 3 ("some structure but content that should be separate is inline").

3 / 5

Total

16

/

20

Passed

Description

58%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 specific and appropriately scoped to the Agent Zero niche, listing concrete artifacts rather than vague claims. Its main weakness is the missing "Use when..." clause and the absence of natural trigger variations beyond "create agent".

Suggestions

Append an explicit trigger clause such as "Use when the user asks to create, add, or configure an Agent Zero agent profile or subordinate agent".

Include natural trigger variations ("new agent", "add agent profile", "subagent") in the description to broaden keyword coverage.

Optionally mention the model-preset config surface so the capability list is more comprehensive.

DimensionReasoningScore

Specificity

Names the domain plus several concrete artifacts — "agent.yaml, prompt overrides, tools and extensions" — giving multiple specific actions with only minor gaps; it falls short of anchor 5 because it omits config/preset and testing surfaces, and exceeds anchor 3 because it lists more than 1-2 actions.

4 / 5

Completeness

The description clearly answers "what" (create profiles with agent.yaml, prompt overrides, tools, extensions) but contains no "Use when..." or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Phrases like "Create Agent Zero profiles" include natural keywords, but common user variations ("new agent", "add agent", "subagent", "subordinate") are absent from the description itself — matching anchor 3 rather than 4, which requires only a few missing natural terms.

3 / 5

Distinctiveness Conflict Risk

"Agent Zero profiles" establishes a clear niche with low conflict risk; the generic leading phrase "Create agent" could overlap with non-Agent-Zero agent-creation skills, keeping it below anchor 5 but above anchor 3.

4 / 5

Total

14

/

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.

Validation — 15 / 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
agent0ai/agent-zero
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.