a0-development

Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API/WebUI.

Quality

79%

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/a0-development/SKILL.md

Quality

Content

93%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 a model of an overview-first skill: lean rules, a concrete need→reference navigation table backed by a real bundle, and a sequenced working flow with grounding and closeout verification. The only notable gap is that validation is delegated to DOX files without inline commands or an explicit error-recovery loop.

Dimension	Reasoning	Score
Conciseness	The ~55-line body is lean with every line earning its place — "Source and nearest DOX beat memory", "Do not assume ports. Discover WebUI host/port from startup output", "In Docker, framework checks belong to /opt/venv-a0" — with zero padding and no explanation of concepts Claude already knows. It matches anchor 5 (lean and efficient, assumes Claude's competence).	5 / 5
Actionability	Guidance is concrete and executable: a copy-paste JSON snippet for loading references with exact tool args, a need→file Reference Map naming exact paths, and precise rules citing real configuration ("--host", "--port", "WEB_UI_HOST", "WEB_UI_PORT", "/opt/venv-a0", "/opt/venv", "/a0/"). For an instruction/navigation skill this is fully actionable with no significant gaps, matching anchor 5.	5 / 5
Workflow Clarity	The "Working Flow" section lists 7 clearly sequenced steps from reading AGENTS.md through inspecting source before patching, with an explicit validation step ("verify frontmatter parsing, reference paths, and markdown sanity") and a Closeout that requires reporting verification. It falls short of anchor 5 because "Run targeted checks from the relevant DOX file" delegates how to validate without naming the commands, and there is no explicit fix-and-retry error-recovery loop.	4 / 5
Progressive Disclosure	The body is a clear overview with a well-signaled, one-level-deep reference system: the Reference Map table maps each need to an exact file in references/ (all 8 cited files exist in the bundle), and "Load only the references needed" enforces selective loading. This matches anchor 5 (clear overview, well-signaled one-level-deep references, easy navigation).	5 / 5
	Total	19 / 20 Passed

Description

57%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 distinctive thanks to its product-specific anchor and gives a reasonably clear 'what', but it reads as a terse scope list. It lacks any 'Use when...' trigger guidance and omits natural verb-phrase triggers like "extend" or "add a tool", leaving users to guess when it applies.

Suggestions

Append a 'Use when...' clause (e.g., "Use when the user wants to extend, customize, or operate Agent Zero: creating projects or chats, managing tasks, adding tools or extensions, or working with its API/WebUI").

Add natural trigger verb-phrases and synonyms users would actually say — "extend Agent Zero", "add a custom tool", "create a plugin", "change the prompt" — to broaden keyword coverage.

Replace generic verbs "develop or operate" with a couple of concrete actions per surface (e.g., "create and switch projects, start chats, run tasks, register tools, call HTTP/WebSocket endpoints").

Dimension	Reasoning	Score
Specificity	"Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API/WebUI" names the domain plus two actions ("Develop or operate") and enumerates scope areas, matching anchor 3 (domain and 1-2 concrete actions, not comprehensive). It is not a 4 because the enumerated items are nouns describing scope, not additional concrete actions, and "develop/operate" are themselves generic verbs.	3 / 5
Completeness	It clearly answers 'what' ("Develop or operate Agent Zero" across the listed surfaces) but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is concrete and multi-faceted, not vague.	3 / 5
Trigger Term Quality	The description contains relevant keywords ("Agent Zero", "projects", "chats", "tasks", "framework", "tools", "API/WebUI") but misses natural phrases and synonyms users would say, such as "extend", "customize", "add a tool", or "plugin" — matching anchor 3 (some relevant keywords, missing common variations). Not a 4 because it lacks the action-oriented verb phrases that would make the keyword coverage good rather than partial.	3 / 5
Distinctiveness Conflict Risk	Everything is anchored on the proper noun "Agent Zero", giving the skill a clear niche with distinct triggers and minimal risk of firing for unrelated skills — matching anchor 5. It is not a 4 because the product-specific framing leaves essentially no overlap with generic development or tooling skills.	5 / 5
	Total	14 / 20 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: agent0ai/agent-zero
Path: skills/a0-development/SKILL.md
Commit: e3051fb

Reviewed: 10 days 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.