a0-create-plugin

Build, improve, review or publish Agent Zero plugins; local or community, with focused references.

Quality

77%

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-create-plugin/SKILL.md

Quality

Content

86%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.

An exemplary lean instruction-only skill body: dense with domain contracts and concrete paths, a clear verification-including workflow, and a clean one-level-deep reference structure. The only real gap is that verification and troubleshooting steps name what to check but rarely give the concrete command or error signature to execute.

Suggestions

Make the verification step concrete — name the actual command or check (e.g. the management API call or framework Python invocation) instead of 'Verify the real target runtime, not just the checkout'.

Add one or two concrete error examples or signals to the troubleshooting boundaries so 'inspect the relevant server/browser error' is executable rather than directional.

State the expected feedback loop explicitly (verify → fix → re-verify, and when to stop) in the Working Flow rather than leaving it implied across sections.

Dimension	Reasoning	Score
Conciseness	The ~50-line body is lean and assumes competence: no explanations of what plugins or Python are, every sentence is directive contract or path information, and detail is pushed to references. Nothing reads as padding, matching the 5-anchor 'every token earns its place' rather than the 4-anchor's 'minor instances of over-explanation that could be trimmed'.	5 / 5
Actionability	Concrete paths (`/a0/usr/plugins/<name>/`, plugin-root `hooks.py`, `plugin.yaml`), exact lifecycle function names with rerun/ownership semantics, and a copy-paste-ready tool invocation ("use `skills_tool` with `action: "read_file"`, `skill_name: "a0-create-plugin"`" plus the reference path). Per the instruction-only scoring note, absent code is not penalized; the gap versus a 5 is that some guidance stays high-level — e.g. 'Inspect the relevant server/browser error before editing' and the troubleshooting boundary list give no concrete commands or error signatures.	4 / 5
Workflow Clarity	The Working Flow is a clear 5-step sequence with an explicit verification step ("Verify the real target runtime... Read `references/review.md` before declaring the work complete; report actual checks and remaining limitations") and the troubleshooting section adds error-recovery ordering. Not a 5 because the validate→fix→retry loop is implicit rather than an explicit checkpointed loop with concrete verification commands. The destructive-operation cap does not apply: lifecycle operations include uninstall cleanup and the skill does include verification and rerun-safety guidance.	4 / 5
Progressive Disclosure	The body is a pure overview with a work-type → reference mapping table; all five referenced files (implementation, channel-commands, webui, review, contribute) exist one level deep in `references/`, nothing that belongs in a reference is inlined, and navigation is well signaled via the explicit skills_tool read instruction. Matches the 5-anchor's clear overview with well-signaled one-level-deep references; the only blemish (references/AGENTS.md unreferenced) is a source file, not skill content.	5 / 5
	Total	18 / 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.

A concise, domain-specific description with a clear 'what', but it lacks an explicit 'when to use' clause and omits natural trigger terms (debug, troubleshoot, fix, contribute) that its own frontmatter triggers show users need. It is distinct within the Agent Zero plugin niche but has minor overlap with the sibling a0-manage-plugin skill around publishing/contribution.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to create, improve, debug, review, or publish an Agent Zero plugin."

Include the missing natural trigger verbs — debug, troubleshoot, fix, contribute/submit — since they are common user phrasings covered by the frontmatter triggers but absent from the description.

Add a one-line disambiguator against the sibling skill, e.g. "For finding, installing, or updating existing plugins, use a0-manage-plugin instead."

Dimension	Reasoning	Score
Specificity	The description lists four concrete actions — "Build, improve, review or publish Agent Zero plugins" — with a distribution distinction ("local or community"). It matches the anchor listing several specific actions with minor gaps rather than the 5-anchor, since it doesn't say what building/reviewing a plugin concretely involves.	4 / 5
Completeness	The 'what' is clear (build, improve, review, publish plugins), but there is no 'Use when...' clause or equivalent explicit trigger guidance; the rubric guideline explicitly caps completeness at 3 in that case. Not lower because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	Natural phrases like "build", "review", "publish", "plugin" are present, but common variations users would say are missing — notably debug/troubleshoot/fix/contribute, which the skill's own frontmatter triggers cover extensively. This fits 'some relevant keywords but missing common variations or synonyms' better than the 4-anchor's 'a few natural terms missing', since entire usage categories are absent.	3 / 5
Distinctiveness Conflict Risk	"Agent Zero plugins" is a clear niche with distinct verbs, so minimal conflict with unrelated skills. However, "publish" and the local/community framing overlap slightly with the companion skill a0-manage-plugin (finding/installing/updating plugins) that the body itself references — minor overlap with a closely related skill, matching the 4-anchor.	4 / 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-create-plugin/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.