a0-review-plugin

Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 highly actionable and clearly sequenced with strong validation checkpoints, making it an effective audit procedure. Its main weakness is progressive disclosure: it references a `checklists.md` file that is not present in the bundle while inlining much of the detailed checklist content that file is meant to hold.

Suggestions

Ship the referenced `checklists.md` in a `references/` bundle (or remove the reference) so progressive disclosure is not broken by a missing file.

Move the detailed per-phase checklists into `checklists.md` and keep SKILL.md as a concise overview pointing to it, rather than inlining the full checklists and also referencing the file.

Tighten the wordier checklist items (hooks.py lifecycle explanation, LICENSE rationale) into compact PASS/FAIL/WARN rules to lift conciseness toward fully lean.

Dimension	Reasoning	Score
Conciseness	The body is a tight checklist of concrete checks with a copy-paste Store Gating example and a reporting template; a few items are wordy (the hooks.py lifecycle explanation and the LICENSE rationale) but earn their place, fitting the score-4 anchor rather than the fully-lean score-5.	4 / 5
Actionability	Concrete, specific guidance throughout — regex `^[a-z0-9_]+$`, exact imports ("from agent import AgentContext, AgentContextType"), exact calls ("get_plugin_config(\"plugin-name\", agent=agent)", "toastFrontendError(msg, ...)"), a copy-paste Store Gate snippet, and a reporting template; per the instruction-skill note, absence of runnable code is not penalized when guidance is this actionable.	5 / 5
Workflow Clarity	Four phases are explicitly sequenced ("Run all 4 phases in order") with per-item PASS/FAIL/WARN validation checkpoints and a READY/NEEDS WORK/OPTIONAL feedback loop; this is a read-only audit so the destructive-cap does not apply, matching the score-5 checklist anchor.	5 / 5
Progressive Disclosure	Structure exists (4 phases, a References section) and `checklists.md` is signaled ("read `checklists.md` in this skill directory when needed"), but no `references/`/`scripts/`/`assets/` bundle exists and `checklists.md` is absent — a dead reference — while the detailed checklists the body says live in that file are largely inlined here, fitting the score-3 anchor (some structure, references not cleanly honored, content that should be separate is inline).	3 / 5
	Total	17 / 20 Passed

Description

92%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 strong: it states a concrete, comprehensive set of audit actions, gives explicit third-person trigger guidance with multiple natural synonyms, and occupies a clear niche with low conflict risk. The only minor gap is a few additional natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Quotes "Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index" — multiple specific concrete audit actions with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both "what" ("Full audit of Agent Zero plugins... Reviews manifest validity, directory structure, code patterns, security, and duplicate detection") and "when" ("Use when asked to review, audit, validate, or check an existing plugin before using or contributing it") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Quotes "Use when asked to review, audit, validate, or check an existing plugin" — four natural synonymous verbs users would say; good coverage, though a few natural variants (e.g. "inspect", "test plugin") are missing, fitting the score-4 anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ("Agent Zero plugins in usr/plugins/", "before using or contributing it") with distinct review/audit triggers and minimal overlap risk with other skills, matching the score-5 anchor.	5 / 5
	Total	19 / 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-review-plugin/SKILL.md
Commit: b22a144

Reviewed: 4 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.