a0-manage-plugin

Manage Agent Zero plugins lifecycle: browse the Plugin Hub, scan for security, install from Git/ZIP/Plugin Hub, update, uninstall, enable, disable, debug, and troubleshoot. Use when asked to install, update, uninstall, remove, scan, find, search, enable, disable, debug, or troubleshoot a plugin.

Quality

92%

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%

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

Highly actionable content with executable code, clear routing, and validation checkpoints for destructive operations. Its main weakness is conciseness and progressive disclosure: a long single-file body with some boilerplate and framework-mechanic prose that could be split into referenced files.

Suggestions

Move the repeated API-authentication setup and the scan/install HTTP examples into a referenced file (e.g. references/api.md) and summarize the auth bootstrap once, reducing repetition across sections.

Tighten the inline prose — the pre-install scan dialog quotes and 'How installed state works' paragraph restate framework behavior derivable from the code; keep only the decision-relevant parts.

Consider extracting the security-scan verdict/interpretation table into a reference so the main body stays a lean overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and action-oriented, but inline prose like the pre-install scan dialog quotes, the 'How installed state works' explanation, and repeated authentication boilerplate could be tightened; it explains some framework mechanics Claude could infer from the code.	2 / 3
Actionability	Provides complete, copy-paste-ready Python and bash snippets with real endpoints, headers, and parameter payloads across install, scan, update, uninstall, and activation — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Clear action-routing table sequences the user to the right section, and risky operations have explicit validation checkpoints: pre-install scan offer, verdict-driven install gating, explicit uninstall confirmation, and scan-timeout error handling.	3 / 3
Progressive Disclosure	Well-organized into labeled sections with a routing table, but it is a single monolithic SKILL.md (~360 lines) with no bundle files and only one-level internal references; large API/auth blocks that could live in a reference file are inlined.	2 / 3
	Total	10 / 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.

A strong, third-person description that lists concrete actions and pairs them with an explicit, natural-language 'Use when' trigger clause. It cleanly answers both what the skill does and when to invoke it within a distinctive niche.

Dimension	Reasoning	Score
Specificity	Names many concrete actions — 'browse the Plugin Hub, scan for security, install from Git/ZIP/Plugin Hub, update, uninstall, enable, disable, debug, and troubleshoot' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both 'what' (the full lifecycle action list) and 'when' via a clear 'Use when asked to...' trigger clause, the strongest completeness anchor.	3 / 3
Trigger Term Quality	The 'Use when...' clause repeats natural user phrasings ('install, update, uninstall, remove, scan, find, search, enable, disable, debug, or troubleshoot a plugin'), covering common variations users would actually say.	3 / 3
Distinctiveness Conflict Risk	The narrow Agent Zero plugin-management niche with distinct plugin-lifecycle triggers makes it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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-manage-plugin/SKILL.md
Commit: 391fab9

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.