CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A well-structured, highly actionable skill body with strong validation checkpoints around destructive operations and clear navigation. The main improvement room is tightening some repeated session-setup prose and pulling the API reference detail into a bundled file.

Suggestions

Factor the repeated CSRF/session-authentication setup into a single anchored snippet and reference it once instead of restating '(after authentication setup)' across multiple code blocks.

Move the API authentication and endpoint detail into a bundled reference file (e.g. references/api.md) and keep SKILL.md focused on the routing table and per-action recipes, improving progressive_disclosure.

Tighten the quoted warning blocks in the Security Scan and Uninstall sections into concise imperatives to reduce token cost without losing the safety guidance.

DimensionReasoningScore

Conciseness

Mostly efficient and focused on hard-won operational knowledge rather than generic padding, but the CSRF session setup is referenced repeatedly and a few warning/quote blocks could be trimmed without losing clarity.

4 / 5

Actionability

Every operation ships concrete, copy-paste-ready Python and bash with real endpoints, headers, and parameters — install (git/zip), scan, toggle, update, uninstall — covering the common cases fully.

5 / 5

Workflow Clarity

Destructive operations carry explicit validation checkpoints — uninstall confirmation prompts, 'NEVER delete from plugins/' guards, scan-verdict-to-action mapping, and scan-timeout handling — with feedback loops for the risky paths.

5 / 5

Progressive Disclosure

An action-routing table and well-labeled sections aid navigation, and references to sibling skills/docs are one level deep and clearly signaled, though substantial API/auth detail is inlined rather than split into a separate reference file.

4 / 5

Total

18

/

20

Passed

Description

96%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 strong, specific description that clearly states what the skill does and when to invoke it, with comprehensive natural trigger terms. The only minor risk is overlap with related plugin skills it references.

DimensionReasoningScore

Specificity

Enumerates many concrete actions — 'browse the Plugin Hub, scan for security, install from Git/ZIP/Plugin Hub, update, uninstall, enable, disable, debug, and troubleshoot' — giving comprehensive coverage of the plugin lifecycle.

5 / 5

Completeness

Explicitly answers both 'what' (the full lifecycle action list) and 'when' (a concrete 'Use when asked to...' clause enumerating trigger verbs), matching the top anchor.

5 / 5

Trigger Term Quality

'Use when asked to install, update, uninstall, remove, scan, find, search, enable, disable, debug, or troubleshoot a plugin' provides comprehensive natural trigger terms including synonyms like remove/uninstall and find/search.

5 / 5

Distinctiveness Conflict Risk

The 'Agent Zero plugins' niche is distinct with clear triggers, but it overlaps slightly with sibling skills (debug/create/review-plugin) that it explicitly routes to, so it sits just below the minimal-conflict top anchor.

4 / 5

Total

19

/

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.

Validation15 / 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.