yao-agent

Agent management expert. ALWAYS invoke this skill when you need to list available agents, download or reference agent source code, deploy agent code to the host, or query the LLM connector matrix. Do not guess agent structures — use this skill first.

Quality

86%

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

83%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 concise, highly actionable single-file tool reference with clean per-tool sections and executable examples. Its main weakness is the lack of a validation/verification step around the destructive deploy operation.

Suggestions

Add an explicit pre-deploy validation checkpoint (e.g. re-run `agent_list`/`agent_reference` to confirm the target id and namespace before calling `agent_deploy`) and an error-recovery note for rejected deploys.

Consider splitting the per-tool parameter tables into a short reference file if the skill grows, keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	Lean throughout — short tool intros, parameter tables, and copy-paste bash commands with no over-explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	Each tool ships with executable `tai tool ...` commands and concrete JSON argument examples covering the common cases, plus parameter tables — fully copy-paste ready.	5 / 5
Workflow Clarity	The Guidelines give a rough sequence (list before download/reference, deploy is smith-only), but the destructive `agent_deploy` operation has no validate-before-deploy checkpoint, so per the destructive-operations cap it cannot exceed 3.	3 / 5
Progressive Disclosure	Well-organized into one section per tool with a closing Guidelines section and no nested references; self-contained and easy to navigate, though at ~80 lines it slightly exceeds the under-50-line simple-skill exception that would warrant a 5.	4 / 5
	Total	17 / 20 Passed

Description

88%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 description that pairs a clear capability list with an explicit 'use when' trigger clause and reinforced 'use this skill first' guidance. Slightly lacking in synonym coverage and the niche is moderately broad.

Suggestions

Add a few natural synonyms or phrasings users might say (e.g. 'browse agents', 'pull agent code', 'inspect connectors') to broaden trigger coverage.

Tighten the niche framing so it is clearly distinct from any general 'agent' or 'host tooling' skill that might coexist.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'list available agents', 'download or reference agent source code', 'deploy agent code to the host', 'query the LLM connector matrix' — covering the full toolset comprehensively.	5 / 5
Completeness	Clearly answers what ('Agent management expert' plus the enumerated actions) and when ('ALWAYS invoke this skill when you need to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'list available agents', 'download agent source code', and 'query the LLM connector matrix' are present, but synonyms and common variations are missing, so it falls just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The niche is mostly distinct — smith-namespace restrictions and the 'LLM connector matrix' are specific triggers — but 'agent management' is broad enough to carry minor overlap risk with related skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: YaoApp/yao
Path: tools/skills/yao-agent/SKILL.md
Commit: 8999225

Reviewed: 3 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.