huashu-agent-swarm

多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

72%Weight 40%Scale 1-3

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

Highly actionable with a clean sequenced workflow and good progressive-disclosure structure, but it loses points for padding (the inspiration quote and promotional footer) and for lacking validation checkpoints on a risky batch operation.

Suggestions

Remove the Carlini inspiration epigraph and the '花叔出品' promotional footer; they add tokens without aiding execution.

Add an explicit validation/health-check checkpoint to the swarm workflow (e.g. after start_swarm.sh, verify each pane is looping via status.sh before walking away).

Reference the existing references/carlini-lessons.md from the body or remove it, so every bundle file is discoverable.

Dimension	Reasoning	Score
Conciseness	The bulk is lean executable commands, but the Carlini inspiration epigraph and the '花叔出品…30万+粉丝' self-promotional footer are unnecessary tokens that do not earn their place, matching the score-2 'could be tightened' anchor rather than score 3.	2 / 3
Actionability	Every step ships a concrete, copy-paste-ready command with arguments (setup_project.sh, start_swarm.sh, dashboard.py, status.sh, send_input.sh, stop_swarm.sh).	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced, but this batch operation (spawning 8 autonomous agents writing code in parallel) has no validation/health-check checkpoints in the workflow itself, so per the batch-operations guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	The body is an overview that signals one-level-deep real bundle files (references/agent-prompt-template.md and the scripts/), with detail (e.g. dashboard.py) appropriately split out into files; navigation is easy.	3 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 with an explicit trigger clause and good natural-language keywords; its only weakness is that the capability statement leans conceptual rather than enumerating concrete actions. Voice is correctly third person.

Dimension	Reasoning	Score
Specificity	Names the domain ('大型项目开发') and some actions ('多Agent蜂群并行协作', '纯git自组织') but they are abstract concepts rather than a comprehensive list of concrete actions, matching the score-2 anchor.	2 / 3
Completeness	States both what it does (multi-agent parallel collaboration via git self-organization) and an explicit 'when' trigger ('当用户提到…时使用'), satisfying both halves.	3 / 3
Trigger Term Quality	Provides natural user-facing keywords — '蜂群模式', '多agent', '并行开发', 'agent swarm' — covering the variations a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche (agent-swarm orchestration for large projects) with distinctive triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: alchaincyf/huashu-skills
Path: huashu-agent-swarm/SKILL.md
Commit: 35e7cf3

Reviewed: 12 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.