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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./huashu-agent-swarm/SKILL.md

Quality

Content

76%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 content is highly actionable with concrete executable commands and a clear step sequence, but it lacks the validation checkpoints required for a destructive/batch operation that launches parallel autonomous agents. Progressive disclosure is well-organized with a real bundle, though one reference file is orphaned.

Suggestions

Add validation checkpoints to the workflow: verify setup_project.sh succeeded before starting the swarm, and have stop_swarm.sh validate that branch merges succeeded before cleaning worktrees (validate -> fix -> retry loop).

Remove the unrelated author-promotion footer ('花叔出品 | 公众号... 30万+粉丝') and avoid repeating the trigger-conditions block already in the frontmatter description.

Link references/carlini-lessons.md explicitly from the body (e.g., a 'Background / lessons learned' pointer) so no bundle file is orphaned.

Dimension	Reasoning	Score
Conciseness	Mostly lean with concrete commands and compact tables, but the trailing author-bio footer ('花叔出品 \| 公众号「花叔」\| 30万+粉丝') and the repeated trigger-conditions section are padding that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste ready commands with arguments throughout (setup_project.sh, start_swarm.sh, dashboard.py, stop_swarm.sh, tmux attach), covering the common cases with a specific config and risk table.	5 / 5
Workflow Clarity	A clear 5-step sequence exists, but this batch/destructive skill (8 autonomous --dangerously-skip-permissions agents, stop_swarm.sh auto-merging branches) has no validation checkpoints or feedback loops, capping workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Good structure: the body is an overview invoking 7 real scripts and one real reference template (agent-prompt-template.md) one level deep. Minor gap: references/carlini-lessons.md is not linked from the body and navigation is via command invocation rather than explicit 'See X.md' links.	4 / 5
	Total	16 / 20 Passed

Description

82%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 well-structured, explicitly covering both what the skill does and when to use it with concrete Chinese and English trigger phrases. Its main weakness is specificity, where the described actions lean toward abstract mechanism ('纯git自组织') rather than enumerated concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('多Agent蜂群并行协作', '纯git自组织', '适合大型项目开发') with 1-2 actions, but the actions are high-level mechanism descriptions rather than a comprehensive list of concrete capabilities.	3 / 5
Completeness	Explicitly answers both 'what' (multi-agent swarm with git self-organization for large projects) and 'when' ('当用户提到...时使用') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say ('蜂群模式', '多agent', '并行开发', 'agent swarm') with good coverage, though a few common synonyms/variations are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (agent swarm / git self-organization) with distinct triggers ('蜂群模式', 'agent swarm'), minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: alchaincyf/huashu-skills
Path: huashu-agent-swarm/SKILL.md
Commit: 49a55ba

Reviewed: 9 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.