Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add majiayu000/claude-skill-registry --skill agent-define-skillgit clone --depth 1 https://github.com/majiayu000/claude-skill-registryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-define-skill)<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-define-skill"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-define-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-define-skill"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-define-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.03219 |
| Opus 5 | $0.00012 | $0.01610 |
| Sonnet 5 | $0.00005 | $0.00644 |
| Haiku 4.5 | $0.00002 | $0.00322 |
Grade A, and why
agent-define-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-define-skill
用途: 定义 Agent(Subagent)的职责、擅长领域和配置
输入: Skills 列表、Workflows 列表、系统需求
输出: Agent 定义文件(.md)
核心原则
- 职责明确 - Agent 的职责要清晰
- 技能匹配 - Agent 擅长的 Skills 要与职责匹配
- 领域专精 - 每个 Agent 专注于特定领域
- 可协作 - Agent 之间可以通过 handoff 协作
- 适度数量 - 不要创建过多 Agent
输入格式
input:
system_info:
name: string # 系统名称
domain: string # 领域
purpose: string # 系统目标
skills: # 可用的 Skills
- name: string
purpose: string
complexity: string
workflows: # Workflows 列表
- name: string
purpose: string
main_skills: array # 主要使用的 Skills
requirements:
collaboration_needed: boolean # 是否需要多 Agent 协作
specialization_level: string # 专业化程度(low/medium/high)
输出格式
output:
agents: # Agent 列表
- name: string # Agent 名称
role: string # 角色描述
responsibilities: array # 职责列表
skills: array # 擅长的 Skills
workflows: array # 负责的 Workflows
personality: string # 性格特点(可选)
# Agent 文件内容
file_content: string # 完整的 .md 文件内容
执行逻辑
1. 分析系统需求
确定是否需要多个 Agent:
def should_create_multiple_agents(system_info, skills, workflows):
"""
判断是否需要创建多个 Agent
"""
# 简单系统:1 个 Agent
if len(skills) <= 5 and len(workflows) <= 3:
return False
# 复杂系统但领域单一:1 个 Agent
if system_info.specialization_level == "low":
return False
# 多领域系统:多个 Agent
skill_domains = identify_skill_domains(skills)
if len(skill_domains) >= 2:
return True
return False
2. 识别领域和角色
将 Skills 和 Workflows 按领域分组:
def identify_domains(skills, workflows):
"""
识别不同的领域
"""
# 健康管理系统示例
domains = {
"analysis": [], # 分析类
"reporting": [], # 报告类
"data_management": [] # 数据管理类
}
for skill in skills:
if "analysis" in skill.name or "assess" in skill.name:
domains["analysis"].append(skill)
elif "report" in skill.name or "review" in skill.name:
domains["reporting"].append(skill)
elif "collect" in skill.name or "data" in skill.name:
domains["data_management"].append(skill)
return domains
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 629 lines · 23 tokens per session scan A 57211fdbc5b9
agent-define-skill is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 3,219 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
remotion-docs
Search and fetch Remotion documentation pages.
remotion-captions
Dealing with captions in Remotion.
remotion-render
Best practices for rendering videos.
academy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude…
remotion-maps
Remotion Map animation knowledge.
mediabunny
Multimedia handling with the Mediabunny library.