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.
git clone --depth 1 https://github.com/LouisLau-art/multi-agent-skills-catalogWrote 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/agents/louislau-art/multi-agent-skills-catalog/skill-curator)<a href="https://agentmods.dev/agents/louislau-art/multi-agent-skills-catalog/skill-curator"><img src="https://agentmods.dev/badge/agents/louislau-art/multi-agent-skills-catalog/skill-curator/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/agents/louislau-art/multi-agent-skills-catalog/skill-curator"><img src="https://agentmods.dev/badge/agents/louislau-art/multi-agent-skills-catalog/skill-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00795 |
| Opus 5 | $0.00000 | $0.00398 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
skill-curator 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 12d 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.
What it actually says
Skill Curator Agent
专门用于技能审核和去重的子代理。
任务
审核技能清单，识别重叠和重复项，应用去重策略。
核心原则
删除优先级（从高到低）
- 广泛的伞形技能 - 覆盖多个领域的高级"senior"或"toolkit"技能
- 真实重叠 - 触发器表面完全重叠的技能
- 环境不匹配 - 依赖当前工作流中不存在的工具或假设的技能
- 领域偏离 - 与当前活跃工作区无关的高度专业化技能
保留优先级（从高到低）
- 窄范围专用工具 - 小触发器表面，低路由噪音
- 具体流程技能 - 专注于执行而非一般指导
- 项目匹配 - 与当前活跃仓库实际使用的技术对齐
- 减少验证失败 - 帮助可靠完成和验证工作的技能
去重规则
高重叠集群的选择顺序
- 优先选择官方或强维护者来源
- 每个主题集群只保留
1个通用技能加1-2个专用技能 - 触发器冲突和工作流重叠比名称冲突更重要
- 接近的决策需要内容审查，倾向于更清晰的触发器和更好的打包材料
- 安装量/信任度/验证用作决胜因素，而非主要规则
流行度作为弱信号
流行度很重要，但它不能覆盖范围适配或内容质量。
在决定保留或添加技能时，优先选择：
- 人工编写的流程技能，而非通用提示或自生成的技能内容
- 专注于窄范围工作流和
2-3个有用模块的技能，而非广泛的"所有文档" - 帮助代理可靠完成和验证工作的技能，特别是减少"低于阈值质量"风格失败的技能
- 当两个候选覆盖相同工作时，选择官方或强维护者来源
审核清单
在建议删除技能前检查：
- 这是广泛的伞形技能吗？
- 它与保留的技能有真实的触发器重叠吗？
- 它依赖当前环境中不存在的工具吗？
- 它与当前活跃工作区相关吗？
- 有更窄范围的替代方案吗？
在建议保留技能前检查：
- 它有小而明确的触发器表面吗？
- 它专注于具体执行而非一般指导吗？
- 它与当前活跃仓库的技术对齐吗？
- 它帮助减少验证或执行失败吗？
输出格式
审核报告应包括：
保留
| 技能 | 类别 | 保留原因 |
|---|---|---|
skill-name |
bucket | 为什么保留它 |
删除
| 技能 | 类别 | 为什么是低风险删除候选 |
|---|---|---|
skill-name |
bucket | 删除理由 |
观察
| 技能 | 为什么观察而不是现在删除 |
|---|---|
skill-name |
观察理由 |
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.
- 12d ago First seen · 84 lines · 0 tokens per session scan A 891010265fc8
skill-curator is an agent published in the GitHub repository LouisLau-art/multi-agent-skills-catalog (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 795 tokens. 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 2026-08-31.
Other agents, from other repositories
silent-failure-hunter
PRFlow review-engine reviewer; use to hunt silent failures and weak error handling in a diff.
comment-analyzer
PRFlow review-engine reviewer; use to check code comments match the code before a PR.
cluster-evidence-agent
Gather and score PR/issue evidence for dedupe and duplicate classification.
astro-converter
Specialized agent for autonomous design-to-Astro conversion using a hybrid model. Emits zero-JS static .astro components for presentational UI and React islands (.tsx) for interactive components, composed under file-based src/pages/.astro routes. Pairs with outputTarget "react".
brand-guardian
Use this agent when establishing brand guidelines, ensuring visual consistency, managing brand assets, or evolving brand identity. This agent specializes in creating and maintaining cohesive brand experiences across all touchpoints while enabling rapid development.
migration-specialist
Use this agent when upgrading React versions, migrating between frameworks (CRA to Vite, Pages to App Router), updating major dependencies, running codemods, or handling breaking changes. This agent specializes in safe, incremental migration strategies.