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 Ow1onp/hermes-agent-skills --skill skill-curatorgit clone --depth 1 https://github.com/Ow1onp/hermes-agent-skillsWrote 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/ow1onp/hermes-agent-skills/skill-curator)<a href="https://agentmods.dev/skills/ow1onp/hermes-agent-skills/skill-curator"><img src="https://agentmods.dev/badge/skills/ow1onp/hermes-agent-skills/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/skills/ow1onp/hermes-agent-skills/skill-curator"><img src="https://agentmods.dev/badge/skills/ow1onp/hermes-agent-skills/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 | $0.00054 | $0.01509 |
| Opus 5 | $0.00027 | $0.00754 |
| Sonnet 5 | $0.00011 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
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 10d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技能策展人 (Skill Curator) — 自进化引擎
1. 概述
这是整个技能集合的 "元技能"——它不直接完成具体任务,而是让所有其他技能变得更好。本技能对接 Hermes Agent 的 /curator 自学习系统,自动分析任务执行记录,提出技能创建/更新/废弃建议,形成持续改进的正反馈循环。
执行任务 → 分析记录 → 发现改进点 → 更新技能 → 下次更好
↑ │
└────────────────────────────────────────────┘
自我进化正反馈循环
2. 核心流程
2.1 四阶段策展流程
阶段一:采集 (Collect)
├─ 从 session_search 获取最近完成的复杂任务
├─ 识别执行中的困难点(多次重试、用户纠正、工具调用失败)
└─ 提取关键决策点和工作流
阶段二:分析 (Analyze)
├─ 对比现有技能库:这个工作流是否已被某个技能覆盖?
├─ 评估复用价值:下次遇到类似任务,这个工作流能用上吗?
├─ 识别技能盲区:现有技能是否缺少关键步骤或陷阱提醒?
└─ 量化改进空间:如果当时有这个技能,能节省多少时间/Token?
阶段三:建议 (Propose)
├─ 创建建议:全新的工作流 → 建议创建新技能
├─ 更新建议:现有技能有缺陷 → 建议 patch 更新
├─ 废弃建议:长期未使用的技能 → 建议标记为 stale
└─ 合并建议:多个技能有重叠 → 建议合并
阶段四:执行 (Execute)
├─ 使用 skill_manage(action="create") 创建新技能
├─ 使用 skill_manage(action="patch") 更新现有技能
├─ 使用 /curator archive 归档废弃技能
└─ 验证更新后的技能在下次类似任务中有效
2.2 技能质量评估矩阵
| 维度 | 指标 | 健康阈值 | 警告阈值 |
|---|---|---|---|
| 使用频率 | 30 天内被调用次数 | ≥ 3 次 | ≤ 1 次 → stale 候选 |
| 成功率 | 使用技能后任务成功完成率 | ≥ 80% | ≤ 50% → 需要重写 |
| 用户满意度 | 技能执行后无用户纠正/抱怨 | 0 纠正 | ≥ 2 次纠正 → 质量有问题 |
| 时效性 | 距离上次更新的天数 | ≤ 90 天 | ≥ 180 天 → 需要审查 |
| 命令准确率 | 技能中的命令是否仍有效 | 100% | 任何失效命令 → 立即更新 |
2.3 Hermes 命令体系集成
# 查看技能健康状态
/curator status
# 手动触发策展审查
/curator run
# 对特定技能进行深度分析
/curator review skill-name
# 固定优质技能(防止自动归档)
/curator pin skill-name
# 归档长期未使用的技能
/curator archive skill-name
# 在 Hermes 会话中直接分析最近任务
session_search(query="recent complex tasks", limit=5)
2.4 自进化自举机制
本技能自身也在进化范围内——当策展流程发现更有效的分析方法时,它会更新自己的分析逻辑:
- 分析模式积累:从高评分任务中提取成功的分析模式
- 误判修正:如果某技能被错误标记为 stale 但后来被频繁使用,调整阈值
- 领域自适应:不同项目类型(Web/ML/Infra)使用不同的评估权重
- 用户偏好学习:用户更倾向于创建新技能还是更新现有技能?调整建议倾向
2.5 身份感知
- 读取
SOUL.md中的 "自我进化" 态度 - 保守型用户 → 更谨慎的建议,更低的自动执行频率
- 激进型用户 → 更积极的建议,允许自动应用低风险更新
- 技能文档风格跟随 SOUL 人设
3. 门禁标准
- 分析阶段至少检查了最近 3 个已完成任务
- 评估矩阵的五维度全部有数据支撑(无主观猜测)
- 建议包含具体的改进前后对比
- 如果建议创建新技能,已检查不与现有技能重复
- 如果建议更新现有技能,提供了 old_string / new_string
- 所有建议在执行前已向用户呈现并获得确认
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.
- 10d ago First seen · 117 lines · 54 tokens per session scan A 48b30c4ddeef
skill-curator is a skill published in the GitHub repository Ow1onp/hermes-agent-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,509 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
openspec-plus-apply
MANDATORY skill that activates whenever the OpenSpec apply phase begins. Triggers: /opsx-apply runs, the openspec-apply-change vanilla skill is referenced or active, openspec instructions apply is invoked, or the user asks to implement, apply, execute, or build out an OpenSpec change ('implement the change', 'apply…
openspec-plus-design
MANDATORY skill that activates whenever the OpenSpec design phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; openspec instructions design is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec design…
openspec-plus-spec
MANDATORY skill that activates whenever the OpenSpec specification phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; openspec instructions spec or openspec instructions specs is invoked; or the user wants to create, update, review…
openspec-plus-tdd
MANDATORY skill that activates whenever code is written to implement an OpenSpec change task. Triggers: openspec-plus-apply is active, /opsx-apply is running, the user is implementing tasks from an OpenSpec change, an implementer subagent dispatched by openspec-plus-apply is starting work, or the user invokes phrases…
openspec-plus-tasks
MANDATORY skill that activates whenever the OpenSpec tasks phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; openspec instructions tasks is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec tasks.md…
openspec-plus-proposal
MANDATORY skill that activates whenever the OpenSpec proposal phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; openspec instructions proposal is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec…