Agent Skill Discovery
Agent Skill Discovery
Agent Skill Discovery is the workflow of finding, ranking, reading, and selectively adapting reusable agent skills before installing or copying them. It treats public skill hubs as a research corpus, not as a package manager to trust blindly.
Workflow
- Discover from multiple indexes: Hermes Skills Hub, skills.sh, GitHub repositories, and official platform skill collections.
- Rank by both popularity and trust: install count/star count, official source, repository reputation, recency, and specificity.
- Archive raw content before interpretation so future sessions can re-read the original instructions.
- Read for patterns: trigger design, precondition checks, tool commands, fallback paths, verification gates, and “do not use for” boundaries.
- Synthesize into wiki pages before installation.
- Install or adapt later only when a specific recurring task justifies it.
Quality signals
- Concrete trigger phrases in
description:. - Clear scope boundaries and negative triggers.
- Stepwise workflow with prerequisites before action.
- Verification steps and observable success criteria.
- References/scripts separated via progressive disclosure.
- Security boundaries for credentials, writes, purchases, deployment, or browser automation.
Anti-patterns
- Installing high-install skills without reading them.
- Treating install count as equivalent to quality.
- Copying commands for tools Hermes does not have.
- Letting a script own agent orchestration instead of keeping reasoning in the main agent.
Related
2026-06-30 补充：从技能文件到技能分发基础设施
Agent Skill Ecosystem Snapshot 2026-06-30 显示，外部技能生态正在从零散 SKILL.md 发展为分发基础设施：marketplace、package manager、lockfile、curated directory、cross-agent compatibility。代表项目包括 craftdesk、cc-skills 和 skill-of-skills。
因此 discovery workflow 的重点应继续保持在“先读再装”：星数和 marketplace 只能作为发现信号，不能替代对触发条件、权限边界、验证步骤和副作用的审查。
2026-08-30 补充：发现 skill 之后还要审计派生 skill
| [[evomal-self-poisoning-agent-skill-libraries | EVOMAL]] 把 Agent Skill Discovery 的安全边界从“外部 skill 是否可信”扩展到“agent 模仿外部 skill 后生成的派生 skill 是否可信”。共享 skill library 中的恶意模板即使未被直接调用，也可能在 authoring 阶段被复制进新 skill，并通过 agent-authored copies 留在长期库中。 |
因此 discovery workflow 应新增派生审计：任何从外部 README、网页、skill hub 或历史 skill 生成的新 skill，都应记录 derived_from、source_hash、author_run_id、review_status，并在进入自动加载前检查动态下载/执行、凭据读取、网络外传、混淆 payload、过宽权限和 banner-style copy。
写入记录
- 2026-08-30 09:00 CST：补充 EVOMAL 对 skill discovery、派生 skill provenance 与安全审计字段的启发。