Creating Skills
Skills are the preferred way to add new capabilities to Hermes Agent. They're easier to create than tools, require no code changes to the agent, and can be shar
- Section
- Developer Guide
- Source
- hermesbible.com/docs/developer-guide/creating-skills
Skills are the preferred way to add new capabilities to Hermes Agent. They're easier to create than tools, require no code changes to the agent, and can be shar
Excerpt from the official Hermes Agent documentation, quoted for reference. View sourceWhat this page covers
- Should it be a Skill or a Tool?
- Skill Directory Structure
- SKILL.md Format
- When to Use
- Quick Reference
- Procedure
- Pitfalls
- Verification
- Platform-Specific Skills
- Conditional Skill Activation
Section outline mirrored from the official Hermes Agent documentation. Follow any heading to read the complete text on the source site.
Upstream outline
- Should it be a Skill or a Tool?
- Skill Directory Structure
- SKILL.md Format
- When to Use
- Quick Reference
- Procedure
- Pitfalls
- Verification
- Platform-Specific Skills
- Conditional Skill Activation
- Environment Variable Requirements
- Secure Setup on Load
- Config Settings (config.yaml)
- Credential File Requirements (OAuth tokens, etc.)
Section map
Should it be a Skill or a Tool?
Maps should it be a skill or a tool? to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
Skill Directory Structure
Maps skill directory structure to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
SKILL.md Format
Maps skill.md format to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
When to Use
Maps when to use to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
Quick Reference
Maps quick reference to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
Procedure
Maps procedure to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
Pitfalls
Maps pitfalls to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
Verification
Maps verification to the Developer Guide documentation path, with the source page reserved for exact commands and updates.
Implementation notes
- Use this Developer Guide doc as a navigation page first: the local clone mirrors the source structure and links each heading back to the authoritative upstream section.
- Primary decision areas: Should it be a Skill or a Tool?, Skill Directory Structure, SKILL.md Format, When to Use, Quick Reference. Read those source anchors before changing installs, credentials, automation, or runtime configuration.
- Useful search signals for this doc: creating, skills, preferred, capabilities, agent.. These are derived from the public title and summary so the clone remains lightweight.
Decision table
Use when you need orientation for creating skills before applying exact upstream commands.
Open the source anchor for Should it be a Skill or a Tool? and confirm platform-specific requirements before changing configuration.
Use the upstream page as the authority for current syntax, release changes, and security-sensitive steps.
Verification checklist
- Use this page to orient yourself within Developer Guide, then open the linked source page for exact current syntax.
- Start with the source section for Should it be a Skill or a Tool?; do not rely on the local summary for commands or secrets.
- Check platform, install method, provider, and credential assumptions before changing a real environment.
- Review the source section for Skill Directory Structure if the page involves setup, automation, messaging, or runtime behavior.
- After applying anything from the source, run the smallest relevant smoke test before widening scope.
Risk notes
Treat every token, OAuth grant, secret manager entry, and API key as production-sensitive. Verify least privilege and revocation before reuse.
Set provider, token, and retry limits before scaling the workflow beyond a single test run.
Check filesystem, shell, browser, repository, and server permissions before granting the agent write access.
What this page covers
- Core concept and where it fits in the Hermes Agent system.
- Setup or operating context implied by the upstream page summary.
- The source page link for full current details and updates.
Source mirror note
This page is generated from the public Hermes Bible index so the clone has the same route coverage and search surface. It stores the public title, category, summary, and source link locally; use the source page for full upstream text and updates.
Open source page