hermes-agent-skill-authoring
Author in-repo SKILL.md: frontmatter, validator, structure.
Author in-repo SKILL.md: frontmatter, validator, structure.
Real data. Real impact.
Emerging
Developers
Per week
Excellent
Skills give you superpowers. Install in 30 seconds.
There are two places a SKILL.md can live:
~/.hermes/skills/<maybe-category>/<name>/SKILL.md — personal, not shared. Created via skill_manage(action='create')./home/bb/hermes-agent/skills/<category>/<name>/SKILL.md — committed, shipped with the package. Use write_file + git add. skill_manage(action='create') does NOT target this tree./home/bb/hermes-agent/skills/ (use patch for small edits, write_file for rewrites; skill_manage still works for patch on in-repo skills, but not for create)Source of truth:
tools/skill_manager_tool.py::_validate_frontmatter. Hard requirements:
--- as the first bytes (no leading blank line).\n---\n before the body.name field present.description field present, ≤ 1024 chars (MAX_DESCRIPTION_LENGTH).---.Peer-matched shape used by every skill under
skills/software-development/:
--- name: my-skill-name # lowercase, hyphens, ≤64 chars (MAX_NAME_LENGTH) description: Use when <trigger>. <one-line behavior>. version: 1.0.0 author: Hermes Agent license: MIT metadata: hermes: tags: [short, descriptive, tags] related_skills: [other-skill, another-skill] ---
version / author / license / metadata are NOT enforced by the validator, but every peer has them — omit and your skill sticks out.
MAX_SKILL_CONTENT_CHARS, ~36k tokens).software-development/ sit at 8-14k chars. Aim for that range. If you're pushing past 20k, split into references/*.md and reference them from SKILL.md.Every in-repo skill follows roughly:
# <Title> ## Overview One or two paragraphs: what and why. ## When to Use - Bulleted triggers - "Don't use for:" counter-triggers ## <Topic sections specific to the skill> - Quick-reference tables are common - Code blocks with exact commands - Hermes-specific recipes (tests via scripts/run_tests.sh, ui-tui paths, etc.) ## Common Pitfalls Numbered list of mistakes and their fixes. ## Verification Checklist - [ ] Checkbox list of post-action verifications ## One-Shot Recipes (optional) Named scenarios → concrete command sequences.
Not every section is mandatory, but
Overview + When to Use + actionable body + pitfalls are the minimum for the skill to feel like a peer.
skills/<category>/<skill-name>/SKILL.md
Categories currently in repo (confirm with
ls skills/): autonomous-ai-agents, creative, data-science, devops, dogfood, email, gaming, github, leisure, mcp, media, mlops/*, note-taking, productivity, red-teaming, research, smart-home, social-media, software-development.
Pick the closest existing category. Don't invent new top-level categories casually.
Read 2-3 peer SKILL.md files to match tone and structure.ls skills/<category>/
tools/skill_manager_tool.py if unsure.write_file to skills/<category>/<name>/SKILL.md.import yaml, re, pathlib content = pathlib.Path("skills/<category>/<name>/SKILL.md").read_text() assert content.startswith("---") m = re.search(r'\n---\s*\n', content[3:]) fm = yaml.safe_load(content[3:m.start()+3]) assert "name" in fm and "description" in fm assert len(fm["description"]) <= 1024 assert len(content) <= 100_000
skill_view / skills_list will not see the new skill until a new session. This is expected, not a bug.metadata.hermes.related_skills unions both trees (skills/ in-repo and ~/.hermes/skills/) at load time. You CAN reference a user-local skill from an in-repo skill, but it won't resolve for other users who clone the repo fresh. Prefer referencing only in-repo skills from in-repo skills. If a frequently-referenced skill lives only in ~/.hermes/skills/, consider promoting it to the repo.
skill_manage(action='patch', name=..., old_string=..., new_string=...) works fine on in-repo skills.write_file the whole SKILL.md. skill_manage(action='edit') also works but requires supplying the full new content.write_file to skills/<category>/<name>/references/<file>.md, templates/<file>, or scripts/<file>. skill_manage(action='write_file') also works and enforces the references/templates/scripts/assets subdir allowlist.Using
for an in-repo skill. It writes to skill_manage(action='create')
~/.hermes/skills/, not the repo tree. Use write_file for in-repo creation.
Leading whitespace before
. The validator checks ---
content.startswith("---"); any leading blank line or BOM fails validation.
Description too generic. Peer descriptions start with "Use when ..." and describe the trigger class, not the one task. "Use when debugging X" > "Debug X".
Forgetting the author/license/metadata block. Not validator-enforced, but every peer has it; omitting makes the skill look half-finished.
Writing a skill that duplicates a peer. Before creating,
ls skills/<category>/ and open 2-3 peers. Prefer extending an existing skill to creating a narrow sibling.
Expecting the current session to see the new skill. It won't. The skill loader is initialized at session start. Verify in a fresh session or via
skill_view using the exact path.
Linking to skills that don't exist in-repo.
related_skills: [some-user-local-skill] works for you but breaks for other clones. Prefer only in-repo links.
skills/<category>/<name>/SKILL.md (not in ~/.hermes/skills/)---, closes with \n---\nname, description, version, author, license, metadata.hermes.{tags, related_skills} all present# Title → ## Overview → ## When to Use → body → ## Common Pitfalls → ## Verification Checklistrelated_skills references resolve in-repo (or are explicitly OK to be user-local)git add skills/<category>/<name>/ && git commit completed on the intended branchMIT
mkdir -p ~/.hermes/skills/software-development/hermes-agent-skill-authoring && curl -o ~/.hermes/skills/software-development/hermes-agent-skill-authoring/SKILL.md https://raw.githubusercontent.com/NousResearch/hermes-agent/main/skills/software-development/hermes-agent-skill-authoring/SKILL.md1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.