Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
日本語の概要は準備中です。原文の説明を表示しています。
Author in-repo SKILL.md: frontmatter, validator, structure.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
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.
ls skills/<category>/
Read 2-3 peer SKILL.md files to match tone and structure.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 skill_manage(action='create') for an in-repo skill. It writes to ~/.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 branchまだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
日本語の概要は準備中です。原文の説明を表示しています。
专为追求倍速增长的初建学校设计的教师选、育、用、留四环节体系。基于科德高中融合部真实管理经验,结合十部AI Agent架构,将人才管理从校长个人经验升级为可继承、可协同、可沉淀的组织能力。
日本語の概要は準備中です。原文の説明を表示しています。
115 网盘智能管理:扫码登录、文件浏览、搜索、转存、离线下载、智能整理。适用于"登录 115"、"查看文件"、"搜索 xxx"、"转存链接"、"磁力链接"、"整理文件"等场景。
日本語の概要は準備中です。原文の説明を表示しています。
12306-specific knowledge for booking train tickets via the Android app. Covers UC WebView virtual list behavior, proven booking flow, and common pitfalls. Uses appium-android-adb bridge OR direct uiautomator2 for all interaction.
日本語の概要は準備中です。原文の説明を表示しています。
Connect to 163/126/yeah.net (Coremail) email via IMAP, read inbox, search emails, and send emails via SMTP. Activate when user asks to check email, read mail, send email, or monitor inbox on 163/126/yeah.net accounts. Handles the Coremail-specific IMAP ID command requirement that causes "Unsafe Login" errors in standard clients.
日本語の概要は準備中です。原文の説明を表示しています。
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.
日本語の概要は準備中です。原文の説明を表示しています。