- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add aden-hive/hive --skill writing-hive-skills -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add aden-hive/hive --skill writing-hive-skills -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add aden-hive/hive --skill writing-hive-skills -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add aden-hive/hive --skill writing-hive-skills -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/aden-hive/hive/tree/HEAD/core/framework/skills/_default_skills/writing-hive-skills來自發布者
Hive agents discover skills by scanning several roots, in precedence order (later wins):
core/framework/skills/_default_skills/~/.agents/skills/ — user, cross-client$HIVE_HOME/skills/ — the shared library every queen and colony reads$HIVE_HOME/queens/<queen_id>/skills/ — one queen's own skills (her colonies read them too)$HIVE_HOME/colonies/<colony_name>/skills/ — one colony's skills<project>/.agents/skills/, then <project>/.hive/skills/ — projectEach skill is a directory containing a SKILL.md. At startup, only the frontmatter name + description of every skill is loaded; the body is loaded only when the agent activates the skill. Design for that.
write_skillAlways add a skill with write_skill. Never write a SKILL.md into a skills folder with the terminal or write_file: a skill put there by hand isn't in any running catalog until a new session, and one put in the shared library skips the user's approval. write_skill takes the content inline or copies an existing skill folder (source_path, e.g. one you git cloned into your workspace), and its scope decides who sees it:
scope="queen"): a protocol, an API you use, a style you keep. You can replace a skill you wrote, but not one the user made in your skills.scope="colony"): the operational protocol a single colony needs — its API auth, DOM selectors, DB schema, task-queue conventions. Write it once before fanning out workers and name it in each task string. Keeping it in the colony means no other colony sees it at selection time.scope="global"): only when the skill is genuinely useful to every queen. Nothing is installed when you call it: the user is asked in this session's chat in the Hive dashboard, and a message tells you when they approve or decline. You don't wait for it; carry on. If you're talking with them in a chat app, tell them it's waiting in the dashboard.write_skill(
skill_name="honeycomb-api-protocol",
skill_description="How to query the HoneyComb staging API…",
skill_body="## Operational Protocol\n\nAuth: …",
skill_files=[{"path": "scripts/fetch_tickers.py", "content": "…"}], # optional
scope="colony",
)
<project>/.hive/skills/ when the skill is tied to that codebase's APIs, conventions, or infra and multiple agents in the project should share it.core/framework/skills/_default_skills/ AND register in framework/skills/defaults.py::SKILL_REGISTRY only when the skill is a universal operational protocol shipped with Hive. Default skills use the hive.<name> naming convention and include type: default-skill in metadata.<skill-name>/
├── SKILL.md # Required
├── scripts/ # Optional — executable helpers
├── references/ # Optional — on-demand docs
└── assets/ # Optional — templates, data, images
Rules:
name frontmatter field (for framework defaults, the directory is the unprefixed name, e.g. writing-hive-skills/ for hive.writing-hive-skills).SKILL.md under ~500 lines. Move long reference material into references/.scripts/foo.py, references/API.md). Keep references one level deep.Required fields:
Optional fields:
Minimal template:
---
name: my-skill
description: One sentence on what it does. One sentence on when to use it, with concrete trigger words the agent will see in user requests.
---
# My Skill
<body>
descriptionThis is the single most important field — it's the only thing the agent sees at skill-selection time.
Helps with trading.Buy and sell shares on the HoneyComb exchange. Handles auth, slippage-protected orders, idempotent retries, and AMM output estimation. Use when placing trades or interacting with the AMM.Include verbs the user is likely to say (buy, sell, place trade) and proper nouns (HoneyComb, AMM).
Structure the body for the agent, not a human reader:
Recommended sections (adapt to the domain):
Three tiers of context cost:
name + description. Keep tight.SKILL.md.scripts/, references/, assets/. The agent reads these only when the body points to them.If a section is long and only needed sometimes (e.g., a full schema dump, rarely-used edge cases), move it to references/SOMETHING.md and link to it from the body: See [the error catalog](references/ERRORS.md) for the full list.
Put executable helpers in scripts/. They should:
Reference them from the body by relative path:
Estimate buy output with `scripts/estimate_buy.py --v-hc 1000000 --v-shares 1000000 --hc 500`.
For Python scripts in a Hive project, prefer uv run scripts/foo.py ....
<skill-name> (lowercase-hyphenated).write_skill with that scope — STOP here, do not hand-author the folder), project (<project>/.hive/skills/), or framework default (core/framework/skills/_default_skills/ + registry entry).SKILL.md with frontmatter + body.scripts/, references/, assets/ only if needed.uv run hive skill validate <path-to-skill-dir>
uv run hive skill doctor
uv run hive skill list.When adding a skill as a shipped default:
core/framework/skills/_default_skills/<unprefixed-name>/.name: hive.<unprefixed-name> and metadata.type: default-skill.SKILL_REGISTRY in core/framework/skills/defaults.py:
SKILL_REGISTRY: dict[str, str] = {
...
"hive.<unprefixed-name>": "<unprefixed-name>",
}
{{placeholder}} substitution, add defaults to _SKILL_DEFAULTS in the same file.DATA_BUFFER_KEYS.SKILL.md.Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to cr
---name: hive.writing-hive-skillsdescription: Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML…---# core/framework/skills/_default_skills/writing-hive-skills/SKILL.md總覽
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, install, or package a new skill for a Hive agent, or you want to keep a procedure as a skill.
常見問題
從發布者下載 core/framework/skills/_default_skills/writing-hive-skills/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/aden-hive/hive。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。