New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Skill Authoring

by spytensor in spytensor/openmozi

How to install a skill package a user hands over (.skill/.zip/.tar.gz), and how to write a new skill into this runtime so it is listed, enabled and usable.

MITAuto-check passedAgent Workflows

Install Skill Authoring

skills CLI
$ npx skills add spytensor/openmozi --skill skill-authoring -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install spytensor/openmozi skill-authoring --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/spytensor/openmozi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-authoring .claude/skills/skill-authoring && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-authoring
GitHub stars
439
Token cost
~1.3k tokens
SKILL.md length
591 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

How to install a skill package a user hands over (.skill/.zip/.tar.gz), and how to write a new skill into this runtime so it is listed, enabled and usable.

  • Works in 4 steps: Write the files into a folder you can… → SKILL.md starts with YAML frontmatter.… → Install it — this is the step that makes… → …
  • The user says 安装这个技能/装一下这个 SKILL/install this skill
  • SKILL.md covers Installing a package the user…, Writing a new skill and Two things that are not this
  • Calls claude; needs SOME_API_KEY

What it does

Skill Authoring is an agent skill from spytensor/openmozi. How to install a skill package a user hands over (.skill/.zip/.tar.gz), and how to write a new skill into this runtime so it is listed, enabled and usable. Use when the user says 安装这个技能/装一下这个 SKILL/install this skill, uploads a skill package, or asks MOZI to 做一个技能/写一个 SKILL/把这个流程存成技能 — anything that ends with a skill living inside MOZI.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: A custom Agent OS built to be hackable, heavily inspired by OpenClaw. The licence is MIT.

When your agent uses it

  • The user says 安装这个技能/装一下这个 SKILL/install this skill
  • Uploads a skill package
  • Asks MOZI to 做一个技能/写一个 SKILL/把这个流程存成技能 — anything that ends with a skill living inside MOZI

Example prompts

  • “/skill-authoring”

Requirements

  • A credential in SOME_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Write the files into a folder you can write — the workspace, or beside
  2. SKILL.md starts with YAML frontmatter. name and description are
  3. Install it — this is the step that makes it real
  4. Confirm before you report success. Call list_runtime_skills (or

What it can do on your machine

Read from SKILL.md and the folder at commit ac46df0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • SOME_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Authoring loads about 1.3k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 591 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from spytensor/openmozi at commit ac46df0, republished under its MIT licence (© spytensor). 591 words, ~1,284 tokens.

Download SKILL.mdSave it as .claude/skills/skill-authoring/SKILL.md (or your agent's skills folder).
name
skill-authoring
description
How to install a skill package a user hands over (.skill/.zip/.tar.gz), and how to write a new skill into this runtime so it is listed, enabled and usable. Use when the user says 安装这个技能/装一下这个 SKILL/install this skill, uploads a skill package, or asks MOZI to 做一个技能/写一个 SKILL/把这个流程存成技能 — anything that ends with a skill living inside MOZI.
version
1.0.0
category
system
user-invocable
true
metadata.priority
60

Skill authoring and installation

This is MOZI's own runtime contract for skills. It is not the same as Claude Code's — skill-creator in this catalog is Anthropic's asset and describes .claude/ conventions and a claude -p eval loop that do not apply here. Follow this skill for anything that has to end up installed in MOZI.

Installing a package the user handed over

A skill package is an archive. .skill is the standard format (it is a zip); users also send plain .zip, and it is common for the archive to contain the .skill next to unrelated files they used while building it.

Pass the archive straight to install_skill. Do not unpack it first.

install_skill { "source": "path", "source_path": "<absolute path to the archive>" }
  • Uploaded files arrive with their absolute path in your turn context. Use that path verbatim.
  • source: "path" also accepts a directory containing SKILL.md, or the SKILL.md file itself.
  • source: "bundled" is only for reinstalling a skill MOZI already ships. It is never the right choice for a user's package — it needs skill_id, and a user's skill has no bundled id.
  • Add "overwrite": true only when replacing a skill of the same name.

The runtime unpacks the archive, finds SKILL.md (at the root, in a single wrapper directory, or in a single nested .skill), copies it into the workspace skill directory, and reloads the catalog. The result includes eligible and any missing_bins / missing_env.

If it refuses, the message says why. Act on it rather than retrying:

MessageWhat to do
No SKILL.md found inside <file>Not a skill package. Look inside with shell_exec and tell the user what it actually contains.
contains N skillsAsk which one, then point source_path at that directory after unpacking.
Workspace skill already existsConfirm with the user, then repeat with "overwrite": true.
missing_bins / missing_env non-emptyIt installed but cannot run yet. Tell the user exactly which binary or key is missing.
Show full SKILL.md (360 more words)Show less

Writing a new skill

When the user asks MOZI to turn a workflow into a skill:

  1. Write the files into a folder you can write — the workspace, or beside the files this turn is already working with. A skill is a directory:

    <name>/
  SKILL.md          # required
  references/       # optional supporting docs
  scripts/          # optional executable helpers

  2. SKILL.md starts with YAML frontmatter. name and description are required; everything else is optional:

    yaml
    ---
name: weekly-pnl-brief
description: "What it does, and — just as important — when it should trigger. Include the phrasings a user would actually type, in their language."
version: "1.0.0"
category: utility        # utility | coding | research | communication | media | system
user-invocable: true     # false = model-only, not callable by name
requires:
  bins: [python3]        # checked at load; missing ones make the skill ineligible
  env: [SOME_API_KEY]
---

    The body below the frontmatter is the procedure, and it is what gets loaded into context when the skill activates. Write it as steps, not prose.

  3. Install it — this is the step that makes it real:

    install_skill { "source": "path", "source_path": "<the folder you just wrote>" }

    Installing copies the folder into the workspace skill directory and refreshes the catalog. Writing SKILL.md somewhere and stopping does not install anything.

  4. Confirm before you report success. Call list_runtime_skills (or validate_skill) and check the skill is listed, enabled and eligible. Report what the runtime returned, not what you intended.

description decides whether the skill is ever used again: it is the only line in the catalog, so it must carry both what the skill does and when to reach for it. A description that only says what it does will never trigger.

Two things that are not this

  • propose_skill persists a draft into the autogen namespace with user-invocable: false. It is for a workflow you judged reusable mid-task — not for a skill the user asked you to make. Autogen drafts are hidden from the operator's Skills page, so a user who asked for a skill would see nothing there.
  • Editing an installed skill is install_skill with "overwrite": true, or the operator editing SKILL.md on the Skills page. Do not hand-patch files under the workspace skill directory and assume the catalog noticed; call reload_skills if you do.

© spytensor, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/skill-authoring of spytensor/openmozi.

Open the folder on GitHubat commit ac46df0

Compare with similar skills

Skill Authoring next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Authoring compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Authoring this skillspytensor/openmozi439—~1.3kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79489 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k10 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official37k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official37k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    794 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 10 repos~3.5k tokens
    Agent WorkflowsAuto-check passed

  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    37k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    37k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed

  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    65k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from spytensor/openmozi

All 13 skills in this repo

  • Commit

    spytensor/openmozi

    Smart commit: bump version, find related issues, commit with Co-authored-by, push.

    439 GitHub stars~480 tokensUpdated 2 mo ago
    Auto-check passed

  • Pipeline

    spytensor/openmozi

    Full development pipeline: create GitHub issue, plan, implement with agent team, verify (build+test), commit, push, close issue.

    439 GitHub stars~549 tokensUpdated 2 mo ago
    Auto-check passed

  • Coding Agent

    spytensor/openmozi

    Structured coding workflow: read, plan, implement, test, verify

    439 GitHub stars~723 tokensUpdated 2 mo ago
    Auto-check passed

  • Research Workflow

    spytensor/openmozi

    Structured research workflow: decompose the question, search in parallel, cross-verify sources, synthesize with citations.

    439 GitHub stars~594 tokensUpdated 2 mo ago
    Auto-check passed

  • Self Ops

    spytensor/openmozi

    Runtime self-diagnosis knowledge: database layout, observability APIs, timeout hierarchy, restart procedure, failure replay.

    439 GitHub stars~767 tokensUpdated 2 mo ago
    Auto-check passed

  • Creative Writing

    spytensor/openmozi

    Creative content workflow: brief, research, outline, draft, refine.

    439 GitHub stars~373 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Skill Authoring

What does Skill Authoring do?

How to install a skill package a user hands over (.skill/.zip/.tar.gz), and how to write a new skill into this runtime so it is listed, enabled and usable. Skill Authoring is an agent skill from spytensor/openmozi.gz), and how to write a new skill into this runtime so it is listed, enabled and usable.

When should I use Skill Authoring?

Skill Authoring fits situations like: the user says 安装这个技能/装一下这个 SKILL/install this skill; uploads a skill package; asks MOZI to 做一个技能/写一个 SKILL/把这个流程存成技能 — anything that ends with a skill living inside MOZI.

How do I install Skill Authoring in Claude Code?

Run `npx skills add spytensor/openmozi --skill skill-authoring -a claude-code`. Or copy the skill folder (skills/skill-authoring in spytensor/openmozi) into .claude/skills/skill-authoring in your project. Claude Code loads it when a task matches its description.

How do I install Skill Authoring in Codex?

Run `npx skills add spytensor/openmozi --skill skill-authoring -a codex`. Or copy the skill folder (skills/skill-authoring in spytensor/openmozi) into .agents/skills/skill-authoring in your project. Codex loads it when a task matches its description.

Can I use Skill Authoring in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add spytensor/openmozi --skill skill-authoring -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-authoring, .gemini/skills/skill-authoring, .github/skills/skill-authoring and .opencode/skills/skill-authoring in your project.

What does Skill Authoring need to run?

Going by SKILL.md and its folder, Skill Authoring needs the command-line tools its instructions call (claude) and credentials named SOME_API_KEY. Our summary lists: A credential in SOME_API_KEY.

Does Skill Authoring access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Authoring safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Skill Authoring use?

Skill Authoring is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Authoring use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Authoring?

Skills that share tags, products or a category with Skill Authoring: Skill Creator (Azure/azqr, 794 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Authoring?

spytensor (a GitHub user) maintains it in spytensor/openmozi, which has 439 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 7, 2026.

Source: spytensor/openmozi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.