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.
Lists, downloads, references and deploys agents on a Yao host through five bash-invoked tools, keeping edits to the smith namespace while allowing read-only study of any agent.
Install Yao Agent Management Tools
$ npx skills add YaoApp/yao --skill yao-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install YaoApp/yao yao-agent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/YaoApp/yao.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tools/skills/yao-agent .claude/skills/yao-agent && rm -rf skills-srcUse ~/.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/
Install the "yao-agent" agent skill from https://github.com/YaoApp/yao/tree/main/tools/skills/yao-agent into .claude/skills/yao-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-agent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/YaoApp/yao/tree/main/tools/skills/yao-agentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add YaoApp/yao --skill yao-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install YaoApp/yao yao-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YaoApp/yao.git skills-src && mkdir -p .agents/skills && cp -r skills-src/tools/skills/yao-agent .agents/skills/yao-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "yao-agent" agent skill from https://github.com/YaoApp/yao/tree/main/tools/skills/yao-agent into .agents/skills/yao-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-agent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add YaoApp/yao --skill yao-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install YaoApp/yao yao-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YaoApp/yao.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/tools/skills/yao-agent .cursor/skills/yao-agent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "yao-agent" agent skill from https://github.com/YaoApp/yao/tree/main/tools/skills/yao-agent into .cursor/skills/yao-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-agent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/YaoApp/yao.git --path tools/skills/yao-agent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add YaoApp/yao --skill yao-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install YaoApp/yao yao-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YaoApp/yao.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/tools/skills/yao-agent .gemini/skills/yao-agent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "yao-agent" agent skill from https://github.com/YaoApp/yao/tree/main/tools/skills/yao-agent into .gemini/skills/yao-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-agent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install YaoApp/yao yao-agentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add YaoApp/yao --skill yao-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/YaoApp/yao.git skills-src && mkdir -p .github/skills && cp -r skills-src/tools/skills/yao-agent .github/skills/yao-agent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "yao-agent" agent skill from https://github.com/YaoApp/yao/tree/main/tools/skills/yao-agent into .github/skills/yao-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-agent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add YaoApp/yao --skill yao-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install YaoApp/yao yao-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/YaoApp/yao.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/tools/skills/yao-agent .opencode/skills/yao-agent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "yao-agent" agent skill from https://github.com/YaoApp/yao/tree/main/tools/skills/yao-agent into .opencode/skills/yao-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yao-agent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
yao-agent- GitHub stars
- 8.1k
- Token cost
- ~873 tokens
- SKILL.md length
- 262 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Lists, downloads, references and deploys agents on a Yao host through five bash-invoked tools, keeping edits to the smith namespace while allowing read-only study of any agent.
- Listing what agents are available on a Yao host
- SKILL.md covers agent_list, agent_download, agent_reference and agent_deploy, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Downloading a smith-namespace agent's source to edit it locally
What it does
The skill wraps five tools called through the tai bash command. agent_list returns id, name, description and capabilities for every agent, optionally filtered by namespace. agent_download pulls a smith-namespace agent's source into a development directory for editing and is restricted to that namespace only, while agent_reference downloads any agent's source, from any namespace, into a separate read-only study folder.
agent_deploy pushes source from the sandbox development directory back to the host, again restricted to the smith namespace, with an optional message for logging, and rejects an attempt to deploy into another namespace. A further agent_connectors tool, described but truncated in the excerpt, is mentioned for querying the LLM connector matrix.
When your agent uses it
- Listing what agents are available on a Yao host
- Downloading a smith-namespace agent's source to edit it locally
- Deploying an edited smith agent back to the host
Example prompts
- “List all agents in the smith namespace.”
- “Download smith.weather for editing, then deploy it back after I add a page.”
- “Reference yao.slides so I can study how it's built.”
Requirements
- The tai CLI on the host
What it can do on your machine
Read from SKILL.md and the folder at commit 0b6ee5f. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Yao Agent Management Tools loads about 873 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 262 words of instructions outside code blocks.
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 262 words (~873 tokens).
“Five tools for managing agents on the host, called via bash.”
- name
- yao-agent
Files
Just SKILL.md in tools/skills/yao-agent of YaoApp/yao.
Open the folder on GitHubat commit 0b6ee5f
Compare with similar skills
Yao Agent Management Tools 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 | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Yao Agent Management Tools this skillYaoApp/yao | 8.1k | — | ~873 | Automated safety check: Pass | Custom licence | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Using Agent Skillsaddyosmani/agent-skills | 103k | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Ponytail Help CardDietrichGebert/ponytail | 158k | — | ~728 | Automated safety check: Pass | MIT | |
| Skill Creatorzhayujie/CowAgent | 47k | — | ~4.7k | Automated safety check: Notes | MIT | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
Ponytail Help Card
DietrichGebert/ponytail
Shows a one-shot quick-reference card for the ponytail skills: intensity levels, the six commands, and how to turn it off, set a default mode and update.
Skill Creator
zhayujie/CowAgent
Guides creating, installing and updating agent skills in a workspace: SKILL.md frontmatter, bundled scripts and references, with scripts to scaffold, validate and package.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
Open-Science Skill Creator
aipoch/open-science
Creates, revises, evaluates and publishes skills in the Open-Science app through its native host.skills composer, with optional test prompts and benchmarks.
More from YaoApp/yao
All 14 skills in this repoYao Image Tools
YaoApp/yao
Lets an agent read and describe images through a vision model and generate or edit images from text prompts, using the tai command-line tool.
Yao Audio Transcription
YaoApp/yao
Transcribes audio files such as mp3, m4a, wav and webm to text with the tai audio_transcribe tool, and lists the available speech-to-text providers.
Yao Daemon Manager
YaoApp/yao
Starts, lists, checks, restarts and stops long-running background services through Yao daemon tools, reporting the verified port and URL of each.
Yao Background Job Manager
YaoApp/yao
Starts, lists, monitors, waits on and stops long-running background commands through a dedicated set of job-management tools.
Yao Workspace Files
YaoApp/yao
Lists workspaces and reads or writes their files on a remote node through five tai tool commands, for cross-node file work the local filesystem cannot do.
Yao Workspace Git Config
YaoApp/yao
Manages Git identity, HTTPS access tokens and SSH keys at the workspace level through three `tai tool` commands, each with a get, set, list, import or delete action.
Related
Categories
Questions about Yao Agent Management Tools
What does Yao Agent Management Tools do?
Lists, downloads, references and deploys agents on a Yao host through five bash-invoked tools, keeping edits to the smith namespace while allowing read-only study of any agent. The skill wraps five tools called through the tai bash command. agent_list returns id, name, description and capabilities for every agent, optionally filtered by namespace.
When should I use Yao Agent Management Tools?
Yao Agent Management Tools fits situations like: listing what agents are available on a Yao host; downloading a smith-namespace agent's source to edit it locally; deploying an edited smith agent back to the host.
How do I install Yao Agent Management Tools in Claude Code?
Run `npx skills add YaoApp/yao --skill yao-agent -a claude-code`. Or copy the skill folder (tools/skills/yao-agent in YaoApp/yao) into .claude/skills/yao-agent in your project. Claude Code loads it when a task matches its description.
How do I install Yao Agent Management Tools in Codex?
Run `npx skills add YaoApp/yao --skill yao-agent -a codex`. Or copy the skill folder (tools/skills/yao-agent in YaoApp/yao) into .agents/skills/yao-agent in your project. Codex loads it when a task matches its description.
Can I use Yao Agent Management Tools 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 YaoApp/yao --skill yao-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yao-agent, .gemini/skills/yao-agent, .github/skills/yao-agent and .opencode/skills/yao-agent in your project.
What does Yao Agent Management Tools need to run?
SKILL.md names no scripts, command-line tools or credentials: Yao Agent Management Tools is instructions for the agent only. Our summary lists: The tai CLI on the host.
Does Yao Agent Management Tools 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 Yao Agent Management Tools 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 Yao Agent Management Tools use?
Yao Agent Management Tools has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Yao Agent Management Tools use?
About 873 tokens (SKILL.md is roughly 3.5k 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 Yao Agent Management Tools?
Skills that share tags, products or a category with Yao Agent Management Tools: Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), Using Agent Skills (addyosmani/agent-skills, 103k stars), Ponytail Help Card (DietrichGebert/ponytail, 158k stars) and Skill Creator (zhayujie/CowAgent, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Yao Agent Management Tools?
YaoApp (a GitHub organization) maintains it in YaoApp/yao, which has 8,095 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 5, 2026.
Source: YaoApp/yao on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.