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.
Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help.
Install Skill Discovery
$ npx skills add HKUDS/OpenSpace --skill skill-discovery -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/OpenSpace skill-discovery --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/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/openspace/host_skills/skill-discovery .claude/skills/skill-discovery && 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 "skill-discovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/openspace/host_skills/skill-discovery into .claude/skills/skill-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-discovery", 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/HKUDS/OpenSpace/tree/main/openspace/host_skills/skill-discoveryType 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 HKUDS/OpenSpace --skill skill-discovery -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/OpenSpace skill-discovery --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/openspace/host_skills/skill-discovery .agents/skills/skill-discovery && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-discovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/openspace/host_skills/skill-discovery into .agents/skills/skill-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-discovery", 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 HKUDS/OpenSpace --skill skill-discovery -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/OpenSpace skill-discovery --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/openspace/host_skills/skill-discovery .cursor/skills/skill-discovery && 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 "skill-discovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/openspace/host_skills/skill-discovery into .cursor/skills/skill-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-discovery", 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/HKUDS/OpenSpace.git --path openspace/host_skills/skill-discovery--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 HKUDS/OpenSpace --skill skill-discovery -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/OpenSpace skill-discovery --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/openspace/host_skills/skill-discovery .gemini/skills/skill-discovery && 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 "skill-discovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/openspace/host_skills/skill-discovery into .gemini/skills/skill-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-discovery", 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 HKUDS/OpenSpace skill-discoveryInstalls 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 HKUDS/OpenSpace --skill skill-discovery -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/openspace/host_skills/skill-discovery .github/skills/skill-discovery && 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 "skill-discovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/openspace/host_skills/skill-discovery into .github/skills/skill-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-discovery", 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 HKUDS/OpenSpace --skill skill-discovery -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HKUDS/OpenSpace skill-discovery --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/openspace/host_skills/skill-discovery .opencode/skills/skill-discovery && 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 "skill-discovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/openspace/host_skills/skill-discovery into .opencode/skills/skill-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-discovery", 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
skill-discovery- GitHub stars
- 7.8k
- Token cost
- ~871 tokens
- SKILL.md length
- 300 words
- Files
- 2
- Skills in repo
- 199
- Repo updated
- First seen
- Licence
- MIT
At a glance
Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help.
- Tasks that involve Skill management
- SKILL.md covers When to use, Cloud access, search_skills and cloud_browse_skills, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Skill Discovery is an agent skill from HKUDS/OpenSpace. Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.
Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.
It sits in Agent Workflows, covering Skill management. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.
When your agent uses it
- Tasks that involve Skill management
Example prompts
- “/skill-discovery”
What it can do on your machine
Read from SKILL.md and the folder at commit 3827781. 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
Skill Discovery loads about 871 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 300 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
The full file from HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 300 words, ~871 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-discovery/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- skill-discovery
- description
- Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.
Skill Discovery
Discover and browse skills from OpenSpace's local registry and cloud skill library.
When to use
- User asks "what skills are available?" or "is there a skill for X?"
- You encounter an unfamiliar task — a proven skill can save significant tokens over trial-and-error
- You need to decide: handle a task yourself, or delegate to OpenSpace
Cloud access
search_skills is local-only. If the user wants cloud results, or a cloud operation reports a missing/invalid key, set up cloud access first and use cloud_browse_skills.
Ask for email and agent_name. Ask for password only through secure secret input; it must be 8 to 72 characters. Do not ask for passcode/OTP because cloud_auth_flow does not accept one.
cloud_auth_flow(action="bootstrap_agent_key", email="user@example.com", password="<secure-password>", agent_name="openspace-local-agent")If secure password input is not available, ask the user to run:
openspace-cloud-auth bootstrap-agent-key --email user@example.com --agent-name openspace-local-agentAfter setup, use cloud_browse_skills.
search_skills
search_skills(query="automated deployment with rollback")| Parameter | Required | Default | Description |
|---|---|---|---|
query | yes | — | Natural language or keywords |
limit | no | 20 | Max results |
cloud_browse_skills
Use this single cloud tool when local search is not enough. Continue calling
the same tool with the returned next_actions[].action.
cloud_browse_skills(action="search_skills", query="automated deployment with rollback")
cloud_browse_skills(action="local_placement", query="automated deployment with rollback")
cloud_browse_skills(action="local_placement", local_category_path="technology/computing/deployment")
cloud_browse_skills(action="import_skill", cloud_skill_id="<cloud_skill_id>", local_category_path="technology/computing/deployment/rollback")Use recall and pull_projection only when you need package discovery or
package outlines before choosing a skill. Concrete skill search should start
with search_skills.
Choose local_category_path for the user's local package taxonomy. It uses the
same shape as cloud package paths, but is stored independently and may be more
specific than the current cloud tree. Use local_placement to inspect existing
paths and create a nearby child path before importing.
After search
Results are returned to you (not executed). Cloud imports return a local_path after cloud_browse_skills(action="import_skill", ...).
Found a matching skill?
├── YES, and I can follow it myself
│ → read SKILL.md at local_path, follow the instructions
├── YES, but I lack the capability
│ → delegate via execute_task (see delegate-task skill)
└── NO match
→ handle it yourself, or delegate via execute_taskNotes
- This is for discovery — you see results and decide. For direct execution, use
execute_taskfrom thedelegate-taskskill. - Cloud skills have been evolved through real use — more reliable than skills written from scratch.
- Always tell the user what you found (or didn't find) and what you recommend.
© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in openspace/host_skills/skill-discovery of HKUDS/OpenSpace.
- SKILL.md
- .skill_id
Open the folder on GitHubat commit 3827781
Compare with similar skills
Skill Discovery 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 |
|---|---|---|---|---|---|---|
| Skill Discovery this skillHKUDS/OpenSpace | 7.8k | — | ~871 | Automated safety check: Pass | MIT | |
| 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 | 159k | — | ~726 | 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.
Skill Stocktake
affaan-m/ECC
Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.
More from HKUDS/OpenSpace
All 199 skills in this repoAudio Track Production Workflow
HKUDS/OpenSpace
Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.
Cascade Failure Recovery
HKUDS/OpenSpace
Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
Sandbox Code Execution Fallback
HKUDS/OpenSpace
Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.
Code Execution Fallback
HKUDS/OpenSpace
A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.
Code Execution Fallback and Path Anchoring
HKUDS/OpenSpace
Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.
Code Execution Fallback E81068
HKUDS/OpenSpace
Fallback workflow for executing Python code when executecodesandbox fails repeatedly
Related
Categories
Questions about Skill Discovery
What does Skill Discovery do?
Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Skill Discovery is an agent skill from HKUDS/OpenSpace. Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help.
When should I use Skill Discovery?
Skill Discovery fits situations like: tasks that involve Skill management.
How do I install Skill Discovery in Claude Code?
Run `npx skills add HKUDS/OpenSpace --skill skill-discovery -a claude-code`. Or copy the skill folder (openspace/host_skills/skill-discovery in HKUDS/OpenSpace) into .claude/skills/skill-discovery in your project. Claude Code loads it when a task matches its description.
How do I install Skill Discovery in Codex?
Run `npx skills add HKUDS/OpenSpace --skill skill-discovery -a codex`. Or copy the skill folder (openspace/host_skills/skill-discovery in HKUDS/OpenSpace) into .agents/skills/skill-discovery in your project. Codex loads it when a task matches its description.
Can I use Skill Discovery 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 HKUDS/OpenSpace --skill skill-discovery -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-discovery, .gemini/skills/skill-discovery, .github/skills/skill-discovery and .opencode/skills/skill-discovery in your project.
What does Skill Discovery need to run?
SKILL.md names no scripts, command-line tools or credentials: Skill Discovery is instructions for the agent only.
Does Skill Discovery 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 Discovery 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 Discovery use?
Skill Discovery 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 Discovery use?
About 871 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 Skill Discovery?
Skills that share tags, products or a category with Skill Discovery: Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), Using Agent Skills (addyosmani/agent-skills, 103k stars), Ponytail Help Card (DietrichGebert/ponytail, 159k 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 Skill Discovery?
HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,750 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.
Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.