Find reusable skills in OpenSpace's local registry and explore its cloud library when needed. Review matching skills, choose where to import them locally, and decide whether to follow them or delegate the task.
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.
Review the instructions the agent will receive before you install.
Discover and browse skills from OpenSpace's local registry and cloud skill library.
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-agent
After setup, use cloud_browse_skills.
search_skills(query="automated deployment with rollback")
| Parameter | Required | Default | Description |
|---|---|---|---|
query | yes | — | Natural language or keywords |
limit | no | 20 | Max results |
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.
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_task
execute_task from the delegate-task skill.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Prepare audio stems, the separate parts of a track, for mixing by matching their durations with silence, loops, or crossfades. Verify each generated and processed file before moving to the next production step.
Produce audio in separate stems, meaning individual instrument tracks, and verify each output as you go. Align track lengths with silence, loops, or crossfades, then apply effects, mix a master, and package the files.
Build serverless endpoints that relay external API requests for a dashboard while keeping API keys on the server. Includes Vercel examples for input checks, caching, cross-origin access, and consistent JSON responses.
Produce a master track and separate audio parts through a structured Python workflow. Apply filters and reverb, export WAV files with consistent settings, package them in a ZIP archive, and check that the deliverables meet the requested specifications.
Keep document creation moving when web searches and page retrieval repeatedly fail. The skill preserves the original task, uses the model’s existing knowledge, and clearly identifies information that could not be checked against external sources.
When Python execution repeatedly fails in execute_code_sandbox, use a file-based alternative: save the script, run it through the shell, and capture results or errors. The guidance covers paths, imports, timeouts, structured output, and optional cleanup.