Updated 2mo ago
by HKUDS
OpenSpace
"OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/
7.8k GitHub stars (7,757)
+17 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | +1 |
| Oct 3 | −2 |
| Oct 4 | +2 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | +1 |
| Oct 8 | +6 |
| Oct 9 | +2 |
| Oct 10 | +3 |
| Oct 11 | +3 |
| Oct 12 | 0 |
| Oct 13 | −1 |
| Oct 14 | 0 |
| Oct 15 | +1 |
| Oct 16 | +1 |
- 28 skills (28 skills found in its SKILL.md files)
- 925 forks (925 forks)
- 2mo ago last update (Last updated 2mo ago)
Install
Skills CLI
npx skills add HKUDS/OpenSpace
Asks which skills and agents to install. Just one: npx skills add HKUDS/OpenSpace --skill delegate-task — add -g for every project.
Claude Code
git clone https://github.com/HKUDS/OpenSpacecp -r "OpenSpace/openspace/host_skills/delegate-task" ~/.claude/skills/
Copies the delegate-task skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add HKUDS/OpenSpace
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 28 of 265 files.
-
delegate-task
Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.
openspace/host_skills/delegate-task/SKILL.md on GitHub (opens in a new tab) -
skill-discovery
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.
openspace/host_skills/skill-discovery/SKILL.md on GitHub (opens in a new tab) -
remember
Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.
openspace/skills/remember/SKILL.md on GitHub (opens in a new tab) -
adaptive-stem-alignment
Incremental audio production with duration mismatch handling, adaptive stem extension, and pre-mix alignment verification
benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced-b8f537/SKILL.md on GitHub (opens in a new tab) -
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow
benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced-enhanced/SKILL.md on GitHub (opens in a new tab) -
aligned-stem-workflow
Incremental audio production with duration alignment handling, per-stem verification, and adaptive extension strategies
benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced/SKILL.md on GitHub (opens in a new tab) -
incremental-audio-workflow
Step-by-step audio production with per-stem verification, timing alignment, and incremental quality gates
benchmarks/gdpval/skills/audio-track-production-enhanced/SKILL.md on GitHub (opens in a new tab) -
audio-track-production
End-to-end audio production workflow with stems, effects, archiving, and verification
benchmarks/gdpval/skills/audio-track-production/SKILL.md on GitHub (opens in a new tab) -
cascade-fail-recovery
Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
benchmarks/gdpval/skills/cascade-fail-recovery/SKILL.md on GitHub (opens in a new tab) -
code-exec-fallback-266cba
Fallback workflow for reliable code execution when sandbox fails repeatedly
benchmarks/gdpval/skills/code-exec-fallback-266cba/SKILL.md on GitHub (opens in a new tab) -
code-exec-fallback
Fallback pattern for executing Python code when execute_code_sandbox fails
benchmarks/gdpval/skills/code-exec-fallback/SKILL.md on GitHub (opens in a new tab) -
code-execution-fallback-e81068
Fallback workflow for executing Python code when execute_code_sandbox fails repeatedly
benchmarks/gdpval/skills/code-execution-fallback-e81068/SKILL.md on GitHub (opens in a new tab) -
code-execution-fallback
Handle code execution failures with fallback strategies and anchored workspace paths
benchmarks/gdpval/skills/code-execution-fallback/SKILL.md on GitHub (opens in a new tab) -
comprehensive-soap-note
Generate complete medical SOAP notes with all four sections in a single comprehensive file write operation
benchmarks/gdpval/skills/create-soap-note-merged/SKILL.md on GitHub (opens in a new tab) -
create-soap-note
Generate structured medical SOAP notes with all required sections in a single comprehensive file write.
benchmarks/gdpval/skills/create-soap-note/SKILL.md on GitHub (opens in a new tab) -
debug-sandbox-execution
Debug Python code execution failures by capturing partial traces, isolating failing functions, and incrementally verifying outputs
benchmarks/gdpval/skills/debug-sandbox-execution/SKILL.md on GitHub (opens in a new tab) -
delegated-file-edit-verification
Verify delegated file-edit results directly in the target workspace before accepting success, and rerun with absolute paths if the delegate's report conflicts with reality.
benchmarks/gdpval/skills/delegated-file-edit-verification/SKILL.md on GitHub (opens in a new tab) -
deliverable-completion
Clarifies that file creation tasks are complete when the deliverable is successfully written—no submission step required
benchmarks/gdpval/skills/deliverable-completion/SKILL.md on GitHub (opens in a new tab) -
detect-zero-iteration-failure
Identify and classify agent failures occurring before execution starts
benchmarks/gdpval/skills/detect-zero-iteration-failure/SKILL.md on GitHub (opens in a new tab) -
detect-zero-iteration-failures
Identify and handle pre-execution agent failures occurring before any iterations or tool usage
benchmarks/gdpval/skills/detect-zero-iteration-failures/SKILL.md on GitHub (opens in a new tab) -
direct-reportlab-pdf-generation
Generate complex multi-page PDFs by running reportlab Python code directly via run_shell when shell_agent fails on document creation
benchmarks/gdpval/skills/direct-reportlab-pdf-generation/SKILL.md on GitHub (opens in a new tab) -
document-gen-resilient-workflow
Multi-engine document generation with cascading PDF fallbacks and robust Unicode handling
benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-2794b4/SKILL.md on GitHub (opens in a new tab) -
doc-gen-unicode-diagnostic
Systematic document generation with unicode sanitization, engine fallback chain, and explicit error diagnosis
benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-3d3a9a/SKILL.md on GitHub (opens in a new tab) -
document-gen-resilient-multiformat
Resilient multi-format document generation with environment checks, auto-sanitization, and fallback engines
benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-618c9b/SKILL.md on GitHub (opens in a new tab) -
document-gen-resilient
Multi-path document generation with tool checks, Unicode handling, and Python fallbacks
benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-96865f/SKILL.md on GitHub (opens in a new tab) -
document-gen-dual-backend
Document generation with direct pandoc/ReportLab execution (lightweight default) and optional shell_agent fallback for complex scenarios
benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-9f3b1f/SKILL.md on GitHub (opens in a new tab) -
document-gen-unicode-safe
Unicode-safe fallback workflow for multi-format document generation with character sanitization
benchmarks/gdpval/skills/document-gen-fallback-enhanced-enhanced-c5d426/SKILL.md on GitHub (opens in a new tab) -
resilient-document-pipeline
Unified document generation with tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety
benchmarks/gdpval/skills/document-gen-fallback-enhanced-merged/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.