github.com/HKUDS/OpenSpace
| Skill | Added | Review |
|---|---|---|
adaptive-stem-alignment benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced-b8f537/SKILL.md Incremental audio production with duration mismatch handling, adaptive stem extension, and pre-mix alignment verification | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
adaptive-stem-alignment openspace/benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced-b8f537/SKILL.md Incremental audio production with duration mismatch handling, adaptive stem extension, and pre-mix alignment verification | 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e5a81e7 | |
agentpilot agentpilot/src/agentpilot/host/skills/agentpilot/SKILL.md Prepare and run AgentPilot improvements through one entry. Use when the user requests AgentPilot or iterative improvement with it. The current agent fills missing task/evaluation inputs, then hands a ready environment to the configured AgentPilot runner. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e5a81e7 | |
aligned-stem-workflow benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced/SKILL.md Incremental audio production with duration alignment handling, per-stem verification, and adaptive extension strategies | 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
aligned-stem-workflow openspace/benchmarks/gdpval/skills/audio-track-production-enhanced-enhanced/SKILL.md Incremental audio production with duration alignment handling, per-stem verification, and adaptive extension strategies | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e5a81e7 | |
audio-track-production benchmarks/gdpval/skills/audio-track-production/SKILL.md End-to-end audio production workflow with stems, effects, archiving, and verification | 51 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
audio-track-production openspace/benchmarks/gdpval/skills/audio-track-production/SKILL.md End-to-end audio production workflow with stems, effects, archiving, and verification | 53 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: e5a81e7 | |
cascade-fail-recovery benchmarks/gdpval/skills/cascade-fail-recovery/SKILL.md Handle cascading data retrieval tool failures by falling back to embedded knowledge generation | 49 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
code-exec-fallback benchmarks/gdpval/skills/code-exec-fallback/SKILL.md Fallback pattern for executing Python code when execute_code_sandbox fails | 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
code-exec-fallback-266cba benchmarks/gdpval/skills/code-exec-fallback-266cba/SKILL.md Fallback workflow for reliable code execution when sandbox fails repeatedly | 56 Impact — No eval scenarios have been run Securityby Critical Do not install without reviewing Version: 3827781 | |
code-execution-fallback benchmarks/gdpval/skills/code-execution-fallback/SKILL.md Handle code execution failures with fallback strategies and anchored workspace paths | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
code-execution-fallback-e81068 benchmarks/gdpval/skills/code-execution-fallback-e81068/SKILL.md Fallback workflow for executing Python code when execute_code_sandbox fails repeatedly | 59 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
comprehensive-soap-note benchmarks/gdpval/skills/create-soap-note-merged/SKILL.md Generate complete medical SOAP notes with all four sections in a single comprehensive file write operation | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
context-anchored-fallback-report benchmarks/gdpval/skills/write-file-fallback-report-enhanced-4bc5c2/SKILL.md Generate documents with write_file when retrieval tools fail, with explicit guardrails against task context drift | 48 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
create-soap-note benchmarks/gdpval/skills/create-soap-note/SKILL.md Generate structured medical SOAP notes with all required sections in a single comprehensive file write. | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
debug-sandbox-execution benchmarks/gdpval/skills/debug-sandbox-execution/SKILL.md Debug Python code execution failures by capturing partial traces, isolating failing functions, and incrementally verifying outputs | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
delegated-file-edit-verification benchmarks/gdpval/skills/delegated-file-edit-verification/SKILL.md 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. | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
delegate-task openspace/host_skills/delegate-task/SKILL.md 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. | 63 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
deliverable-completion benchmarks/gdpval/skills/deliverable-completion/SKILL.md Clarifies that file creation tasks are complete when the deliverable is successfully written—no submission step required | 50 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
detect-zero-iteration-failure benchmarks/gdpval/skills/detect-zero-iteration-failure/SKILL.md Identify and classify agent failures occurring before execution starts | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 |