github.com/HKUDS/OpenSpace
| Skill | Added | Review |
|---|---|---|
shell-agent-delegation benchmarks/gdpval/skills/shell-agent-delegation/SKILL.md Delegate complex tasks to shell_agent when direct tool execution fails, leveraging autonomous error recovery and library selection | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
shell-agent-file-ops benchmarks/gdpval/skills/shell-agent-file-ops/SKILL.md Leverage shell_agent for autonomous file creation and modification with automatic tool selection and error recovery | 57 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
shell-agent-file-workflow benchmarks/gdpval/skills/shell-agent-file-workflow/SKILL.md Delegate file generation to shell_agent when direct tools fail, with systematic file location and retrieval | 55 55 Impact — No eval scenarios have been run Securityby Medium Suggest reviewing before use Version: 3827781 | |
shell-doc-gen-and-locate benchmarks/gdpval/skills/shell-doc-gen-and-locate/SKILL.md Generate documents via shell commands and locate nested outputs using find. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
shell-error-debug-workflow benchmarks/gdpval/skills/shell-error-debug-workflow/SKILL.md Systematic workflow for diagnosing and resolving unknown errors from run_shell commands | 54 54 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Version: 3827781 | |
shell-python-fallback benchmarks/gdpval/skills/shell-python-fallback/SKILL.md Use run_shell with embedded Python heredoc as reliable fallback when code execution tools fail | 56 56 Impact — No eval scenarios have been run Securityby Medium Suggest reviewing before use Version: 3827781 | |
shell-python-heredoc benchmarks/gdpval/skills/shell-python-heredoc/SKILL.md Execute complex Python code via run_shell heredoc when execute_code_sandbox fails | 60 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
skill-discovery openspace/host_skills/skill-discovery/SKILL.md 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. | 60 60 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3827781 | |
soap-note-creation benchmarks/gdpval/skills/soap-note-creation/SKILL.md Create structured medical SOAP notes with all four components in a single comprehensive file write | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
soap-note-creation-b354d8 benchmarks/gdpval/skills/soap-note-creation-b354d8/SKILL.md Create structured medical SOAP notes by writing comprehensive content to a file in one iteration | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-audit-edit-validate benchmarks/gdpval/skills/spreadsheet-audit-edit-validate/SKILL.md Safely update Excel workbooks by first locating candidate files, verifying workbook structure before editing, and running post-write validation against required sheets, populated columns, and sample counts. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-create-verify-gate benchmarks/gdpval/skills/spreadsheet-proof-gate-merged-fedf41/SKILL.md Create or edit Excel workbooks with openpyxl-specific pitfall handling, anchored preflight audit, and deterministic post-write proof that every criterion is satisfied | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-direct-python benchmarks/gdpval/skills/spreadsheet-direct-python/SKILL.md Use direct Python execution for reliable spreadsheet operations instead of shell_agent | 51 51 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-direct-verification benchmarks/gdpval/skills/spreadsheet-direct-verification/SKILL.md Use a deterministic Python/openpyxl inspection pass to verify workbook structure, counts, marked rows, and output-file existence when delegated spreadsheet summaries seem inconsistent. | 67 67 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-proof-gate benchmarks/gdpval/skills/spreadsheet-audit-edit-validate-merged/SKILL.md Edit Excel workbooks only after anchored preflight audit, then require deterministic Python/openpyxl post-write proof that every requested criterion is satisfied or explicitly reconciled before finalizing. | 62 62 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-python-file-exec benchmarks/gdpval/skills/spreadsheet-direct-python-enhanced/SKILL.md Execute Python scripts from files for reliable spreadsheet operations, avoiding heredoc issues with shell_agent | 52 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-source-validated benchmarks/gdpval/skills/spreadsheet-direct-python-enhanced-enhanced-2e6773/SKILL.md Execute Python scripts for spreadsheet operations with mandatory source data validation and fallback protocols | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-struct-verified benchmarks/gdpval/skills/spreadsheet-audit-edit-validate-enhanced/SKILL.md Create and modify Excel workbooks with mandatory deterministic Python verification of workbook structure, required sheets, populated columns, and sample counts before reporting completion. | 60 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
spreadsheet-validated-exec benchmarks/gdpval/skills/spreadsheet-direct-python-enhanced-enhanced-f0b1db/SKILL.md Execute Python scripts for spreadsheets with prerequisite data validation and source accessibility checks | 53 53 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
ssl-proxy-debug-workflow benchmarks/gdpval/skills/ssl-proxy-debug-workflow/SKILL.md Systematic debugging workflow for SSL/proxy connectivity issues with government and institutional websites | 53 53 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Version: 3827781 |