OpenSpace
github.com/HKUDS/OpenSpace
| Skill | Added | Review |
|---|---|---|
python-heredoc-fallback benchmarks/gdpval/skills/python-heredoc-fallback/SKILL.md Use shell Python heredoc as fallback when code sandbox fails | 58 58 Impact — No eval scenarios have been run Securityby  Passed No findings from the security scan Version: 3827781 | |
python-shell-fallback benchmarks/gdpval/skills/python-shell-fallback/SKILL.md Fallback to shell execution when sandbox fails for library-dependent Python code | 55 55 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
python-shell-workaround benchmarks/gdpval/skills/python-shell-workaround/SKILL.md Workaround for executing Python code with external packages when sandbox fails | 57 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
python-spreadsheet-debug benchmarks/gdpval/skills/python-spreadsheet-debug/SKILL.md Systematic Python debugging workflow for spreadsheet tasks to isolate environment issues from script logic | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
regulatory-fallback-research benchmarks/gdpval/skills/regulatory-fallback-research/SKILL.md Handle tool failures when researching regulatory/government content by using fallback methods and domain knowledge | 50 50 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3827781 | |
regulatory-research-fallback benchmarks/gdpval/skills/regulatory-research-fallback/SKILL.md Fallback workflow for regulatory research when web extraction tools fail on government PDFs | 55 55 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3827781 | |
reliable-excel-workbook-creation benchmarks/gdpval/skills/reliable-excel-workbook-creation/SKILL.md Use run_shell with cd and heredoc syntax for complex Excel operations when read_file fails on XLSX or execute_code_sandbox fails on multi-step workbook creation | 57 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
reliable-pdf-extraction benchmarks/gdpval/skills/reliable-pdf-extraction/SKILL.md Use shell commands or Python libraries to extract PDF text when read_file PDF handler fails | 61 61 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3827781 | |
reliable-pdf-extraction-ac5f89 benchmarks/gdpval/skills/reliable-pdf-extraction-ac5f89/SKILL.md Extract PDF text content using shell tools or Python libraries when read_file PDF handler fails | 60 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
reliable-script-execution benchmarks/gdpval/skills/reliable-script-execution/SKILL.md Execute Python scripts reliably using file-first approach instead of heredoc | 55 55 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
remember openspace/skills/remember/SKILL.md 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. | 61 61 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
reportlab-styles benchmarks/gdpval/skills/reportlab-styles/SKILL.md Use reportlab's pre-defined styles from getSampleStyleSheet() correctly | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
research-fallback benchmarks/gdpval/skills/research-fallback/SKILL.md Handle web research failures by pivoting to internal knowledge for content generation | 49 49 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
research-fallback-robust benchmarks/gdpval/skills/research-fallback-enhanced/SKILL.md Handle web research failures with explicit error recognition and domain-specific fallback strategies | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
resilient-context-extraction benchmarks/gdpval/skills/prioritize-context-data-enhanced/SKILL.md Ensures agents extract data from context files with validation and fallback strategies before resorting to assumptions or external searches. | 46 46 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
resilient-data-gathering benchmarks/gdpval/skills/resilient-data-gathering/SKILL.md Fallback pattern when primary tools fail - embed known data in scripts and persist to JSON for auditability | 51 51 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
resilient-document-pipeline benchmarks/gdpval/skills/document-gen-fallback-enhanced-merged/SKILL.md Unified document generation with tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety | 53 53 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
resilient-research-workflow benchmarks/gdpval/skills/spreadsheet-proof-gate-merged/SKILL.md Unified workflow that delegates failed web searches to shell_agent for resilient data gathering, then applies anchored spreadsheet proof gates for verified Excel output | 59 59 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3827781 | |
resilient-spreadsheet-workflow benchmarks/gdpval/skills/resilient-spreadsheet-workflow/SKILL.md Resilient multi-step workflow for spreadsheet processing when execute_code_sandbox fails, using shell_agent exploration, file-based scripts, and verification steps | 62 62 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 | |
robust-file-creation benchmarks/gdpval/skills/robust-file-creation/SKILL.md Fallback to run_shell and write_file when execute_code_sandbox or shell_agent fail on filesystem operations | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3827781 |