CtrlK
BlogDocsLog inGet started
Tessl Logo

OpenSpace

github.com/HKUDS/OpenSpace

SkillAddedReview
robust-pdf-extraction

benchmarks/gdpval/skills/robust-pdf-extraction/SKILL.md

Multi-method PDF extraction with sequential fallback and OCR for scanned documents

54

robust-pdf-read

benchmarks/gdpval/skills/robust-pdf-read/SKILL.md

Reliably extract text from PDFs using pdftotext when standard file reading fails.

55

route-failed-searches-to-shell-agent

benchmarks/gdpval/skills/route-failed-searches-to-shell-agent/SKILL.md

Delegate web search tasks to shell_agent when direct search_web tool fails, using its retry mechanism and multi-step capabilities for resilient data gathering

57

run-shell-fallback

benchmarks/gdpval/skills/run-shell-fallback/SKILL.md

Use run_shell with inline Python as a reliable fallback when execute_code_sandbox or read_file fail

55

run-shell-python-file-io

benchmarks/gdpval/skills/run-shell-python-file-io/SKILL.md

Use run_shell with inline Python for reliable file I/O when execute_code_sandbox cannot access working directory files

59

safe-script-execution

benchmarks/gdpval/skills/safe-script-execution/SKILL.md

Fallback workflow for code execution when automated tools fail, using shell heredoc with verification

61

safe-video-concat-workflow

benchmarks/gdpval/skills/safe-video-concat-workflow/SKILL.md

Two-pass video concatenation workflow that avoids encoder compatibility issues by separating concat and audio mixing

57

sandbox-exec-fallback

benchmarks/gdpval/skills/sandbox-exec-fallback/SKILL.md

Fallback pattern for executing Python code when execute_code_sandbox fails by writing to file and running via shell

58

sandbox-execution-fallback

benchmarks/gdpval/skills/sandbox-execution-fallback/SKILL.md

Recover from execute_code_sandbox failures by writing Python scripts to files and executing via run_shell

58

sandbox-execution-fallback-238489

benchmarks/gdpval/skills/sandbox-execution-fallback-238489/SKILL.md

Fallback pattern for when execute_code_sandbox fails - write script to file and execute directly with run_shell

58

sandbox-execution-fallback-717e65

benchmarks/gdpval/skills/sandbox-execution-fallback-717e65/SKILL.md

Fallback from execute_code_sandbox to file-based run_shell execution when sandbox fails

58

sandbox-failure-recovery

benchmarks/gdpval/skills/sandbox-failure-recovery/SKILL.md

Recover from execute_code_sandbox failures by writing code to file and executing via run_shell

56

sandbox-fallback-execution

benchmarks/gdpval/skills/sandbox-fallback-execution/SKILL.md

Fallback workflow for executing Python code when execute_code_sandbox fails

60

sandbox-fallback-execution-048d5a

benchmarks/gdpval/skills/sandbox-fallback-execution-048d5a/SKILL.md

Fallback method to execute Python code when execute_code_sandbox fails with e2b errors

65

sandbox-fallback-execution-5eda7b

benchmarks/gdpval/skills/sandbox-fallback-execution-5eda7b/SKILL.md

Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell

48

sandbox-fallback-python

benchmarks/gdpval/skills/sandbox-fallback-python/SKILL.md

Fallback to run_shell with embedded Python when execute_code_sandbox fails due to e2b unavailability

58

sandbox-fallback-python-e5d7ae

benchmarks/gdpval/skills/sandbox-fallback-python-e5d7ae/SKILL.md

Fallback to run_shell with Python heredoc when execute_code_sandbox fails

57

sandbox-file-discovery-and-validation

benchmarks/gdpval/skills/sandbox-file-discovery-and-validation/SKILL.md

Use shell tools safely in sandboxed environments by discovering files from real workspace roots instead of assumed user folders, then explicitly verifying output artifacts after generation.

60

search-fail-pivot

benchmarks/gdpval/skills/search-fail-pivot/SKILL.md

Heuristic for detecting search tool failures and pivoting to domain knowledge for document generation

50

search-fallback-workflow

benchmarks/gdpval/skills/search-fallback-workflow/SKILL.md

Graceful degradation workflow for continuing tasks when web search tools fail, using internal knowledge with verification caveats

48