HKUDS/OpenSpace

"OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/

About the project

OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.

7.5kStars on the repository
200Mods indexed here, across every type
26d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

python-debug-pattern

121

HKUDS/OpenSpace

Skill Claude CodeCodex

Debug Python script execution failures by capturing full output with exit codes and verifying working directory before file operations.

not rated 7.5k +24 26d ago A SkillSpector: pass 23 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Fallback method for executing Python when executecodesandbox fails with unknown errors.

not rated 7.5k +24 26d ago A SkillSpector: pass 25 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Four-step recovery workflow for code execution failures when inline Python fails.

not rated 7.5k +24 26d ago A SkillSpector: pass 18 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Use shell Python heredoc as fallback when code sandbox fails.

not rated 7.5k +24 26d ago A SkillSpector: pass 18 tokens original MIT

python-shell-fallback

125

HKUDS/OpenSpace

Skill Claude CodeCodex

Fallback to shell execution when sandbox fails for library-dependent Python code.

not rated 7.5k +24 26d ago A SkillSpector: pass 17 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Workaround for executing Python code with external packages when sandbox fails.

not rated 7.5k +24 26d ago A SkillSpector: pass 17 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Systematic Python debugging workflow for spreadsheet tasks to isolate environment issues from script logic.

not rated 7.5k +24 26d ago A SkillSpector: pass 21 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Handle tool failures when researching regulatory/government content by using fallback methods and domain knowledge.

not rated 7.5k +24 26d ago A SkillSpector: pass 23 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

not rated 7.5k +24 26d ago A SkillSpector: pass 20 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Use runshell with cd and heredoc syntax for complex Excel operations when readfile fails on XLSX or executecodesandbox fails on multi-step workbook creation.

not rated 7.5k +24 26d ago A SkillSpector: pass 40 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Extract PDF text content using shell tools or Python libraries when readfile PDF handler fails.

not rated 7.5k +24 26d ago A SkillSpector: pass 27 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Use shell commands or Python libraries to extract PDF text when readfile PDF handler fails.

not rated 7.5k +24 26d ago A SkillSpector: pass 23 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Execute Python scripts reliably using file-first approach instead of heredoc.

not rated 7.5k +24 26d ago A SkillSpector: warn 18 tokens original MIT

reportlab-styles

134

HKUDS/OpenSpace

Skill Claude CodeCodex

Use reportlab's pre-defined styles from getSampleStyleSheet() correctly.

not rated 7.5k +24 26d ago A SkillSpector: pass 19 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Handle web research failures with explicit error recognition and domain-specific fallback strategies.

not rated 7.5k +24 26d ago A SkillSpector: pass 20 tokens original MIT

research-fallback

136

HKUDS/OpenSpace

Skill Claude CodeCodex

Handle web research failures by pivoting to internal knowledge for content generation.

not rated 7.5k +24 26d ago A 17 tokens copy · 88% MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Fallback pattern when primary tools fail - embed known data in scripts and persist to JSON for auditability.

not rated 7.5k +24 26d ago A SkillSpector: pass 27 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

Resilient multi-step workflow for spreadsheet processing when executecodesandbox fails, using shellagent exploration, file-based scripts, and verification steps.

not rated 7.5k +24 26d ago A SkillSpector: pass 37 tokens original MIT

robust-file-creation

139

HKUDS/OpenSpace

Skill Claude CodeCodex

Fallback to runshell and writefile when executecodesandbox or shellagent fail on filesystem operations.

not rated 7.5k +24 26d ago A SkillSpector: warn 25 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

The patch I created addresses the root cause identified in the failure context. The key fixes include.

not rated 7.5k +24 26d ago A SkillSpector: pass 0 tokens original MIT

robust-pdf-extraction

141

HKUDS/OpenSpace

Skill Claude CodeCodex

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

not rated 7.5k +24 26d ago A SkillSpector: pass 19 tokens original MIT

robust-pdf-read

142

HKUDS/OpenSpace

Skill Claude CodeCodex

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

not rated 7.5k +24 26d ago A SkillSpector: pass 23 tokens original MIT

HKUDS/OpenSpace

Skill Claude CodeCodex

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

not rated 7.5k +24 26d ago A SkillSpector: warn 35 tokens original MIT

run-shell-fallback

144

HKUDS/OpenSpace

Skill Claude CodeCodex

Use runshell with inline Python as a reliable fallback when executecodesandbox or readfile fail.

not rated 7.5k +24 26d ago A SkillSpector: pass 24 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: