Skill collection
HKUDS/OpenSpace agent skills
- skills
- 199
- GitHub stars
- 7.7k
GitHub description: “"OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/”
- Stars
- 7,749 (923 forks)
- Licence
- MIT
- Last push
- Aug 2026
- Created
- Mar 2026
Install all skills
npx skills add HKUDS/OpenSpaceAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in HKUDS/OpenSpace, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification. | HKUDS/ | 7.7k | — | ~2.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 2 | Handle cascading data retrieval tool failures by falling back to embedded knowledge generation | HKUDS/ | 7.7k | — | ~765 | Automated safety check: Pass | MIT | 1 mo ago |
| 3 | Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead. | HKUDS/ | 7.7k | — | ~588 | Automated safety check: Pass | MIT | 1 mo ago |
| 4 | A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output. | HKUDS/ | 7.7k | — | ~652 | Automated safety check: Pass | MIT | 1 mo ago |
| 5 | Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place. | HKUDS/ | 7.7k | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 6 | Fallback workflow for executing Python code when executecodesandbox fails repeatedly | HKUDS/ | 7.7k | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 7 | Generate documents with writefile when retrieval tools fail, with explicit guardrails against task context drift | HKUDS/ | 7.7k | — | ~2.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 8 | Debug Python code execution failures by capturing partial traces, isolating failing functions, and incrementally verifying outputs | HKUDS/ | 7.7k | — | ~843 | Automated safety check: Pass | MIT | 1 mo ago |
| 9 | 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. | HKUDS/ | 7.7k | — | ~2.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 10 | 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. | HKUDS/ | 7.7k | — | ~2.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 11 | Clarifies that file creation tasks are complete when the deliverable is successfully written—no submission step required | HKUDS/ | 7.7k | — | ~731 | Automated safety check: Pass | MIT | 1 mo ago |
| 12 | Identify and classify agent failures occurring before execution starts | HKUDS/ | 7.7k | — | ~477 | Automated safety check: Pass | MIT | 1 mo ago |
| 13 | Identify and handle pre-execution agent failures occurring before any iterations or tool usage | HKUDS/ | 7.7k | — | ~1.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 14 | Generate complex multi-page PDFs by running reportlab Python code directly via runshell when shellagent fails on document creation | HKUDS/ | 7.7k | — | ~1.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 15 | Systematic document generation with unicode sanitization, engine fallback chain, and explicit error diagnosis | HKUDS/ | 7.7k | — | ~2.7k | Automated safety check: Pass | MIT | 1 mo ago |
| 16 | Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports | HKUDS/ | 7.7k | — | ~2.7k | Automated safety check: Pass | MIT | 1 mo ago |
| 17 | Document generation with direct pandoc/ReportLab execution (lightweight default) and optional shellagent fallback for complex scenarios | HKUDS/ | 7.7k | — | ~4.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 18 | Fallback workflow for multi-format document generation when shellagent encounters errors | HKUDS/ | 7.7k | — | ~917 | Automated safety check: Pass | MIT | 1 mo ago |
| 19 | Multi-path document generation with tool checks, Unicode handling, and Python fallbacks | HKUDS/ | 7.7k | — | ~3.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 20 | Resilient multi-format document generation with environment checks, auto-sanitization, and fallback engines | HKUDS/ | 7.7k | — | ~3.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 21 | Multi-engine document generation with cascading PDF fallbacks and robust Unicode handling | HKUDS/ | 7.7k | — | ~3k | Automated safety check: Pass | MIT | 1 mo ago |
| 22 | Robust document generation with engine fallback chain, error diagnostics, and Python alternatives | HKUDS/ | 7.7k | — | ~3.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 23 | Unicode-safe fallback workflow for multi-format document generation with character sanitization | HKUDS/ | 7.7k | — | ~3k | Automated safety check: Pass | MIT | 1 mo ago |
| 24 | Unicode-safe fallback workflow for multi-format document generation with character sanitization and explicit error capture | HKUDS/ | 7.7k | — | ~2.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 25 | Use direct Python execution for reliable spreadsheet and document/PDF generation operations | HKUDS/ | 7.7k | — | ~2.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 26 | Use direct Python execution for reliable spreadsheet and document/PDF generation operations | HKUDS/ | 7.7k | — | ~2.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 27 | Extract text from DOCX files using shell or Python zipfile, with environment-aware fallback | HKUDS/ | 7.7k | — | ~1.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 28 | Extract text from DOCX files with shell-primary approach and Python zipfile fallback for maximum reliability | HKUDS/ | 7.7k | — | ~1.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 29 | Use runshell with python-docx as reliable fallback when readfile fails on .docx files | HKUDS/ | 7.7k | — | ~555 | Automated safety check: Pass | MIT | 1 mo ago |
| 30 | Extract text from DOCX files using shell commands when python-docx is unavailable | HKUDS/ | 7.7k | — | ~659 | Automated safety check: Pass | MIT | 1 mo ago |
| 31 | Extract text from DOCX files using shell commands when python-docx is unavailable | HKUDS/ | 7.7k | — | ~633 | Automated safety check: Pass | MIT | 1 mo ago |
| 32 | Handle docx files using shell-based XML extraction and python-docx via runshell when standard tools fail | HKUDS/ | 7.7k | — | ~1.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 33 | Use shellagent as fallback when executecodesandbox fails for Excel file operations | HKUDS/ | 7.7k | — | ~921 | Automated safety check: Pass | MIT | 1 mo ago |
| 34 | Iteratively debug Excel structure with exploratory scripts before writing extraction logic | HKUDS/ | 7.7k | — | ~1.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 35 | Create Excel files with openpyxl by falling back to shell-based Python heredoc when sandbox execution fails | HKUDS/ | 7.7k | — | ~1.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 36 | Create Excel files with openpyxl by falling back to runshell with inline Python heredoc when executecodesandbox fails | HKUDS/ | 7.7k | — | ~1.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 37 | Audit generated Excel reports by enumerating populated output rows, exposing formulas, and checking that each subtotal range includes all visible detail rows. | HKUDS/ | 7.7k | — | ~3.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 38 | Unmerge merged cells in openpyxl worksheets before writing values to avoid AttributeError | HKUDS/ | 7.7k | — | ~820 | Automated safety check: Pass | MIT | 1 mo ago |
| 39 | Fallback from executecodesandbox to runshell when e2b sandbox is unavailable | HKUDS/ | 7.7k | — | ~1k | Automated safety check: Pass | MIT | 1 mo ago |
| 40 | Fallback workflow for running code via file write and shell when sandbox execution fails | HKUDS/ | 7.7k | — | ~763 | Automated safety check: Pass | MIT | 1 mo ago |
| 41 | Generate professional documents after tool failures using shellagent for complex formats or writefile for simple text/markdown | HKUDS/ | 7.7k | — | ~2.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 42 | Fallback pattern for reliable file creation when code execution tools fail | HKUDS/ | 7.7k | — | ~1k | Automated safety check: Pass | MIT | 1 mo ago |
| 43 | Use runshell as fallback when executecodesandbox or shellagent fail on filesystem operations | HKUDS/ | 7.7k | — | ~718 | Automated safety check: Pass | MIT | 1 mo ago |
| 44 | Reliable Python execution workflow when executecodesandbox or shellagent fail | HKUDS/ | 7.7k | — | ~676 | Automated safety check: Pass | MIT | 1 mo ago |
| 45 | Use runshell with Python heredoc when executecodesandbox or readfile fail | HKUDS/ | 7.7k | — | ~1k | Automated safety check: Pass | MIT | 1 mo ago |
| 46 | Two-step script execution workflow for debugging when shellagent and executecodesandbox consistently fail | HKUDS/ | 7.7k | — | ~898 | Automated safety check: Pass | MIT | 1 mo ago |
| 47 | Check FFmpeg encoder availability before video encoding to avoid library mismatches | HKUDS/ | 7.7k | — | ~894 | Automated safety check: Pass | MIT | 1 mo ago |
| 48 | Check available FFmpeg encoders before writing encoding scripts to avoid library version mismatches | HKUDS/ | 7.7k | — | ~615 | Automated safety check: Pass | MIT | 1 mo ago |
Questions, answered from the data.
What is the best skill in HKUDS/OpenSpace?
Audio Track Production Workflow from HKUDS/OpenSpace ranks first of the 199 skills in HKUDS/OpenSpace listed here, with the highest score: its repository has 7.7k GitHub stars, its SKILL.md loads about 2.9k tokens and it passes the automated safety check with no findings. Next come Cascade Failure Recovery and Sandbox Code Execution Fallback.
Are the skills in HKUDS/OpenSpace official?
None yet. All 199 skills in HKUDS/OpenSpace listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from HKUDS/OpenSpace?
Run npx skills add HKUDS/OpenSpace in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.