Repository
Zedong-Liu/SparseReading agent skills
- skills
- 2
- GitHub stars
- 242
GitHub description: “SparseRead: token-efficient reading for AI agents. 读得更少，token 更省，证据不变。 Paper arXiv:2608.22237”
- Stars
- 242 (11 forks)
- Licence
- MIT
- Last push
- Sep 2026
- Created
- May 2026
- ai-agents
- claude-code
- context-management
- llm
- opencode
- python
- typescript
Install all skills
npx skills add Zedong-Liu/SparseReadingAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in Zedong-Liu/SparseReading, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Use SparseRead for long documents, PDFs, and compact multi-file evidence closures without disrupting small native reads. | Zedong-Liu/ | 242 | — | ~437 | Automated safety check: Pass | MIT | 10 days ago |
| 2 | Use SparseRead tools to inspect large, structured, or multi-file project inputs with targeted evidence. | Zedong-Liu/ | 242 | — | ~278 | Automated safety check: Pass | MIT | 10 days ago |
Questions, answered from the data.
What is the best skill in Zedong-Liu/SparseReading?
Sparse Reading from Zedong-Liu/SparseReading ranks first of the 2 skills in Zedong-Liu/SparseReading listed here, with the highest score: its repository has 242 GitHub stars, its SKILL.md loads about 437 tokens and it passes the automated safety check with no findings. Next come Sparse Reading.
Are the skills in Zedong-Liu/SparseReading official?
None yet. All 2 skills in Zedong-Liu/SparseReading 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 Zedong-Liu/SparseReading?
Run npx skills add Zedong-Liu/SparseReading 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.