MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Use SparseRead tools to inspect large, structured, or multi-file project inputs with targeted evidence.
MITAuto-check passed
Install Sparse Reading
$ npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Zedong-Liu/SparseReading sparse-reading --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Zedong-Liu/SparseReading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/integrations/codex/plugin/sparseread-codex/skills/sparse-reading .claude/skills/sparse-reading && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sparse-reading" agent skill from https://github.com/Zedong-Liu/SparseReading/tree/main/integrations/codex/plugin/sparseread-codex/skills/sparse-reading into .claude/skills/sparse-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sparse-reading", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Zedong-Liu/SparseReading/tree/main/integrations/codex/plugin/sparseread-codex/skills/sparse-readingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Zedong-Liu/SparseReading sparse-reading --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Zedong-Liu/SparseReading.git skills-src && mkdir -p .agents/skills && cp -r skills-src/integrations/codex/plugin/sparseread-codex/skills/sparse-reading .agents/skills/sparse-reading && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sparse-reading" agent skill from https://github.com/Zedong-Liu/SparseReading/tree/main/integrations/codex/plugin/sparseread-codex/skills/sparse-reading into .agents/skills/sparse-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sparse-reading", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Zedong-Liu/SparseReading sparse-reading --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Zedong-Liu/SparseReading.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/integrations/codex/plugin/sparseread-codex/skills/sparse-reading .cursor/skills/sparse-reading && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sparse-reading" agent skill from https://github.com/Zedong-Liu/SparseReading/tree/main/integrations/codex/plugin/sparseread-codex/skills/sparse-reading into .cursor/skills/sparse-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sparse-reading", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Zedong-Liu/SparseReading.git --path integrations/codex/plugin/sparseread-codex/skills/sparse-reading--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Zedong-Liu/SparseReading sparse-reading --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Zedong-Liu/SparseReading.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/integrations/codex/plugin/sparseread-codex/skills/sparse-reading .gemini/skills/sparse-reading && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sparse-reading" agent skill from https://github.com/Zedong-Liu/SparseReading/tree/main/integrations/codex/plugin/sparseread-codex/skills/sparse-reading into .gemini/skills/sparse-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sparse-reading", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Zedong-Liu/SparseReading sparse-readingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Zedong-Liu/SparseReading.git skills-src && mkdir -p .github/skills && cp -r skills-src/integrations/codex/plugin/sparseread-codex/skills/sparse-reading .github/skills/sparse-reading && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sparse-reading" agent skill from https://github.com/Zedong-Liu/SparseReading/tree/main/integrations/codex/plugin/sparseread-codex/skills/sparse-reading into .github/skills/sparse-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sparse-reading", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Zedong-Liu/SparseReading sparse-reading --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Zedong-Liu/SparseReading.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/integrations/codex/plugin/sparseread-codex/skills/sparse-reading .opencode/skills/sparse-reading && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sparse-reading" agent skill from https://github.com/Zedong-Liu/SparseReading/tree/main/integrations/codex/plugin/sparseread-codex/skills/sparse-reading into .opencode/skills/sparse-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sparse-reading", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sparse-reading- GitHub stars
- 242
- Token cost
- ~278 tokens
- SKILL.md length
- 153 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use SparseRead tools to inspect large, structured, or multi-file project inputs with targeted evidence.
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Sparse Reading is an agent skill from Zedong-Liu/SparseReading. Use SparseRead tools to inspect large, structured, or multi-file project inputs with targeted evidence.
Its SKILL.md is about 280 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Python and TypeScript. The repository describes itself as: SparseRead: token-efficient reading for AI agents. 读得更少，token 更省，证据不变。 Paper arXiv:2608.22237. The licence is MIT.
Example prompts
- “/sparse-reading”
What it can do on your machine
Read from SKILL.md and the folder at commit 5c6fee5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Sparse Reading loads about 278 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 153 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Zedong-Liu/SparseReading at commit 5c6fee5, republished under its MIT licence (© Zedong-Liu). 153 words, ~278 tokens.
Download SKILL.mdSave it as
.claude/skills/sparse-reading/SKILL.md (or your agent's skills folder).- name
- sparse-reading
- description
- Use SparseRead tools to inspect large, structured, or multi-file project inputs with targeted evidence.
SparseRead in Codex
Use SparseRead when an answer depends on a large document, structured file, or a collection of project files.
- Call
sro_decideto inspect the recommended reading route for a path. - Call
sro_previewbefore exploring a large or structured input. Use the returned card and preview to choose the evidence needed. - Call
sro_readwith a focused goal and suitable mode such asscout,focus,collect, orverify. - Call
sro_rawonly with araw_refreturned by SparseRead and a narrow range or selector. - Call
sro_cardfor file metadata andsro_traceto explain recent SparseRead routing.
Small and bounded reads can use Codex's normal tools. If a hook redirects a broad shell read, preview the named path and use the evidence tools before retrying the native command.
Codex does not run the bundled hooks until you review and trust their definitions in /hooks. Trust is a user decision; the plugin does not bypass it.
© Zedong-Liu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in integrations/codex/plugin/sparseread-codex/skills/sparse-reading of Zedong-Liu/SparseReading.
Open the folder on GitHubat commit 5c6fee5
Compare with similar skills
Sparse Reading next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Sparse Reading this skillZedong-Liu/SparseReading | 242 | — | ~278 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Image to Three.js Modelimg2threejs/img2threejs | 18k | 1 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Firecrawl Page Scrape Integrationfirecrawl/firecrawl | 190k | 1 repos | ~944 | Automated safety check: Pass | ISC |
Similar skills
- Official
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
Image to Three.js Model
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
Firecrawl Page Scrape Integration
firecrawl/firecrawl
Adds Firecrawl's /scrape endpoint to application code to pull markdown, HTML, links, screenshots or structured data from a single known URL.
Firecrawl Interact Integration
firecrawl/firecrawl
Guides adding Firecrawl's /interact endpoint to product code for pages that need clicks, forms, pagination or logged-in flows beyond plain scraping.
More from Zedong-Liu/SparseReading
Sparse Reading
Zedong-Liu/SparseReading
Use SparseRead for long documents, PDFs, and compact multi-file evidence closures without disrupting small native reads.
Related
Works with
Questions about Sparse Reading
What does Sparse Reading do?
Use SparseRead tools to inspect large, structured, or multi-file project inputs with targeted evidence. Sparse Reading is an agent skill from Zedong-Liu/SparseReading. Use SparseRead tools to inspect large, structured, or multi-file project inputs with targeted evidence.
How do I install Sparse Reading in Claude Code?
Run `npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a claude-code`. Or copy the skill folder (integrations/codex/plugin/sparseread-codex/skills/sparse-reading in Zedong-Liu/SparseReading) into .claude/skills/sparse-reading in your project. Claude Code loads it when a task matches its description.
How do I install Sparse Reading in Codex?
Run `npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a codex`. Or copy the skill folder (integrations/codex/plugin/sparseread-codex/skills/sparse-reading in Zedong-Liu/SparseReading) into .agents/skills/sparse-reading in your project. Codex loads it when a task matches its description.
Can I use Sparse Reading in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Zedong-Liu/SparseReading --skill sparse-reading -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sparse-reading, .gemini/skills/sparse-reading, .github/skills/sparse-reading and .opencode/skills/sparse-reading in your project.
What does Sparse Reading need to run?
SKILL.md names no scripts, command-line tools or credentials: Sparse Reading is instructions for the agent only.
Does Sparse Reading access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Sparse Reading safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Sparse Reading use?
Sparse Reading is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sparse Reading use?
About 278 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Sparse Reading?
Skills that share tags, products or a category with Sparse Reading: MCP Server Builder (anthropics/skills, 180k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and Image to Three.js Model (img2threejs/img2threejs, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sparse Reading?
Zedong-Liu (a GitHub user) maintains it in Zedong-Liu/SparseReading, which has 242 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 28, 2026.
Source: Zedong-Liu/SparseReading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.