Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
查询本机 CrabRAG RAG 知识库，返回证据片段 JSON；当用户问题需要本地知识库资料、法规、制度、流程或业务规则依据时使用。
Install Crabrag RAG
$ npx skills add guoyijia22/CrabRAG --skill crabrag-rag -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install guoyijia22/CrabRAG crabrag-rag --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/guoyijia22/CrabRAG.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/crabrag-rag .claude/skills/crabrag-rag && 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 "crabrag-rag" agent skill from https://github.com/guoyijia22/CrabRAG/tree/main/skills/crabrag-rag into .claude/skills/crabrag-rag/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "crabrag-rag", 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/guoyijia22/CrabRAG/tree/main/skills/crabrag-ragType 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 guoyijia22/CrabRAG --skill crabrag-rag -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install guoyijia22/CrabRAG crabrag-rag --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/guoyijia22/CrabRAG.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/crabrag-rag .agents/skills/crabrag-rag && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "crabrag-rag" agent skill from https://github.com/guoyijia22/CrabRAG/tree/main/skills/crabrag-rag into .agents/skills/crabrag-rag/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "crabrag-rag", 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 guoyijia22/CrabRAG --skill crabrag-rag -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install guoyijia22/CrabRAG crabrag-rag --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/guoyijia22/CrabRAG.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/crabrag-rag .cursor/skills/crabrag-rag && 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 "crabrag-rag" agent skill from https://github.com/guoyijia22/CrabRAG/tree/main/skills/crabrag-rag into .cursor/skills/crabrag-rag/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "crabrag-rag", 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/guoyijia22/CrabRAG.git --path skills/crabrag-rag--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 guoyijia22/CrabRAG --skill crabrag-rag -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install guoyijia22/CrabRAG crabrag-rag --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/guoyijia22/CrabRAG.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/crabrag-rag .gemini/skills/crabrag-rag && 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 "crabrag-rag" agent skill from https://github.com/guoyijia22/CrabRAG/tree/main/skills/crabrag-rag into .gemini/skills/crabrag-rag/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "crabrag-rag", 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 guoyijia22/CrabRAG crabrag-ragInstalls 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 guoyijia22/CrabRAG --skill crabrag-rag -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/guoyijia22/CrabRAG.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/crabrag-rag .github/skills/crabrag-rag && 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 "crabrag-rag" agent skill from https://github.com/guoyijia22/CrabRAG/tree/main/skills/crabrag-rag into .github/skills/crabrag-rag/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "crabrag-rag", 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 guoyijia22/CrabRAG --skill crabrag-rag -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install guoyijia22/CrabRAG crabrag-rag --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/guoyijia22/CrabRAG.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/crabrag-rag .opencode/skills/crabrag-rag && 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 "crabrag-rag" agent skill from https://github.com/guoyijia22/CrabRAG/tree/main/skills/crabrag-rag into .opencode/skills/crabrag-rag/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "crabrag-rag", 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
crabrag-rag- GitHub stars
- 113
- Token cost
- ~282 tokens
- SKILL.md length
- 68 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
查询本机 CrabRAG RAG 知识库，返回证据片段 JSON；当用户问题需要本地知识库资料、法规、制度、流程或业务规则依据时使用。
- Tasks that involve Retrieval-augmented generation
- SKILL.md covers 前置配置, 查询证据, 回答规则 and 使用要求
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Crabrag RAG is an agent skill from guoyijia22/CrabRAG. 查询本机 CrabRAG RAG 知识库，返回证据片段 JSON；当用户问题需要本地知识库资料、法规、制度、流程或业务规则依据时使用。
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 sits in AI & LLM Engineering, covering Retrieval-augmented generation. The repository describes itself as: Production-ready local RAG system with incremental indexing, atomic index generations, ACL-aware retrieval, GraphRAG, and local/API model support. The licence is MIT.
When your agent uses it
- Tasks that involve Retrieval-augmented generation
Example prompts
- “/crabrag-rag”
What it can do on your machine
Read from SKILL.md and the folder at commit 400ccd0. 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 (its code samples are bat).
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
Crabrag RAG loads about 282 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 68 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 guoyijia22/CrabRAG at commit 400ccd0, republished under its MIT licence (© guoyijia22). 68 words, ~282 tokens.
Download SKILL.mdSave it as
.claude/skills/crabrag-rag/SKILL.md (or your agent's skills folder).- name
- crabrag-rag
- description
- 查询本机 CrabRAG RAG 知识库，返回证据片段 JSON；当用户问题需要本地知识库资料、法规、制度、流程或业务规则依据时使用。
CrabRAG 证据检索
当用户问题可能需要本机 CrabRAG 知识库中的资料、制度、流程、业务规则或证据片段时，使用此 Skill。UniClaw 单文件入口为项目根目录的 crabrag.skill；本文件保留给支持目录式 Skill 的本地调用端使用。
前置配置
CRABRAG_HOME 必须指向 CrabRAG 项目根目录，例如：
set CRABRAG_HOME=F:\trae\CrabRAG查询证据
调用本地 CLI，并原样传入用户问题：
"%CRABRAG_HOME%\crab-rag.bat" --question "用户问题" --top-k 6 --pretty可选参数：
--mode auto|vector|graph|hybrid：选择检索方式。默认使用auto。--include-trace：调试时返回检索诊断信息。--no-rerank：跳过 Rerank，适合只需要最快原始检索结果的场景。
回答规则
只根据 CLI 返回的 JSON 证据回答。把 evidence[].content 作为原文依据；有来源信息时，引用 source_file 和 section_title。
如果 ok 为 false，说明本地 RAG 查询失败，并带上 error 内容。
如果 evidence 为空，或 warnings 包含 out_of_scope / no_evidence，说明本地知识库没有提供足够依据。不要编造事实。
不要调用 CrabRAG 的 /api/chat 接口。本 Skill 只负责查资料和返回证据，最终回答必须由当前 Uniclaw/OpenClaw 模型根据证据生成。
使用要求
Uniclaw 回答要更直接，但不能牺牲证据约束：
- 先给结论，再列依据。
- 依据不足时直接说明“知识库未检索到足够证据”。
- 不要把常识、猜测或模型自身知识混入知识库结论。
- 来源引用保持简洁，例如：
来源：rules.md / 资费材料。
© guoyijia22, 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 skills/crabrag-rag of guoyijia22/CrabRAG.
Open the folder on GitHubat commit 400ccd0
Compare with similar skills
Crabrag RAG 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 |
|---|---|---|---|---|---|---|
| Crabrag RAG this skillguoyijia22/CrabRAG | 113 | — | ~282 | Automated safety check: Pass | MIT | |
| Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Senior Prompt Engineermaslennikov-ig/claude-code-orchestrator-kit | 260 | 3 repos | ~1.4k | Automated safety check: Pass | Custom licence | |
| MCP Local RAGshinpr/mcp-local-rag | 412 | — | ~4.4k | Automated safety check: Pass | MIT | |
| Ms Agent Framework RAGshuyu-labs/WebCode | 278 | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Local RAG Searchnkapila6/mcp-local-rag | 134 | 1 repos | ~1.6k | Automated safety check: Pass | MIT |
Similar skills
Senior Prompt Engineer
maslennikov-ig/claude-code-orchestrator-kit
Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.
MCP Local RAG
shinpr/mcp-local-rag
Searches, saves, and maintains a local document index through a local RAG MCP server.
Ms Agent Framework RAG
shuyu-labs/WebCode
Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C.
Local RAG Search
nkapila6/mcp-local-rag
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking.
Blockify Integration
iternal-technologies-partners/blockify-agentic-data-optimization
Process documents with Blockify API to create optimized IdeaBlocks for RAG.
Related
Categories
Questions about Crabrag RAG
What does Crabrag RAG do?
查询本机 CrabRAG RAG 知识库，返回证据片段 JSON；当用户问题需要本地知识库资料、法规、制度、流程或业务规则依据时使用。. Crabrag RAG is an agent skill from guoyijia22/CrabRAG.
When should I use Crabrag RAG?
Crabrag RAG fits situations like: tasks that involve Retrieval-augmented generation.
How do I install Crabrag RAG in Claude Code?
Run `npx skills add guoyijia22/CrabRAG --skill crabrag-rag -a claude-code`. Or copy the skill folder (skills/crabrag-rag in guoyijia22/CrabRAG) into .claude/skills/crabrag-rag in your project. Claude Code loads it when a task matches its description.
How do I install Crabrag RAG in Codex?
Run `npx skills add guoyijia22/CrabRAG --skill crabrag-rag -a codex`. Or copy the skill folder (skills/crabrag-rag in guoyijia22/CrabRAG) into .agents/skills/crabrag-rag in your project. Codex loads it when a task matches its description.
Can I use Crabrag RAG 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 guoyijia22/CrabRAG --skill crabrag-rag -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/crabrag-rag, .gemini/skills/crabrag-rag, .github/skills/crabrag-rag and .opencode/skills/crabrag-rag in your project.
What does Crabrag RAG need to run?
SKILL.md names no scripts, command-line tools or credentials: Crabrag RAG is instructions for the agent only.
Does Crabrag RAG 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 Crabrag RAG 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 Crabrag RAG use?
Crabrag RAG 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 Crabrag RAG use?
About 282 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 Crabrag RAG?
Skills that share tags, products or a category with Crabrag RAG: Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars), Senior Prompt Engineer (maslennikov-ig/claude-code-orchestrator-kit, 260 stars), MCP Local RAG (shinpr/mcp-local-rag, 412 stars) and Ms Agent Framework RAG (shuyu-labs/WebCode, 278 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Crabrag RAG?
guoyijia22 (a GitHub user) maintains it in guoyijia22/CrabRAG, which has 113 GitHub stars. The repository was last updated on July 30, 2026.
Source: guoyijia22/CrabRAG on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.