Graph Retrieval
study8677/repobrain
Exposes graph-based retrieval as a tool capability via querygraph.
“图谱与血缘检索技能，查询实体之间的关系、上下游依赖与数据血缘。”
MITAuto-check passed
Install Graph Retrieval
$ npx skills add larry-zy/cognida --skill graph-retrieval -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install larry-zy/cognida graph-retrieval --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/larry-zy/cognida.git skills-src && mkdir -p .claude/skills && cp -r skills-src/services/cognida-go/skills/graph-retrieval .claude/skills/graph-retrieval && 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 "graph-retrieval" agent skill from https://github.com/larry-zy/cognida/tree/main/services/cognida-go/skills/graph-retrieval into .claude/skills/graph-retrieval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "graph-retrieval", 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/larry-zy/cognida/tree/main/services/cognida-go/skills/graph-retrievalType 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 larry-zy/cognida --skill graph-retrieval -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install larry-zy/cognida graph-retrieval --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/larry-zy/cognida.git skills-src && mkdir -p .agents/skills && cp -r skills-src/services/cognida-go/skills/graph-retrieval .agents/skills/graph-retrieval && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "graph-retrieval" agent skill from https://github.com/larry-zy/cognida/tree/main/services/cognida-go/skills/graph-retrieval into .agents/skills/graph-retrieval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "graph-retrieval", 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 larry-zy/cognida --skill graph-retrieval -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install larry-zy/cognida graph-retrieval --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/larry-zy/cognida.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/services/cognida-go/skills/graph-retrieval .cursor/skills/graph-retrieval && 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 "graph-retrieval" agent skill from https://github.com/larry-zy/cognida/tree/main/services/cognida-go/skills/graph-retrieval into .cursor/skills/graph-retrieval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "graph-retrieval", 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/larry-zy/cognida.git --path services/cognida-go/skills/graph-retrieval--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 larry-zy/cognida --skill graph-retrieval -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install larry-zy/cognida graph-retrieval --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/larry-zy/cognida.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/services/cognida-go/skills/graph-retrieval .gemini/skills/graph-retrieval && 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 "graph-retrieval" agent skill from https://github.com/larry-zy/cognida/tree/main/services/cognida-go/skills/graph-retrieval into .gemini/skills/graph-retrieval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "graph-retrieval", 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 larry-zy/cognida graph-retrievalInstalls 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 larry-zy/cognida --skill graph-retrieval -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/larry-zy/cognida.git skills-src && mkdir -p .github/skills && cp -r skills-src/services/cognida-go/skills/graph-retrieval .github/skills/graph-retrieval && 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 "graph-retrieval" agent skill from https://github.com/larry-zy/cognida/tree/main/services/cognida-go/skills/graph-retrieval into .github/skills/graph-retrieval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "graph-retrieval", 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 larry-zy/cognida --skill graph-retrieval -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install larry-zy/cognida graph-retrieval --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/larry-zy/cognida.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/services/cognida-go/skills/graph-retrieval .opencode/skills/graph-retrieval && 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 "graph-retrieval" agent skill from https://github.com/larry-zy/cognida/tree/main/services/cognida-go/skills/graph-retrieval into .opencode/skills/graph-retrieval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "graph-retrieval", 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
graph-retrieval- GitHub stars
- 182
- Token cost
- ~236 tokens
- SKILL.md length
- 26 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
- SKILL.md covers 何时用 / 何时不用, 标准流程, 工具 and 约束
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Graph Retrieval is a skill in larry-zy/cognida (182 stars). Its SKILL.md is about 236 tokens. Licence: MIT.
What it can do on your machine
Read from SKILL.md and the folder at commit bf76257. 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 json).
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
Graph Retrieval loads about 236 tokens when it runs. Until then it costs about 12 tokens; SKILL.md has 26 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 larry-zy/cognida at commit bf76257, republished under its MIT licence (© larry-zy). 26 words, ~236 tokens.
Download SKILL.mdSave it as
.claude/skills/graph-retrieval/SKILL.md (or your agent's skills folder).- name
- graph-retrieval
- description
- 图谱与血缘检索技能，查询实体之间的关系、上下游依赖与数据血缘。
- when_to_use
- 当问题是关于实体间关系、依赖、影响面或数据血缘（如“这个字段的上游来自哪”“A 和 B 怎么关联”“改动这张表影响谁”）时使用，走知识图谱而非向量文档检索。
- category
- retrieval
- tags
- graph, lineage, relationship, knowledge-graph
- version
- 1.0.0
- author
- Cognida Team
图谱 / 血缘检索
面向「查实体关系与数据血缘」的场景：沿图上的边遍历上下游、依赖与影响面。区别于文档问答（查文本片段）。
何时用 / 何时不用
- ✅ 用：问的是关系/连接/依赖/血缘/影响面——上游来源、下游消费、A 与 B 如何关联、改动波及谁。
- ❌ 不用：
- 问题答案在文档正文里 →
doc-qa - 要的是数据库里的统计数字 →
text2sql-adhoc/semantic-metric
- 问题答案在文档正文里 →
标准流程
1. 明确起点实体与关系方向（上游/下游/双向）
↓
2. graph_query 沿关系边检索（可限定跳数/关系类型）
↓
3. 归纳路径与影响面，必要时二次下钻
↓
4. 结构化呈现关系链 / 血缘路径工具
graph_query — 图谱关系检索
{ "tool": "graph_query", "parameters": { "entity": "orders.amount", "direction": "upstream" } }按实际参数 schema 传入起点、方向与跳数；不确定时先小跳数探路再扩展。
约束
- 先确定方向与范围，避免全图无界遍历。
- 呈现关系链时标明每一跳的关系类型与来源。
- 图谱未启用或实体不在图上时如实说明，不臆造关系。
© larry-zy, 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 services/cognida-go/skills/graph-retrieval of larry-zy/cognida.
Open the folder on GitHubat commit bf76257
Compare with similar skills
Graph Retrieval 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 |
|---|---|---|---|---|---|---|
| Graph Retrieval this skilllarry-zy/cognida | 182 | — | ~236 | Automated safety check: Pass | MIT | |
| Graph Retrievalstudy8677/repobrain | 1.3k | — | ~255 | Automated safety check: Pass | MIT | |
| Graphagenticnotetaking/arscontexta | 3.5k | — | ~4.9k | Automated safety check: Notes | MIT | |
| Bigquery Graphgoogle/adk-python | 22k | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| Iterative Retrievalaffaan-m/ECC | 276k | 7 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Code Review Graph Buildertirth8205/code-review-graph | 32k | — | ~295 | Automated safety check: Pass | MIT |
Similar skills
Graph
agenticnotetaking/arscontexta
Interactive knowledge graph analysis. An agent skill from agenticnotetaking/arscontexta.
- Official
Bigquery Graph
google/adk-python
Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph.
Iterative Retrieval
affaan-m/ECC
Pattern for progressively refining context retrieval to solve the subagent context problem.
Code Review Graph Builder
tirth8205/code-review-graph
Builds or incrementally updates the code-review knowledge graph for a repository and reports whether the build succeeded, partly or failed.
- Official
Mini Context Graph
github/awesome-copilot
A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph.
More from larry-zy/cognida
All 9 skills in this repoAttribution Analysis
larry-zy/cognida
归因/根因分析技能，把指标的期间变化拆解到候选维度，定位驱动因子并给出置信与下钻建议. An agent skill from larry-zy/cognida.
Report Composition
larry-zy/cognida
综合报告生成技能，把多段取数（总览+趋势+分群等）整合成一份带洞察的结构化报告. An agent skill from larry-zy/cognida.
Semantic Metric
larry-zy/cognida
语义指标取数技能，先查治理好的指标语义模型，再按统一口径取指标，避免对物理表猜测. An agent skill from larry-zy/cognida.
Ecommerce Core Metrics Report
larry-zy/cognida
Generate a comprehensive report of core e-commerce operating metrics (GMV, orders, average order value, repurchase)
Text2sql Adhoc
larry-zy/cognida
即席取数技能，把一句话的具体数据问题翻译成 SQL 并执行返回结果。
Trend Analysis
larry-zy/cognida
趋势分析技能，取带时间维度的序列并量化其增长/变化幅度与异常点。
Questions about Graph Retrieval
How do I install Graph Retrieval in Claude Code?
Run `npx skills add larry-zy/cognida --skill graph-retrieval -a claude-code`. Or copy the skill folder (services/cognida-go/skills/graph-retrieval in larry-zy/cognida) into .claude/skills/graph-retrieval in your project. Claude Code loads it when a task matches its description.
How do I install Graph Retrieval in Codex?
Run `npx skills add larry-zy/cognida --skill graph-retrieval -a codex`. Or copy the skill folder (services/cognida-go/skills/graph-retrieval in larry-zy/cognida) into .agents/skills/graph-retrieval in your project. Codex loads it when a task matches its description.
Can I use Graph Retrieval 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 larry-zy/cognida --skill graph-retrieval -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/graph-retrieval, .gemini/skills/graph-retrieval, .github/skills/graph-retrieval and .opencode/skills/graph-retrieval in your project.
What does Graph Retrieval need to run?
SKILL.md names no scripts, command-line tools or credentials: Graph Retrieval is instructions for the agent only.
Does Graph Retrieval 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 Graph Retrieval 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 Graph Retrieval use?
Graph Retrieval 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 Graph Retrieval use?
About 236 tokens (SKILL.md is roughly 944 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 Graph Retrieval?
Skills that share tags, products or a category with Graph Retrieval: Graph Retrieval (study8677/repobrain, 1.3k stars), Graph (agenticnotetaking/arscontexta, 3.5k stars), Bigquery Graph (google/adk-python, 22k stars) and Iterative Retrieval (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Graph Retrieval?
larry-zy (a GitHub user) maintains it in larry-zy/cognida, which has 182 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 31, 2026.
Source: larry-zy/cognida on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.