graphify
Skill2 starsChanged 2 months agoApache-2.0View on GitHub
将代码、政策或项目资料目录构建为可查询的持久知识图谱。仅在用户明确要求知识图谱、关系图、路径追踪、社区聚类、GraphRAG或明确点名graphify时使用。
- Installs packages
115 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- ever-works/skillstheir own version, first seen Nov 8, 2026
- rylsherdamz-rgb/stellar-forgetheir own version, first seen Nov 8, 2026
- brebuilds/claude-skillstheir own version, first seen Nov 8, 2026
- GstMirabal/Token-Optimized-Agent-Pipelinetheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
Used with
Projects with it also use remotion-maps, remotion-saas and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillremotion-maps
Remotion Map animation knowledge
Also in 4 projects that use this
OpenAISkillremotion-saas
Build an app with Remotion
Also in 4 projects that use this
royaluniondesign-sysSkilldeployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
Also in 4 projects that use this
mstuder-slalomSkilldjango-verification
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
Also in 3 projects that use this
ttmouseSkillprompt-master
提示词主控 - 智能选择合适的领域skill并生成提示词,支持自动领域分类和调度
Also in 4 projects that use this
seikaikyoSkilldoubt-driven-development
對非平凡決策啟動新鮮 context 對抗審查(找碴不背書),在修正還便宜的時候抓出錯誤方向。適用:高風險改動(production、資安敏感邏輯、不可逆操作)、不熟的程式碼、要宣稱「這樣是安全的 / 可行的」之前。機械性操作與一行修改不適用。
Also in 6 projects that use this
Other versions115 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 115
- safishamsi/graphify★ 144ksame name
- Graphify-Labs/graphify★ 144ksame name
- zaxbysauce/opencode-swarm★ 519same name
- ZaxbyHub/opencode-swarm★ 518same name
- nandyalu/trailarr★ 486same name
- bdfinst/agentic-dev-team★ 302same name
- cin12211/orca-q★ 225same name
- sammcj/agentic-coding★ 169same name
- EBISPOT/ols4★ 106same name
- buildomator/buildomator★ 102same name
105 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- agriculture-and-rural-projectsSkill
- application-version-diffSkill
- application-writingSkill
- checking-patdocx-cn-single-agentSkill
- consistency-checkSkill
- deep-clarificationSkill
- digitalization-projectsSkill
- enterprise-panorama-analysisSkill
- enterprise-profileSkill
- evidence-ledgerSkill
- evolution-governanceSkill
- experience-recorderSkill
- financial-verificationSkill
- green-development-projectsSkill
- high-tech-enterprise-application-draftingSkill
- high-tech-enterprise-preassessmentSkill
- humanizer-zhSkill
- industrialization-projectsSkill
- industry-chain-foundation-matcherSkill
- industry-positioningSkill
- intellectual-property-projectsSkill
- investment-subsidy-projectsSkill
- ip-assessmentSkill
- legal-regulationsSkill
- manufacturing-tax-risk-analysisSkill
- patent-routerSkill
- peer-benchmarkingSkill
- policy-retrievalSkill
- project-application-assistantSkill
- project-deliverable-archiveSkill
- project-feasibilitySkill
- project-matchingSkill
- project-memorySkill
- project-rule-managerSkill
- project-task-routerSkill
- quality-brand-projectsSkill
- regional-special-projectsSkill
- skill-authoringSkill
- skill-curatorSkill
- skill-evolutionSkill
- sme-development-projectsSkill
- sme-score-preassessmentSkill
- standard-draftingSkill
- talent-projectsSkill
- technology-innovation-projectsSkill
- trade-and-open-economy-projectsSkill
- web-task-operatorSkill
The file
Files
知识图谱构建与查询
把用户指定目录转换为可持续更新的知识图谱,用于发现文件、政策、项目、企业、产品、技术、专利和证据之间的关系。
使用边界
- 普通文件搜索和政策关键词检索不自动触发本技能,直接使用宿主已有的文件或网页检索能力。
- 只有用户明确要求知识图谱、关系追踪、最短路径、社区聚类或GraphRAG时触发。
- 不默认生成Obsidian目录;标准输出为交互式HTML、图数据JSON和图谱报告。
- 图谱中的推断关系必须与原文提取关系分开标记,不把模型推断写成政策或企业事实。
- 只处理用户指定的单一客户、单一项目或单一专题目录,不扫描主目录、磁盘根或混合客户根目录。
- 每个客户或项目使用独立的
graphify-out/;除非用户明确要求集团或多主体对比,不合并不同客户图谱。 - Graphify只用于关系导航、证据链检查和异常发现,不替代政策现行性、企业登记、专利法律状态或财务原值核验。
项目与隐私门禁
- 先读
references/project-profiles.md,选择application-evidence、policy-corpus、ip-evidence或client-dossier。 - 涉及专精特新或小巨人时,先确认申请书项目类型与审核版本;未确认时只能盘点资料和构图,不形成达标结论。
- 客户项目默认
privacy=restricted。不得因环境中存在模型密钥就把客户资料发送给第三方后端。 - 发现凭据、身份证件、银行账号、原始员工花名册或未脱敏客户名单时,排除相应文件并只报告数量。
- 公开政策、公示名单和公开专利可使用
privacy=public,但仍须保留来源和采集日期。
完整规则见 references/privacy-and-scope.md。
前置能力
本技能调用开源 graphifyy 工具。首次使用时先检测:
command -v graphify || python3 -c "import graphify"未安装时向用户说明将安装第三方依赖,再执行以下任一方式:
uv tool install graphifyy或:
python3 -m pip install graphifyy构建流程
- 确认输入目录、业务 Profile、隐私级别和输出目的。
- 至少10个相关文件、预计超过20,000字、需要跨材料证据核对或会持续更新时再构图;小任务直接使用现有检索与审查技能。
- 初始化项目:
python3 scripts/init_project.py PROJECT_ROOT \
--profile PROFILE \
--project-name "项目名称" \
--client-name "客户名称" \
--privacy restricted- 生成业务语义提取规范:
python3 scripts/build_prompt.py \
--overlay references/domain-overlay.md \
--output PROJECT_ROOT/graphify-out/.project-extraction-spec.md如宿主或已安装的 Graphify 提供基础提取规范,可额外传入 --upstream 基础规范路径,再叠加本技能规则。
5. 统计文件数量、类型和规模;超过500份文件时按一级目录分批。
6. 执行完整构建,输出到项目目录下的 graphify-out/,至少保留 graph.json、交互式HTML和 GRAPH_REPORT.md。
7. 审计图谱:
python3 scripts/audit_graph.py \
PROJECT_ROOT/graphify-out/graph.json \
--profile PROJECT_ROOT/.enterprise-project-assistant-graphify.json \
--output PROJECT_ROOT/graphify-out/EVIDENCE_GRAPH_AUDIT.md- 抽样核对实体、关系、来源文件、政策版本、专利状态和推断标记;审计告警不自动改图。
- 后续文件变化时优先增量更新,不重复全量构建。
常用命令:
graphify <目录> --no-viz
graphify <目录> --update
graphify query "问题"
graphify path "实体A" "实体B"
graphify explain "实体名称"需要交互图时移除 --no-viz。需要提供给其他Agent时,优先导出工具支持的GraphRAG JSON,并继续保留原始文件来源。
政府项目场景
- 政策版本图:政策、废止依据、替代文件、申报通知和执行细则。
- 项目关系图:国家、省、市、区县项目及其上下级、别名和申报条件。
- 企业能力图:产品、技术、专利、客户验证、产业链和可申报项目。
- 专利关系图:申请人、权利人、同族、引证、技术特征和产品映射。
业务实体、关系方向、来源等级和申报四项判断规则见 references/domain-overlay.md;常用问题见 references/query-templates.md。
查询与交付
回答必须区分:
- 图谱事实:附
source_file或source_location; - 图谱推断:标明关系置信度;
- 待外部核验:政策现行性、企业登记、专利法律状态和财务原值;
- 行动项:缺少的材料、冲突关系或补证任务。
正式申报文本仍须经过套件的真实性、数据溯源、关联一致性和交付门禁,图谱报告不能替代正式申报材料。
验收
- 每个关键节点可追溯到原文件。
- 抽样关系不存在方向颠倒或同名实体误合并。
EXTRACTED、INFERRED和AMBIGUOUS关系明确区分。- 不同客户资料未进入同一图谱,受限资料未静默发送到外部模型。
- 政策版本、专利状态和事实冲突被显式保留,不以共现关系替代核验。
- 更新后旧图谱可回滚,新增文件能够进入增量结果。
来源说明
本技能是企业项目申报助手的原创适配说明,运行时依赖第三方开源包 graphifyy。第三方软件的安装、版本和许可证以其发布页面为准,不随本技能复制第三方源码。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

