bkn-creator

Name: bkn-creator
Author: openbkn-ai

github.com/openbkn-aiData & databases2466 installsUpdated 7w ago

About bkn-creator

A routing skill for BKN Creator that maps requests about knowledge networks to internal pipelines. It covers creation, extraction, querying, updates, deletion, copying, validation, skill generation, and feedback review, with user confirmation before execution.

Key features

01Intent routing to internal pipelines
02Knowledge-network creation and extraction
03Read, update, delete, and copy operations
04Validation and feedback review
05Confirmation before pipeline execution

Use cases

01Creating a knowledge network from a PRD
02Extracting entities and relations from documents
03Checking or updating an existing network
04Reviewing feedback and trace analysis

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/openbkn-ai/bkn-engineering --skill bkn-creator

After installing, type/bkn-creatorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

internal/_pipelines/

copy.md

create.md

delete.md

extract.md

feedback.md

read.md

skill-gen.md

update.md

validate.md

internal/_plugins/

MANIFEST.md

internal/_shared/

contract.md

display.md

plugin-check.md

prepush-validation.md

internal/bkn-bind/references/

binding-rules.md

semantic-guide.md

internal/bkn-domain/references/

_template.md

domain-crm-sales.md

domain-project-delivery.md

domain-supply-chain.md

generic-extraction.md

scoring-rules.md

internal/bkn-draft/assets/templates/

action_type.bkn.template

concept_group.bkn.template

network_type.bkn.template

object_type.bkn.template

relation_type.bkn.template

internal/bkn-draft/references/examples/k8s-network/

CHECKSUM

internal/bkn-draft/references/examples/k8s-network/action_types/

cordon_node.bkn

restart_pod.bkn

Details

From the project README

BKN 创建器

本文件是 BKN Creator 的桥接入口。实际能力定义在 internal/ 目录中。

路由表

识别用户意图后，读取对应 pipeline 文件并按其指令执行。

意图	触发词	读取文件
`create`	创建知识网络、新建 BKN、根据 PRD 建模	`internal/_pipelines/create.md`
`extract`	提取对象类、从文档抽取实体关系	`internal/_pipelines/extract.md`
`read`	查询、搜索、列出、查看	`internal/_pipelines/read.md`
`update`	修改、编辑、更新、重绑定	`internal/_pipelines/update.md`
`delete`	删除、清理、移除	`internal/_pipelines/delete.md`
`copy`	复制、克隆、基于现有生成新版本	`internal/_pipelines/copy.md`
`validate`	检查网络、评估质量、诊断问题、验证完整性	`internal/_pipelines/validate.md`
`skill_generate`	补 skill、抽成独立 skill、补齐能力	`internal/_pipelines/skill-gen.md`
`feedback_review`	巡检反馈、使用问题、定时任务触发、改进摘要、trace 分析结果	`internal/_pipelines/feedback.md`

执行协议

识别意图 → 输出：识别意图 + 路由目标 + 输入摘要 + 确认请求
路由确认阶段只展示高层信息，不展示对象/关系明细
用户确认后 → 读取上表中的 pipeline 文件，按文件内指令逐步执行
pipeline 中引用的每个 skill，按 pipeline 内标注的相对路径读取其 SKILL.md

共享公约

执行前先读取：internal/_shared/contract.md

约束

未确认时只重复"路由识别 + 确认请求"
跨流程切换必须重新路由确认

Comments

Markdown supported

Details

Author: openbkn-ai
Repository: openbkn-ai/bkn-engineering
Category: Data & databases
Installs: 66
GitHub stars: 24

Report

More skills

All skills

hyperframes-core

github.com/heygen-com

930.6k

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md plan formats. Read before writing composition HTML.

lark-base

open.feishu.cn

823.2k

Operate on Feishu Base: create tables, fields, records, and views; handle statistics, formulas/lookups, forms, dashboards, app mode (BaseApp/AppMode pages and components), Workspace directories, workflows, role permissions, and the template center (Base template categories, lists, and search). Use when encountering Base/multidimensional tables/bitable, BaseApp/AppMode, or /base/ or /app/ links. Do not use lark-apps for BaseApp; route file import/export to lark-drive and authentication/authorization to lark-shared.

lark-sheets

open.feishu.cn

821.8k

Feishu Spreadsheets: create and operate spreadsheets. Supports worksheets and row/column structures (add/delete/merge/size/hide/freeze/group), cell read/write (values/formulas/styles/comments/cell images), range copy/move/sort/fill, find and replace, bulk updates, and creating and maintaining objects such as charts, pivot tables, conditional formatting, filters and filter views, dropdown lists, sparklines, and floating images. Also supports formula validation, restoring historical versions, and importing/exporting local Excel/CSV files and Feishu spreadsheets. Use when users need to create or edit spreadsheets, summarize and visualize data, format spreadsheets, calculate formulas (including migrating Excel formulas), or build financial models (DCF, three statements, budgets, Sensitivity, etc.). For multidimensional tables (Base/bitable), use lark-base. If users want to search for spreadsheet files in cloud storage (Drive/cloud storage) by name or keyword, use lark-drive's drive +search to locate resources first. When users provide a doubao.com /sheets/ URL/token, use this skill directly; do not fall back to WebFetch because the domain is not Feishu. Routing is based on the URL path pattern and token, not the domain.

remotion-best-practices

github.com/remotion-dev

701.4k

Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4). Use whenever writing or editing Remotion code — scaffolding a video project, animating with interpolate/spring over useCurrentFrame(), sequencing scenes and transitions, captions/subtitles, audio, GIFs/Lottie/3D, charts, visual effects, dynamic duration via calculateMetadata, or rendering. Consult before reaching for a Remotion API, since its components and props evolve (e.g. @remotion/media).