ToolJet Marketplace Plugin Builder
ToolJet/ToolJet
Turns an API description, such as an OpenAPI file or a Postman collection, into a connector plugin for ToolJet's marketplace and checks it with the repo's validator.
面向 Henji-AI 的模型与供应商调研、文档整理、参数体验和适配工作流。用于“新增供应商”“给现有供应商新增模型”“模型和供应商都要新增”“核查 API/价格/平台别名”“校对参数顺序、通用交互、隐藏参数或默认请求值”这类需求;先输出确认清单,用户确认后再实施。普通模型 schema 会被标准画布节点自动读取,不因模型会出现在画布里而自动触发节点开发。
$ npx skills add henjicc/Henji-AI --skill henji-model-adaptation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install henjicc/Henji-AI henji-model-adaptation --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/henjicc/Henji-AI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/henji-model-adaptation .claude/skills/henji-model-adaptation && 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 "henji-model-adaptation" agent skill from https://github.com/henjicc/Henji-AI/tree/main/.codex/skills/henji-model-adaptation into .claude/skills/henji-model-adaptation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "henji-model-adaptation", 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/henjicc/Henji-AI/tree/main/.codex/skills/henji-model-adaptationType 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 henjicc/Henji-AI --skill henji-model-adaptation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install henjicc/Henji-AI henji-model-adaptation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/henjicc/Henji-AI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/henji-model-adaptation .agents/skills/henji-model-adaptation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "henji-model-adaptation" agent skill from https://github.com/henjicc/Henji-AI/tree/main/.codex/skills/henji-model-adaptation into .agents/skills/henji-model-adaptation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "henji-model-adaptation", 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 henjicc/Henji-AI --skill henji-model-adaptation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install henjicc/Henji-AI henji-model-adaptation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/henjicc/Henji-AI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/henji-model-adaptation .cursor/skills/henji-model-adaptation && 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 "henji-model-adaptation" agent skill from https://github.com/henjicc/Henji-AI/tree/main/.codex/skills/henji-model-adaptation into .cursor/skills/henji-model-adaptation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "henji-model-adaptation", 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/henjicc/Henji-AI.git --path .codex/skills/henji-model-adaptation--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 henjicc/Henji-AI --skill henji-model-adaptation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install henjicc/Henji-AI henji-model-adaptation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/henjicc/Henji-AI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/henji-model-adaptation .gemini/skills/henji-model-adaptation && 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 "henji-model-adaptation" agent skill from https://github.com/henjicc/Henji-AI/tree/main/.codex/skills/henji-model-adaptation into .gemini/skills/henji-model-adaptation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "henji-model-adaptation", 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 henjicc/Henji-AI henji-model-adaptationInstalls 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 henjicc/Henji-AI --skill henji-model-adaptation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/henjicc/Henji-AI.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/henji-model-adaptation .github/skills/henji-model-adaptation && 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 "henji-model-adaptation" agent skill from https://github.com/henjicc/Henji-AI/tree/main/.codex/skills/henji-model-adaptation into .github/skills/henji-model-adaptation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "henji-model-adaptation", 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 henjicc/Henji-AI --skill henji-model-adaptation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install henjicc/Henji-AI henji-model-adaptation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/henjicc/Henji-AI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/henji-model-adaptation .opencode/skills/henji-model-adaptation && 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 "henji-model-adaptation" agent skill from https://github.com/henjicc/Henji-AI/tree/main/.codex/skills/henji-model-adaptation into .opencode/skills/henji-model-adaptation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "henji-model-adaptation", 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.
henji-model-adaptation面向 Henji-AI 的模型与供应商调研、文档整理、参数体验和适配工作流。用于“新增供应商”“给现有供应商新增模型”“模型和供应商都要新增”“核查 API/价格/平台别名”“校对参数顺序、通用交互、隐藏参数或默认请求值”这类需求;先输出确认清单,用户确认后再实施。普通模型 schema 会被标准画布节点自动读取,不因模型会出现在画布里而自动触发节点开发。
Henji Model Adaptation is an agent skill from henjicc/Henji-AI. 面向 Henji-AI 的模型与供应商调研、文档整理、参数体验和适配工作流。用于“新增供应商”“给现有供应商新增模型”“模型和供应商都要新增”“核查 API/价格/平台别名”“校对参数顺序、通用交互、隐藏参数或默认请求值”这类需求;先输出确认清单,用户确认后再实施。普通模型 schema 会被标准画布节点自动读取,不因模型会出现在画布里而自动触发节点开发。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `agents/openai.yaml`, `references/derived-media-authoring.md` and `references/hidden-default-params.md`).
It sits in Backend & APIs, covering OpenAPI specifications. The repository describes itself as: 痕迹AI - 一个软件用上各种AI!聚合多家供应商,一站式生成图片、视频和音频. The licence is Apache-2.0.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c8107e0. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
npmFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Henji Model Adaptation loads about 2.2k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 448 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.
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.
The full file from henjicc/Henji-AI at commit c8107e0, republished under its Apache-2.0 licence (© henjicc). 448 words, ~2,177 tokens.
.claude/skills/henji-model-adaptation/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.按最小上下文加载执行。
references/intake-checklist.md,输出精简确认清单并等待用户确认。references/new-provider.md。references/new-model-existing-provider.md。references/new-provider.md,再读取 references/new-provider-and-model.md。packages/ai-sdk/docs/model-adaptation/——这是项目唯一资料源;其中 文档采集手册.md 是官方来源、事件契约、fixture/test 闭环与 SDK 首发顺序的唯一详细规范。旧的 docs/api/ 已废弃删除,不要重建或引用。references/source-research-workflow.md;按用户给定的平台矩阵控制范围,并完成模型别名、动态 Tab、价格与登录状态核验后再下结论。调研结论按该文件第 7 节的路径与命名约定落盘,并同步 README.md 清单。endpoints.selector + request.builder 在一个模型内稳定表达时,才考虑拆分成多个模型。mode,只要 API 文档表明它可通过同一端点内的可选字段激活(例如第 2 张图映射为 end_image),也应视为该模型具备此功能。meta.tags:保证模型能被功能筛选命中;inputLimits / requirements:保证输入数量与约束正确;request.builder:把 UI/上传素材转换成 API 所需字段。mode 参数。mode 参数,并通过 linkage/autoSwitch 自动更新其值;这类情况按“显式展示 + 自动切换”处理,不算纯手动模式。mode 参数。mode;mode,默认显示“文/图生视频”,上传 2 张图后自动切到“首尾帧”。mode 主导。references/param-order-patterns.md;先保留跨模型通用参数的标准交互,再收纳模型特有或低频参数。references/derived-media-authoring.md;先设计“创建/编辑/继续编辑”闭环,再决定提交时的媒体路径与上传转换。.tsx 参数面板,按项目规则同时使用 henji-ui-surface;这仍属于共享参数呈现,不因它也会出现在画布里而自动变成画布节点任务。references/hidden-default-params.md。references/modality-differences.md。references/param-order-patterns.md)。packages/ai-sdk/src/{providers,upload,protocols}/,electron/main/services/ai-runtime/** 只保留日志、落盘、取消、进度与 IPC 等宿主薄壳。文档采集手册.md 完成官方资料和事件契约,再在本项目实现、验证、打包回装并发布;消费项目只接入已验证的精确版本。资料不足时暂停,不在消费项目猜协议。packages/ai-sdk/docs/consumers.md,按变更的实际影响逐个同步消费者;未使用的新能力不进入宿主。外部消费者精确锁定版本与 integrity,并把 commit、验证状态和接入边界回写清单。mode”;meta.canonicalModelId,禁止填写 meta.description。适配前先检查 src/core/modelCatalog/generationModelDescriptions.ts:已有同一通用模型标识就直接引用;不存在就新增空描述条目,并在交付时明确告诉用户需要在该文件补充这个模型的定性描述。通用描述只写模型擅长方向或相对定位,不重复 tags 已表达的固有能力。endpoints 填什么;不要只按文档标题猜路径,也不要漏掉现有 provider 统一前缀(例如部分 PPIO 路由实际要走 /async/...)。description 是给智能助手、能力反射与语义检索使用的参数说明,正式参数界面不得渲染它;给用户看的解释、限制和操作后果必须写入 tooltip,并按 henji-ui-surface 通过标签旁的说明入口呈现。两者受众不同,可以同时存在,界面不得用 description 兜底 tooltip。*_url,参数面板也禁止呈现手动 URL 文本框。普通已有素材(角色图、风格参考图、视频、音频、PDF 等)使用对应上传类型或现有上传按钮;由 Electron 主进程调用当前供应商官方上传服务并把返回 URL 写入请求,业务 UI 不直连上传 API。cref / sref / dref / mask_url / pdf_url)必须通过 runtimeConstraints.mediaFields 声明媒体类型,让公共预处理层识别并上传;禁止在上传运行时添加模型 ID 分支。若供应商没有对应官方上传能力,不得让用户自行填写公网链接,应暂停该能力并向用户确认。ParamRenderer 与画布 NodeParamControl 必须能消费同一上传 schema。composite / 特殊面板;面板内部仍复用现有 Ui*、标准参数控件、上传与排序能力,不重做比例选择器、下拉、开关或文件上传。mode / channel 明示切换;独立模态、完全不同的用户目标或无法共存的生命周期才保留多个模型卡片。平台文档分成多页不等于产品必须分成多个模型。role: 'channel',且字段名写 sharedFieldText('apiChannel')(显示为“渠道”)。二者是双向绑定,缺一边都会被 modelParamConventionValidator 在模型注册时拦下。生成面板只按 role 决定主选择器提前渲染,不再从参数名文案反推。渠道参数必须严格排在所有其他参数之前,包括分辨率、比例和模式;这条规则优先于“模式优先”。sharedOptionText('regular' | 'official') 只在恰好两档、且正好是“第三方 vs 官方”时才对得上(目前只有 APIMart 三个模型适用),不是通用约定,不要硬套。role: 'mode'(不要求 order 为 1,字段名不受上面那条约束)。音频“声道”不属于产品渠道,不要声明 role。meta.aliases 只是第一步:旧入口隐含的模式/渠道写入 meta.aliasParamDefaults,旧参数 ID 迁移写入 meta.aliasParamMappings。四个消费方必须一起验证:生成页初始值、模型切换迁移、画布节点参数、主进程 RequestBuilder;禁止出现“能解析旧 ID,但旧工程悄悄换了渠道或丢参数”。GenerationNodeShell -> NodeInputRows -> NodeParamRows 自动读取模型 schema。只改模型参数定义、显隐、联动、计价或请求映射时,默认不修改 src/features/canvas/**,也不加载 canvas-node-builder。只有新增/改造节点 DOM、端口、节点注册、节点专属交互,或现有 ParamRenderer / NodeParamControl 无法共同表达新参数类型时,才进入画布节点工作流。ParamRenderer 与画布的 NodeParamControl 都能消费同一 schema 和同一值结构;优先修正共享参数面板能力,不为画布复制一份模型专属实现。output_format / outputFormat,也不向 API 传递该字段;即使文档支持,也先按“不显示且不请求”处理,除非用户后续明确推翻这条约定。uploadedFilePaths/uploadedVideoFilePaths,画布节点实时值是 images/videos,对话/工具面板实时上传状态是 uploadedImages/uploadedVideos。只查其中一个键会导致另外两个场景判断错误(参数该隐藏没隐藏、画布里 mode 自动切换不触发、计价按错分支)。优先复用 packages/ai-sdk/src/catalog/shared/mediaPresence.ts 的 hasUploadedImage/hasUploadedVideo/countUploadedImages/countUploadedVideos(KIE/PPIO 模型可从同目录 ./mediaSources 导入,已重导出)。GenerationService -> src/commands/aiRuntime.ts -> src/platform/* -> electron/preload/index.ts -> electron/main/ipc/ai-runtime.ts -> electron/main/services/ai-runtime/** 宿主薄壳 -> @henjicc/ai-sdk。packages/ai-sdk/src/catalog/ 的真实 endpoints.selector 与 request.builder,两者都允许同步或异步返回;共享 helper 可以正常 import,但必须位于 SDK 内且满足可移植性检查,禁止反向依赖应用层。npm run gen:catalog,并对 catalog 中的真实模型执行 selector/builder 请求契约测试;异步 builder 必须在测试和主进程调用侧统一 await。meta.tags 是否完整覆盖模型对外宣称的能力(如 start-end-frame、reference-mode、motion-control);default 与 UI 首次渲染显示值必须一致;param.default;autoSwitch/reset 是否在初始化阶段覆盖了默认值。.model.ts 的参数、枚举、输入限制或价格,必须在同一次改动里同步 packages/ai-sdk/docs/model-adaptation/<模型名>/<模型名>_<供应商名>.md,并更新该文件与 README.md 头部的「最后更新」;下线模型时同步删除文档并从 README.md 清单表移除。只改代码不改文档,等于给下一次调研留下错误依据。文档采集手册.md 同步官方 fixture、事件矩阵、正反精确测试与断牙验证;格式和目录约定见 packages/ai-sdk/tests/fixtures/README.md,不得凭空手写样本。docs/rules/testing.md 选择最小验证:模型定义改动通常运行 catalog 生成、model i18n 与对应参数/请求构建精确测试,不默认跑全量 lint。npm run electron:build;构建后需要验收真实桌面能力时再跑 npm run electron:smoke。description 已作为助手语义保留但未进入正式界面,所有用户可见说明均通过 tooltip 呈现。npm run electron:dev。© henjicc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 11 other files (references) in .codex/skills/henji-model-adaptation of henjicc/Henji-AI.
Open the folder on GitHubat commit c8107e0
Henji Model Adaptation 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 |
|---|---|---|---|---|---|---|
| Henji Model Adaptation this skillhenjicc/Henji-AI | 254 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| ToolJet Marketplace Plugin BuilderToolJet/ToolJet | 41k | — | ~2.1k | Automated safety check: Pass | AGPL-3.0 | |
| Step Partsearthtojake/text-to-cad | 19k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| OpenAPI to MCP Servermcp-use/mcp-use | 11k | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Use Yaakmountain-loop/yaak | 19k | — | ~1.9k | Automated safety check: Pass | MIT | |
| API DesignerJeffallan/claude-skills | 12k | 1 repos | ~2k | Automated safety check: Pass | MIT |
ToolJet/ToolJet
Turns an API description, such as an OpenAPI file or a Postman collection, into a connector plugin for ToolJet's marketplace and checks it with the repo's validator.
earthtojake/text-to-cad
Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers…
mcp-use/mcp-use
Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.
mountain-loop/yaak
A skill your agent uses when the user mentions Yaak, a Yaak workspace, or the yaak command, or asks to call, hit, or smoke test HTTP/REST endpoints, save or organize API requests for reuse or manual…
Jeffallan/claude-skills
Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.
huangruiteng/CS-Notes
Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script.
henjicc/Henji-AI
Henji-AI 画布(ReactFlow)新增/改造节点时使用。指导如何选择普通生成节点、节点内工具工作台、标准行拼装或纯展示节点,如何声明 CanvasNodeDefinition,以及如何让遮罩、打光、镜头等特殊交互各自不同但保持统一骨架。普通模型 schema 会被标准生成节点自动读取;只改供应商、模型参数、显隐、计价或请求构建时不使用本 skill。
henjicc/Henji-AI
为 Henji-AI 新增、修改或迁移应用能力,并完成内置 Pi 与现代 MCP 的同源适配。新增工作区、页面、浮层或工具入口、用户数据、设置、业务操作、长任务、稳定引用、权限、宿主上下文、能力搜索,或清理旧 HostCommand/HostQuery/Agent 工具时使用;纯样式、布局、文案和不改变业务能力的组件调整不使用本 skill。
henjicc/Henji-AI
Henji-AI 新建或改造任何界面/页面骨架/面板/弹窗/侧栏/设置分区/节点 UI,或调整按钮层级、分隔线、颜色、图标、毛玻璃、动画、层级时使用。主文件涵盖“石墨”设计系统速览(主题引擎与语义令牌、按钮五档默认静默、淡强调底选中态、尺寸档位)、页面骨架的横向条带上限与命令带、表面层级(surface/elevation)铁律、五级容器词汇表、分隔线准入、选项集合静息态与选中态词汇表、必须复用…
henjicc/Henji-AI
在痕迹AI修图、调色、抠出或选中主体、移除物体、修补瑕疵、编辑图层与蒙版、导出图片或流转图片产物时使用。视频时间线与成片用 video-edit-workbench;写代码画面用 video-edit-code-creation。
henjicc/Henji-AI
在剪辑里设计、编写或修改代码素材(动态图形、标题、花字、模板、滤镜),统一风格、编排动画、放入时间线并取帧审查时使用。普通剪辑、媒体生成和进度查询不触发。
henjicc/Henji-AI
在痕迹AI剪辑工作台做粗剪、整理时间线、节奏、字幕、配乐与音量、响度、调色、转场、多机位、竖版改画幅、导出,或把生成、画布、图片文档、口播产物放进剪辑及把剪辑帧送到其他工作区时使用。写代码画面用 video-edit-code-creation;单独写代码素材不触发本技能。
Categories
面向 Henji-AI 的模型与供应商调研、文档整理、参数体验和适配工作流。用于“新增供应商”“给现有供应商新增模型”“模型和供应商都要新增”“核查 API/价格/平台别名”“校对参数顺序、通用交互、隐藏参数或默认请求值”这类需求;先输出确认清单,用户确认后再实施。普通模型 schema 会被标准画布节点自动读取,不因模型会出现在画布里而自动触发节点开发。. Henji Model Adaptation is an agent skill from henjicc/Henji-AI.
Henji Model Adaptation fits situations like: tasks that involve OpenAPI specifications.
Run `npx skills add henjicc/Henji-AI --skill henji-model-adaptation -a claude-code`. Or copy the skill folder (.codex/skills/henji-model-adaptation in henjicc/Henji-AI) into .claude/skills/henji-model-adaptation in your project. Claude Code loads it when a task matches its description.
Run `npx skills add henjicc/Henji-AI --skill henji-model-adaptation -a codex`. Or copy the skill folder (.codex/skills/henji-model-adaptation in henjicc/Henji-AI) into .agents/skills/henji-model-adaptation in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add henjicc/Henji-AI --skill henji-model-adaptation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/henji-model-adaptation, .gemini/skills/henji-model-adaptation, .github/skills/henji-model-adaptation and .opencode/skills/henji-model-adaptation in your project.
Going by SKILL.md and its folder, Henji Model Adaptation needs the command-line tools its instructions call (npm).
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Henji Model Adaptation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Henji Model Adaptation: ToolJet Marketplace Plugin Builder (ToolJet/ToolJet, 41k stars), Step Parts (earthtojake/text-to-cad, 19k stars), OpenAPI to MCP Server (mcp-use/mcp-use, 11k stars) and Use Yaak (mountain-loop/yaak, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
henjicc (a GitHub user) maintains it in henjicc/Henji-AI, which has 254 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 11, 2026.
Source: henjicc/Henji-AI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.