github.com/labring/FastGPT
| Skill | Added | Review |
|---|---|---|
add-permission .agents/skills/support/permission/add-permission/SKILL.md 为 FastGPT 新资源接入权限管理。当用户需要为新资源(如 AgentSkill、Plugin 等)添加权限支持时触发。 | 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
api-development .agents/skills/system/api-development/SKILL.md FastGPT API 开发规范。重点强调使用 zod schema 定义入参和出参,在 API 文档中声明路由信息,编写对应的 OpenAPI 文档,以及在 API 路由中使用 schema.parse 进行验证。 | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
ci-workflow-sync .agents/skills/system/ci-workflow-sync/SKILL.md FastGPT CI workflow 双轨同步。当用户修改或新增 .github/workflows/ 下的 GitHub Actions workflow 时必须触发:同步更新 .forgejo/workflows/ 对应文件保持功能一致,或判断是否需要新建 Forgejo 版本。涉及 CI、GitHub Actions、Forgejo Actions、镜像构建、container registry、artifact、workflow yaml 改动、build-* workflow、test-* workflow 时也使用此技能。即使用户只提到"改一下 CI"或"加个 workflow"也应触发。 | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3b0ad50 | |
deprecate-workflow-node .agents/skills/core/workflow/deprecate_workflow_node/SKILL.md 当用户需要弃用一个工作流节点(保留向后兼容、隐藏出模板面板)时触发该 skill。FastGPT 工作流节点的弃用流程标准化封装,覆盖模板、Dispatcher、UI 引用等所有需要改动的位置。 | 66 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
doc-i18n .agents/skills/doc/i18n/SKILL.md 将 FastGPT 文档从中文翻译为面向北美用户的英文。当用户提到翻译文档、i18n、国际化、translate docs、新增/修改了中文文档需要同步英文版时,使用此 skill。也适用于用户要求检查文档翻译缺失、批量翻译、或对比中英文文档差异的场景。 | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
fastgpt-backport-pr .agents/skills/system/fastgpt-backport-pr/SKILL.md 将 FastGPT 已合入的 GitHub PR cherry-pick(pick、回补、backport)到用户明确提供的维护分支,验证后直接推送并对齐维护版 Pro 子模块;随后更新对应进行中版本的中英文文档,单独向 upstream/main 提交文档 PR。不用于合并源 PR 或执行发布。 | 64 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3b0ad50 | |
fastgpt-docker-deploy document/public/deploy/SKILL.md FastGPT Docker Compose self-hosting deployment workflow. Use when a user asks an AI agent to deploy FastGPT with Docker by referencing /deploy/SKILL.md, including creating an empty fastgpt directory, running the install script in non-interactive mode, starting Docker Compose, monitoring service health, troubleshooting compose issues, and returning the access URL plus root credentials and next steps. | 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
fastgpt-integration-test-case .agents/skills/system/fastgpt-integration-test-case/SKILL.md 为 FastGPT 生成、维护或合并去重按业务归档的集成测试用例 Markdown,以一个业务验收目标覆盖多个相关场景,支持接口、UI、端到端和服务集成测试及单页阅读器。不用于单独编写 Vitest 测试或系统升级迁移用例。 | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
fastgpt-integration-test-runner .agents/skills/system/fastgpt-integration-test-runner/SKILL.md 筛选并执行 FastGPT 集成用例,优先运行 Node 或无头 Playwright 脚本,由 AI 执行未覆盖项并复核脚本失败,逐项更新临时 HTML 报告及执行方、说明和证据。适用于已有用例执行、变更回归和复测;仅编写用例或单元测试时不使用。 | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
fastgpt-release-docs .agents/skills/doc/fastgpt-release-docs/SKILL.md 仅在用户明确调用本 Skill 时,为 FastGPT 编写或更新指定版本的中英文 MDX 更新说明。支持 v4.17.3、4.17.3 或 4173 等版本输入,对比上一正式版本,按功能领域归并改动,先写中文再调用 doc-i18n 翻译英文。不自动用于普通代码任务或一般文档编辑。 | 66 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3b0ad50 | |
i18n-translate .agents/skills/system/i18n-translate/SKILL.md Translate one, multiple, or all explicitly requested FastGPT i18next namespace JSON files from the completed Simplified Chinese source into every supported target locale, with product-language research and structural validation. Use only when the user explicitly invokes `$i18n-translate` and identifies namespace names, files under `packages/web/i18n/zh-CN/`, or all namespaces; never trigger implicitly for ordinary i18n, copywriting, or documentation work. | 77 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
prompt-optimize .agents/skills/core/ai/prompt_optimize/SKILL.md Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks. | 53 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
pr-review .agents/skills/system/pr-review/SKILL.md 显式调用 $pr-review 时,结合 PR 评论审查 FastGPT PR 或本地分支,审查需求与实现方案,独立检查功能正确性、重复冗余、可维护性与仓库规范,复查旧问题修复及新增风险。默认在含 pro 子模块的独立 worktree 中审查;人工调用只输出报告,已授权的自动任务提交 COMMENT Review。 | 69 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 3b0ad50 | |
system-migration-development .agents/skills/system/system-migration-development/SKILL.md 为 FastGPT 新增、修改或审查自动系统升级脚本及其注册信息。涉及系统迁移、升级任务、启动迁移、migration registry、checkpoint、全量重跑、独立模式、进度或失败数据时使用;普通业务更新和未接入自动升级框架的一次性手工清洗不使用。 | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 | |
test-case .agents/skills/system/test-case/SKILL.md 当用户需要编写一个单元测试时,触发该 skill,编写单元测试。 | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 3b0ad50 |