12 skills (repositories by labring) · sorted by popularity
Retire a FastGPT workflow node while preserving existing workflows. The skill guides changes to templates, execution handlers, and interface references so the node disappears from creation menus but still loads, runs, and displays a replacement notice.
Translate selected FastGPT interface text files from Simplified Chinese into every supported target locale. Check product terminology and interface context, preserve JSON structure and placeholders, and validate the translated files for consistency.
Develop and review FastGPT APIs with consistent input and output checks, TypeScript types, and OpenAPI documentation. It guides the use of Zod schemas, definitions that describe and validate data, alongside permission checks and reusable structures.
Translate FastGPT documentation from Chinese into natural English for North American readers. Follow the shared product glossary, preserve document structure and code, synchronize navigation files, and check for missing translations or English pages that need updates.
Keep FastGPT build and test workflows aligned across GitHub Actions and Forgejo Actions. Adapt registry destinations, credentials, proxy settings, and platform-specific steps so the corresponding workflows support the internal network environment.
Create or improve AI prompts through a guided conversation about goals, roles, examples, and output formats. Receive a complete, reusable prompt with an explanation of its design, including behavioral boundaries for public-facing AI roles when needed.
Integrate new FastGPT resources, such as AgentSkill or Plugin, with permission management. Choose an integration guide based on resource hierarchy and permission inheritance, locate the relevant code, and review a checklist for missing implementation steps.
Develop and review FastGPT data migration tasks for automatic system upgrades. Define safe reruns, resume points, progress reporting, and failure handling, while checking task order and whether upgrades must block application startup.
Write unit tests for FastGPT code, covering normal behavior, edge cases, and errors. It guides test placement, limits mocks that replace real dependencies, and checks TypeScript errors and coverage, the share of code exercised by tests.
Review FastGPT pull requests or local branch changes by examining actual code differences. Explain behavior changes and affected areas, identify unrelated changes, and report concrete concerns about code quality, consistency with nearby implementations, and missing test coverage.
Review FastGPT pull requests in stages, starting with the intended change and key execution paths. Check security, performance, tests, and compatibility, then organize findings by severity into a review report and line-level comments.
Deploy FastGPT on your own server using its official installation script and Docker Compose, which runs its services together. Check service health and access, investigate deployment problems, and receive the access URL, initial login details, and next steps.