generated: '2026-08-27'
method: searched
source: https://github.com/infiniflow/ragflow-skills
note: >-
  InfiniFlow publishes an Agent Skill of its own in the separate repository infiniflow/ragflow-skills
  ("Skills for RAGFlow dataset api", last pushed 2026-03-24). The SKILL.md and its output-format
  reference are saved here VERBATIM — nothing in this directory was generated by API Evangelist. The
  upstream skill is script-driven (it ships scripts/*.py that call the RAGFlow HTTP API) rather than
  operationId-driven, because RAGFlow publishes no OpenAPI for operationIds to come from.
skills:
- name: ragflow-dataset-ingest
  file: ragflow-dataset-ingest.md
  method: searched
  source: https://github.com/infiniflow/ragflow-skills/blob/main/dataset_skill/SKILL.md
  api: ragflow-http-api
  description: >-
    Use for RAGFlow dataset tasks: create, list, inspect, update, or delete datasets; upload, list,
    update, or delete documents; start or stop parsing; check parse status; retrieve chunks; and list
    configured models.
  requires_env:
  - RAGFLOW_API_URL
  - RAGFLOW_API_KEY
  covers_rest:
  - POST /api/v1/datasets
  - GET /api/v1/datasets
  - PUT /api/v1/datasets/{dataset_id}
  - DELETE /api/v1/datasets
  - POST /api/v1/datasets/{dataset_id}/documents
  - GET /api/v1/datasets/{dataset_id}/documents
  - PATCH /api/v1/datasets/{dataset_id}/documents/{document_id}
  - DELETE /api/v1/datasets/{dataset_id}/documents
  - POST /api/v1/datasets/{dataset_id}/chunks
  - DELETE /api/v1/datasets/{dataset_id}/chunks
  - POST /api/v1/retrieval
  supporting_files:
  - file: ragflow-dataset-ingest-reference.md
    source: https://github.com/infiniflow/ragflow-skills/blob/main/dataset_skill/reference.md
    role: output-format reference the skill instructs the agent to follow
  guardrails_summary: >-
    Requires explicit user confirmation before any delete, resolves fuzzy names to IDs first, never
    fabricates progress percentages, and relays api_error/error/message fields verbatim.
skill_count: 1