メニュー
Fetch full text for a Tiangong KB course document through the Tiangong AI CLI. Use when a task has a course document_id and tags and needs the complete processed text.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Fetch and atomically save verified academic-paper PDFs from legal open-access sources using a DOI or exact title, with access/license provenance and an adjacent hash manifest. Use for automatic OA retrieval or for a publisher URL that must first be resolved to a DOI and may then require an explicitly selected Chrome or optional CloakBrowser user-authorized browser handoff; supports an injectable transport for embedding in research systems.
Search Tiangong knowledge-base course sources through the Tiangong AI CLI. Use for courseware, lessons, teaching material, Qinghua/Tsinghua humanities archive course collections, and evidence-grounded education-history retrieval. This skill searches only the course source.
Search Tiangong knowledge-base general education sources through the Tiangong AI CLI. Use for broad education knowledge sources only. This skill searches only the edu source, not course or textbook.
Search Tiangong knowledge-base ESG disclosures through the Tiangong AI CLI. Use for environmental, social, and governance reports and disclosure evidence only. This skill searches only the ESG source.
Upload local files or folders into Tiangong KB through the Tiangong AI CLI. Use when a user asks an agent to ingest documents into a KB collection, list uploadable collections, or explain ingest duplicate/status results.
Search Tiangong knowledge-base patent sources through the Tiangong AI CLI. Use for inventions, technical routes, claims, patent evidence, and prior art. This skill searches only the patent source, not sci or report.
| name | tiangong-kb-course-fulltext-fetch |
| description | Fetch full text for a Tiangong KB course document through the Tiangong AI CLI. Use when a task has a course document_id and tags and needs the complete processed text. |
Use this skill when the task has a Tiangong KB course document_id and tags,
and needs the full processed text for that document.
Always call the Tiangong AI CLI:
npx @tiangong-ai/cli@0.0.19 kb course fulltext --document-id <document_id> --tags <tags>
Do not call S3, NAS, Supabase, Pinecone, or OpenSearch directly from the skill. The CLI owns the S3 path rule, list/get behavior, and AWS SDK credential handling.
npx @tiangong-ai/cli@0.0.19; users do not need a
preinstalled CLI. Set TIANGONG_AI_CLI or TIANGONG_AI_CLI_BIN only to
override the CLI entrypoint.AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY,
AWS_SESSION_TOKEN, AWS_PROFILE, AWS_REGION, or AWS_DEFAULT_REGION.env_file. Loaded dotenv values
only fill unset environment variables; explicit JSON fields such as bucket,
prefix, and region are passed as CLI flags and take precedence. Never
print secret values.Pass the course document_id and tags:
./scripts/course_fulltext_fetch.sh '{
"document_id": "000125ed-c4d9-4fe3-9383-281162406d66",
"tags": "thu_humanities"
}'
The wrapper calls:
npx @tiangong-ai/cli@0.0.19 kb course fulltext --document-id <document_id> --tags <tags>
To save the full text:
./scripts/course_fulltext_fetch.sh '{
"document_id": "000125ed-c4d9-4fe3-9383-281162406d66",
"tags": "thu_humanities"
}' ./fulltext.txt
To return CLI metadata and text as JSON:
./scripts/course_fulltext_fetch.sh '{
"document_id": "000125ed-c4d9-4fe3-9383-281162406d66",
"tags": "thu_humanities",
"json": true
}'
document_id or documentId: required course document id.tags or tag: required course tag, such as thu_humanities.output_file: optional output path. The second wrapper argument takes
precedence when both are provided.env_file: optional dotenv file to load before calling the CLI.json: true to return the CLI JSON payload instead of plain text.bucket, prefix, region: optional overrides for the CLI command.When using the returned text in reader-facing prose, cite source titles or paths when useful, but do not describe internal S3 paths, AWS credentials, or retrieval mechanics unless the user asks for implementation details.