tiangong-ai/skills

44 resources in this repository

🎯44Skills

🎯Skills44

Send emails through an SMTP server using environment-based credentials and message fields. Use when tasks need reliable outbound email delivery (single or repeated recipients), SMTP connectivity ch... Part of tiangong-ai/skills.

email-smtp-send

🎯email-imap-fetch🎯Skill

A skill for near-real-time IMAP mailbox monitoring with the IDLE command, supporting multi-account inbox ingestion and automatic webhook delivery to OpenClaw automation.

email-imap-fetch

🎯ai-tech-rss-fetch🎯Skill

A Claude Code skill for subscribing to AI and tech RSS feeds, syncing entries with deduplication, and persisting normalized metadata into SQLite using Python tooling.

ai-tech-rss-fetch

🎯dify-knowledge-base-search🎯Skill

A Claude Code skill for searching and retrieving chunks from Dify knowledge bases using the Dify dataset retrieve API, useful for integrating or debugging knowledge base retrieval workflows.

dify-knowledge-base-search

🎯email-imap-full-fetch🎯Skill

Fetches full email MIME content and attachment files from an IMAP server by message reference, supporting lookup by Message-Id or UID with automatic file saving for .eml and attachments.

email-imap-full-fetch

🎯synology-file-station🎯Skill

Operates Synology DSM File Station via WebAPI for scripted NAS file workflows including listing, search, folder creation, rename, copy/move, delete, upload/download, and archive extraction. Reads connection credentials from environment variables and returns JSON output for automation pipelines.

synology-file-station

🎯document-granular-decompose🎯Skill

A skill that uploads local documents (PDF, Office, images) to the TianGong AI Unstructure API for fine-grained MinerU parsing and returns plain fulltext content for downstream chunking, search, or summarization.

document-granular-decompose

🎯sci-journals-hybrid-search🎯Skill

A skill for performing hybrid search over scientific journal chunks using a Supabase edge function, with support for journal/date filters, chunk expansion, and metadata retrieval.

sci-journals-hybrid-search

🎯ai-tech-summary🎯Skill

A skill that retrieves time-windowed RSS evidence from SQLite and uses RAG to produce AI technology summaries for daily, weekly, monthly, or custom-range digests.

ai-tech-summary

🎯ai-tech-fulltext-fetch🎯Skill

A Claude Code skill that fetches and persists article full text for RSS entries stored in SQLite, enabling downstream indexing, retrieval, and summarization of tech articles.

ai-tech-fulltext-fetch

🎯sustainability-rss-fetch🎯Skill

Ingest all sustainability journal RSS entries into a dedicated RSS SQLite database first, keyed by DOI, then mark relevance and prune non-relevant rows to DOI-only. Use when building a DOI-first ingestion pipeline with mandatory full ingestion before topic filtering.

sustainability-rss-fetch

🎯sustainability-summary🎯Skill

Retrieve time-windowed relevant sustainability RSS evidence from the RSS metadata SQLite database and optionally join DOI-keyed enriched content from a separate fulltext SQLite database. Use when generating grounded daily, weekly, monthly, or custom-range digests after relevance labeling.

sustainability-summary

🎯email-imap-append🎯Skill

Composes RFC 5322 draft email messages with optional attachments and appends them to an IMAP mailbox (typically Drafts) without sending, enabling human review before dispatch.

email-imap-append

🎯sustainability-fulltext-fetch🎯Skill

Fetch and persist content for DOI-keyed sustainability RSS entries from a separate fulltext SQLite DB, using OpenAlex/Semantic Scholar API metadata first and webpage fulltext extraction as fallback. Use when building resilient DOI-first content enrichment after relevance labeling.

sustainability-fulltext-fetch

🎯notebooklm🎯Skill

Part of the Tiangong AI Skills repository, providing reusable skills including scientific journal hybrid search and Dify knowledge base integration, installable via the skills CLI for Claude Code and Codex with both project and global scope support.

notebooklm

🎯eceee-news-fulltext-fetch🎯Skill

A skill that discovers article URLs from the eceee.org news archive and extracts full article text into SQLite with retry-safe incremental sync. Useful for building a searchable corpus of European energy efficiency news.

eceee-news-fulltext-fetch

🎯figshare-data-download🎯Skill

A skill for downloading Figshare dataset files that bypasses anti-bot checks by using a browser-only workflow, handling DOI URL resolution, download triggers, and file verification without relying on curl or web_fetch.

figshare-data-download

🎯fetch-abstract-to-kb🎯Skill

A skill that provides two database operations for backfilling journal abstracts: fetching DOI candidates from a PostgreSQL journals table and batch-updating abstracts by DOI.

fetch-abstract-to-kb

🎯dify-knowledge-base-upload🎯Skill

Uploads local files to a Dify pipeline knowledge base through published datasource flows, with optional metadata field mapping. Solves the issue where standard Dify document creation APIs return completed with zero chunks.

dify-knowledge-base-upload

🎯github-contribution-period-analysis🎯Skill

Analyzes a GitHub user's code contribution activity within a specified UTC time window and generates a Markdown report focused on practical contributions, including authored merged PRs and commits across public and private repositories.

github-contribution-period-analysis

🎯fetch-meta-from-kb🎯Skill

A skill that fetches recent journal paper metadata (DOI, title, abstract, date) from a PostgreSQL knowledge base, returning filtered JSON arrays for downstream processing without LLM filtering.

fetch-meta-from-kb

🎯convert-image-to-jpg🎯Skill

Converts local image files from formats like HEIC, PNG, TIFF, WebP, BMP, GIF, and AVIF into JPG with configurable DPI settings. Supports single file and recursive directory conversion using ImageMagick or macOS sips as the backend.

convert-image-to-jpg

🎯fetch-meta-to-kb🎯Skill

A skill that fetches journal article metadata from Crossref after a specified date and inserts them into a PostgreSQL knowledge base with DOI-based deduplication.

fetch-meta-to-kb

🎯gdelt-doc-search🎯Skill

Skill

gdelt-doc-search

🎯tiangong-kb-sci-search🎯Skill

Skill

tiangong-kb-sci-search

🎯openaq-data-fetch🎯Skill

Skill

openaq-data-fetch

🎯bluesky-cascade-fetch🎯Skill

Skill