59 published skills
- ▌ AI Tech Summary · tiangong-ai bundleRetrieve time-windowed RSS evidence from SQLite and let the agent produce final summaries using RAG over selected records and fields. Use when generating daily, weekly, monthly, or custom-range AI tech digests directly in agent responses instead of fixed template reports.
- ▌ Gdelt Gkg Fetch · tiangong-ai bundleRetrieve bounded GDELT 2.0 Global Knowledge Graph rows through the Tiangong CLI from the latest snapshot or an exact UTC range. Use for machine-extracted themes, entities, locations, tone, and document linkage; do not use for article bodies, verified knowledge, event rows, polling, bulk archival mirroring, or causal claims.
- ▌ Usbr Rise Fetch · tiangong-ai bundleDiscover U.S. Bureau of Reclamation RISE catalog item IDs and retrieve bounded operational or water-environment time-series rows through the Tiangong CLI. Use when a task needs official RISE metadata or values for a known place, parameter, reservoir, dam, or project; do not use to infer shortage severity, compliance, causality, governance responsibility, or complete USBR coverage.
- ▌ Email Imap Fetch · tiangong-ai bundleListen for one or more IMAP inboxes with the IDLE command, fetch unread email metadata plus text previews, and forward each message to OpenClaw webhooks. Use when tasks need near-real-time mailbox monitoring, multi-account inbox ingestion via environment variables, and automatic trigger delivery into OpenClaw automation.
- ▌ Fetch Meta To Kb · tiangong-ai bundleFetch journal articles from Crossref published after a user-specified date and insert them into PostgreSQL `journals` with DOI deduplication. Use when incrementally ingesting journal metadata from `journals_issn` into `journals`.
- ▌ Gdelt Doc Search · tiangong-ai bundleSearch GDELT DOC 2.0 through the Tiangong CLI for bounded article metadata, timeline aggregates, or tone-distribution bins using linted GDELT query syntax and optional split domain filters. Use for news-source discovery and trend reconnaissance; do not use for article bodies, raw GDELT event/GKG/mention rows, representative media measurement, fact verification, sentiment ground truth, or causal inference.
- ▌ Domain Onboarding · tiangong-ai bundleHelp users build an initial mental model of an unfamiliar domain when they do not know where to start, do not know what questions to ask, or lack the vocabulary, structure, and learning path needed to explore the field effectively.
- ▌ Email Imap Append · tiangong-ai bundleCompose unsent email drafts (with optional attachments) and append them to an IMAP mailbox via APPEND (typically Drafts) without sending. Use when tasks need to save draft messages for human review, prefill reply templates, stage outbound content inside mailbox folders before manual send, or prepare draft attachments in mailbox-native format.
- ▌ Notebooklm · tiangong-ai bundleNotebookLM CLI wrapper via `python3 {baseDir}/scripts/notebooklm.py` (backed by notebooklm-py). Use for auth, notebooks, chat, sources, notes, sharing, research, and artifact generation/download.
- ▌ Openaq Data Fetch · tiangong-ai bundleDiscover bounded OpenAQ air-quality monitoring locations and retrieve raw, hourly, or daily measurements for one known sensor through the Tiangong CLI. Use when a task needs OpenAQ location, provider, sensor, parameter, license, coverage, or time-series context; do not use for arbitrary API paths, S3 archive downloads, AQI calculation, health or regulatory decisions, forecasting, source attribution, or cross-sensor analysis.
- ▌ Fetch Meta From Kb · tiangong-ai bundleFetch recent `journals` rows directly from PostgreSQL and return a JSON array containing `doi`, `title`, `abstract`, and `date` (filtered by rolling `DAYS` on `created_at`). Use when users need raw paper payloads for downstream processing without LLM filtering or hotspot report generation.
- ▌ Gdelt Events Fetch · tiangong-ai bundleRetrieve bounded GDELT 2.0 Events rows through the Tiangong CLI from the latest snapshot or an exact UTC range. Use for machine-coded event records and source-document linkage; do not use for article bodies, GKG themes, mention-level provenance, event verification, polling, bulk archival mirroring, or causal claims.
- ▌ Tiangong Kb Ingest · tiangong-ai bundleUpload 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.
- ▌ Usgs Water Iv Fetch · tiangong-ai bundleRetrieve USGS WaterServices instantaneous station observations through the Tiangong CLI for one bounded numeric area or an explicit site list and one bounded time selector. Use for streamflow, gage-height, or other USGS time-series measurements with qualifiers; do not use for station discovery, daily values, flood-stage classification, forecasts, hazard advice, or workflows that require guaranteed service after the legacy API retires.
- ▌ Convert Image To Jpg · tiangong-ai bundleConvert local image files from common raster formats into JPG while setting a target DPI (default 96). Use when Codex needs to convert a file or folder of images such as HEIC, HEIF, PNG, TIFF, WebP, BMP, GIF, AVIF, or JPEG into `.jpg` for upload, OCR, archiving, or tools that require JPEG output.
- ▌ Fetch Abstract To Kb · tiangong-ai bundleFetch DOI candidates from PostgreSQL `journals` and batch write `abstract` by DOI. Use when you need DB-only backfill workflow: (1) select newest rows where doi is not empty, author is not empty, and abstract is empty (default limit 10), then (2) write prepared abstract values back in batch by DOI.
- ▌ Gdelt Mentions Fetch · tiangong-ai bundleRetrieve bounded GDELT 2.0 Global Mentions rows through the Tiangong CLI from the latest snapshot or an exact UTC range. Use for mention-level provenance, confidence, and source linkage around coded events; do not use for article bodies, unique-article counts, event verification, polling, bulk archival mirroring, or causal claims.
- ▌ Remove Similar Image · tiangong-ai bundleAnalyze local image files with ImageHash and OpenCV to detect near-duplicate photos and blurry shots, then preview or remove them. Use when Codex needs to clean a photo folder, deduplicate similar images, identify blur, or safely delete/move bad images after reviewing a report.
- ▌ Youtube Video Search · tiangong-ai bundleDiscover bounded public YouTube video metadata through the Tiangong CLI and enrich selected candidates with public details and statistics. Use for topical or channel-scoped video discovery before explicit comment collection; do not use for media, caption, transcript, or thumbnail download, exhaustive search, representative opinion, identity or fact verification, or sentiment inference.
- ▌ Bluesky Cascade Fetch · tiangong-ai bundleFetch bounded public Bluesky post seeds and optional visible reply cascades through the Tiangong CLI. Use for topic, author, custom-feed, or list-feed discussion reconnaissance and reply-topology collection; do not use for private or exhaustive repository/firehose data, media downloads, representative opinion, identity or fact verification, sentiment ground truth, or causal inference.
- ▌ Email Imap Full Fetch · tiangong-ai bundleFetch full email MIME content and attachment files from IMAP by message reference. Use when downstream steps already have a stage-1 mail_ref and need full headers/body/attachments for a specific message, with message_id_norm as the primary lookup key and uid only as fallback.
- ▌ Epa Eis Records Fetch · tiangong-ai bundleRetrieve official U.S. EPA EIS Database result-table metadata through the Tiangong CLI. Use when a task needs Environmental Impact Statement titles, CEQ/provider IDs, document type, dates, agencies, state, detail links, or document-availability cues from a current common search or a precise search URL created in the official UI; do not use to claim linked documents were reviewed or to judge NEPA adequacy, legal sufficiency, environmental effects, compliance, or policy responsibility.
- ▌ Nasa Firms Fire Fetch · tiangong-ai bundleRetrieve bounded NASA FIRMS satellite active-fire and thermal-anomaly point detections through the Tiangong CLI for one reviewed source, known bounding box, and short UTC date window. Use for hotspot screening or candidate fire-location context; do not use for fire perimeters, burned area, confirmed wildfire incidents, cause attribution, emergency alerts, recurring monitoring, or multi-source fusion.
- ▌ Synology File Station · tiangong-ai bundleOperate Synology DSM File Station via WebAPI for major file workflows including listing, search, folder creation, rename, copy/move, delete, upload/download, and archive extract. Use when tasks need scripted NAS file operations with service address, username, and password loaded from environment variables. Note: compress is temporarily unavailable in this skill.
- ▌ AI Tech Fulltext Fetch · tiangong-ai bundleFetch and persist article full text for RSS entries already stored in SQLite by ai-tech-rss-fetch. Use when backfilling or incrementally syncing body text from entries.url or entries.canonical_url into a companion table for downstream indexing, retrieval, or summarization.
- ▌ Figshare Data Download · tiangong-ai bundleDownload Figshare files via browser-only workflow (no web_fetch/curl probing). Use when a user provides a Figshare DOI or ndownloader URL and needs a reliable fetch path that always opens the page in browser, triggers the real download, then copies the downloaded file into a target path.
- ▌ Open Meteo Flood Fetch · tiangong-ai bundleRetrieve daily Open-Meteo GloFAS simulated river-discharge fields through the Tiangong CLI for up to ten known coordinates and one bounded date window, optionally including forecast ensemble members. Use for broad modeled river-flow context or separately governed uncertainty analysis; do not use for gauge observations, named-river lookup, flood alerts or severity, emergency advice, geocoding, commercial public-endpoint use, or causal interpretation.
- ▌ Sustainability Summary · tiangong-ai bundleRetrieve 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.
- ▌ Tiangong Auto Research · tiangong-ai bundleOrchestrate open-ended, multi-source, evidence-backed research in the current native Codex, Claude Code, WorkBuddy, or CodeBuddy host, especially when an ancestor directory contains `.tiangong-research` or the user asks to research, investigate, build on prior outputs, compare evidence, form a conclusion, or produce a reviewed research artifact. Also use for setup, preflight, native producer execution, recovery, independent review, closure, and requests to report Auto Research bugs or suggest capabilities (反馈问题、提交 Issue). In an Auto Research workspace this Skill takes precedence over individual web, news, SCI, report, patent, download, or document Skills unless the user explicitly requests one isolated standalone operation outside the research workflow. Covers Chinese requests such as “研究一下”, “朝这个方向做一做”, “结合已有成果继续研究”, “查资料并形成结论”, and “系统梳理证据”.
- ▌ Tiangong Kb Edu Search · tiangong-ai bundleSearch 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.
- ▌ Tiangong Kb Esg Search · tiangong-ai bundleSearch 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.
- ▌ Tiangong Kb Sci Search · tiangong-ai bundlePerform one isolated owner-requested SCI search outside Tiangong Auto Research, or provide SCI method guidance when Auto Research discovery invokes the locked broker capability. Searches only `sci`. If an ancestor contains `.tiangong-research` and the request is open-ended, multi-source, analytical, builds on prior outputs, or produces a conclusion/artifact, route to `tiangong-auto-research` and do not execute this standalone wrapper. Inside a managed workspace, standalone use requires the user's explicit isolated-query request and `execution_mode=standalone`.
- ▌ Youtube Comments Fetch · tiangong-ai bundleFetch bounded visible public YouTube top-level comments and optional complete-within-limits replies for explicit video IDs through the Tiangong CLI. Use after selecting videos when a task needs public discussion text; do not use for video discovery, private or moderation data, unbounded harvesting, representative opinion, identity or fact verification, demographic inference, or sentiment ground truth.
- ▌ Academic Paper Download · tiangong-ai bundleFetch and atomically save structurally and identity-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.
- ▌ Airnow Hourly Obs Fetch · tiangong-ai bundleRetrieve preliminary U.S. EPA AirNow HourlyAQObs monitoring-site records through the Tiangong CLI for an inclusive UTC-hour window, WGS84 bounding box, and pollutant list. Use for site-hour observations with source-file lineage; do not use for regulatory AQS compliance data, forecasts, health guidance, exposure estimates, or place-name geocoding.
- ▌ Gdelt Web Ngrams Search · tiangong-ai bundleFind news article links containing literal words or short phrases in an explicit GDELT Web NGrams/TOC minute pair through the Tiangong CLI. Use for file-based topic discovery, including an explicitly selected alternative when DOC search is unavailable. Do not use for DOC query operators, sentiment timelines, full article text, relevance ranking, or complete time-range coverage from a single minute.
- ▌ Sustainability Rss Fetch · tiangong-ai bundleIngest 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.
- ▌ Tsinghua Graduate Thesis · tiangong-ai bundleCreate, format, repair, compile, or audit Tsinghua University (清华大学) master's and doctoral theses in LaTeX with a pinned ThuThesis release. Use for 清华研究生学位论文、硕士论文、博士论文的 ThuThesis 配置、格式合规、参考文献、PDF 提交与视觉检查；do not use for undergraduate theses or non-LaTeX authoring.
- ▌ Eceee News Fulltext Fetch · tiangong-ai bundleDiscover article URLs from https://www.eceee.org/all-news/ and extract/persist full article text into SQLite with retry-safe incremental sync. Use when building or maintaining an eceee news fulltext corpus for downstream search, indexing, or summarization.
- ▌ Tiangong Kb Course Search · tiangong-ai bundleSearch 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.
- ▌ Tiangong Kb Patent Search · tiangong-ai bundlePerform one isolated owner-requested Tiangong patent search outside Auto Research, or provide patent-source method guidance for a separately reviewed locked broker capability. Searches only `patent`. If an ancestor contains `.tiangong-research` and the request is open-ended, multi-source, analytical, builds on prior outputs, or produces a conclusion/artifact, route to `tiangong-auto-research` and do not execute this standalone wrapper. Inside a managed workspace, standalone use requires the user's explicit isolated-query request and `execution_mode=standalone`.
- ▌ Tiangong Kb Report Search · tiangong-ai bundlePerform one isolated owner-requested Tiangong report search outside Auto Research, or provide report-source method guidance for a separately reviewed locked broker capability. Searches only `report`. If an ancestor contains `.tiangong-research` and the request is open-ended, multi-source, analytical, builds on prior outputs, or produces a conclusion/artifact, route to `tiangong-auto-research` and do not execute this standalone wrapper. Inside a managed workspace, standalone use requires the user's explicit isolated-query request and `execution_mode=standalone`.
- ▌ Dify Knowledge Base Search · tiangong-ai bundleDify dataset retrieve API for knowledge base chunk search/testing. Use when integrating or debugging Dify knowledge base retrieval requests, retrieval_model options, or response shaping.
- ▌ Dify Knowledge Base Upload · tiangong-ai bundleUpload local files to a Dify pipeline knowledge base through the published pipeline datasource flow and optionally apply existing metadata fields. Use when the target dataset is a published rag_pipeline/local_file knowledge base or ordinary Dify document create APIs return completed with 0 chunks.
- ▌ Federal Register Doc Fetch · tiangong-ai bundleRetrieve bounded official FederalRegister.gov document metadata through the Tiangong CLI, optionally filtered by publication date, term, agency, type, topic, docket, or RIN. Use to identify notices, proposed rules, final rules, or presidential documents; do not use for document bodies, docket comments, legal interpretation, current-force determinations, or compliance advice.
- ▌ Usbr Project Records Fetch · tiangong-ai bundleInventory official U.S. Bureau of Reclamation project or program pages and their bounded same-origin record links through the Tiangong CLI. Use when a task starts from one or more known www.usbr.gov URLs and needs page metadata or candidate reports, notices, spreadsheets, or related records; do not use for USBR-wide search, RISE time series, linked-file retrieval, or legal, policy, operating, environmental-effects, or governance conclusions.
- ▌ Document Granular Decompose · tiangong-ai bundleUpload local documents to TianGong AI Unstructure `/mineru_with_images` API for fine-grained parsing and return only plain fulltext content. Use when a task needs document fulltext extraction with `return_txt=true`, strict file-type allowlist validation, API base URL/auth token from environment variables, and optional provider/model overrides.
- ▌ Open Meteo Historical Fetch · tiangong-ai bundleRetrieve bounded Open-Meteo historical weather reanalysis through the Tiangong CLI for up to ten known coordinates, one controlled model, and explicit hourly or daily variables. Use for gap-filled historical temperature, precipitation, humidity, wind, radiation, or shallow-soil context; do not use for station observations, forecasts, climate projections or attribution, geocoding, commercial public-endpoint use, or unreviewed cross-model trend conclusions.
- ▌ Tiangong Kb Textbook Search · tiangong-ai bundleSearch Tiangong knowledge-base textbook sources through the Tiangong AI CLI. Use for textbook-style explanations and reference material only. This skill searches only the textbook source, not course or edu.
- ▌ Apply Environmental Thinking · tiangong-ai bundleUse when the user explicitly asks for an environmental, ecological, or sustainability-informed way of thinking, or when a complex question may turn on coupled systems, boundary choices, displaced consequences, environmental pathways, delayed or irreversible change, uneven exposure, shared-resource tensions, acceptable risk, or responsibility across places and generations—even when the topic itself is not environmental. Brings the foundations, causal reasoning, normative commitments, and intervention logics of environmental science, engineering, ecology, risk, and governance into how the problem is understood, relationships are explained, values are assessed, and action is conceived; distinguishes mechanisms, structural analogies, uncertainty, and value commitments; and develops the response in a coherent environmental disciplinary voice.
- ▌ Open Meteo Air Quality Fetch · tiangong-ai bundleRetrieve hourly modeled Open-Meteo air-quality, aerosol, pollen, UV, or AQI fields through the Tiangong CLI for up to ten known coordinates and one bounded date window. Use for spatially continuous CAMS model context beyond station coverage; do not use for monitoring-station observations, regulatory records, health or exposure advice, geocoding, commercial public-endpoint use, or causal interpretation.
- ▌ Regulationsgov Comments Fetch · tiangong-ai bundleSearch bounded Regulations.gov public-comment metadata through the Tiangong CLI. Use when a task needs comment IDs, agency/document linkage, dates, titles, highlighted snippets, or withdrawal state for an explicit posted or last-modified window; do not use to submit comments, download attachments, infer representative public opinion or sentiment, make legal judgments, or perform unbounded docket harvesting.
- ▌ Sustainability Fulltext Fetch · tiangong-ai bundleFetch 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.
- ▌ Use Thuenv Presentation Style · tiangong-ai bundleUse the bundled structured THUENV Deck template when a user explicitly asks for the Tsinghua University School of Environment presentation style, 清华环境学院 PPT 风格, or the THUENV presentation template. Apply it to new or redesigned presentations through a presentation workflow that supports SVG Deck workspaces.
- ▌ River Outfall Status Visualizer · tiangong-ai bundleAnalyze river outfall Excel workbooks and build report-ready river outfall status visualizations that compare current, normal, 20-year, and 50-year water levels, distinguish left-bank and right-bank outfalls, and identify which outfalls are safe, partially submerged, or fully submerged. Use when Codex needs to turn a river longitudinal-profile or outfall inventory workbook into a briefing chart, status summary, mock dataset, or reusable HTML report.
- ▌ Regulationsgov Attachments Fetch · tiangong-ai bundleDownload bounded public attachment files for exact Regulations.gov comment IDs through the Tiangong CLI. Use when selected regulatory comments have supporting files that must be acquired locally with source lineage, SHA-256 hashes, byte counts, and a manifest; do not use for comment search, arbitrary URL download, file safety certification, text extraction, stance analysis, legal interpretation, or evidence synthesis.
- ▌ Tiangong Kb Course Fulltext Fetch · tiangong-ai bundleFetch 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.
- ▌ Github Contribution Period Analysis · tiangong-ai bundleAnalyze one GitHub user's code contribution activity in a specified UTC time window and generate a Markdown report focused on practical contributions (authored merged PRs, PRs merged by the target user, and authored commits) across accessible public and private repositories. Use when users ask to evaluate real engineering contribution over a period and want evidence links.
- ▌ Regulationsgov Comment Detail Fetch · tiangong-ai bundleRetrieve curated public Regulations.gov comment details for explicit IDs through the Tiangong CLI. Use after comment discovery when a task needs comment text, docket/document linkage, dates, withdrawal or restriction state, organizational context, duplicate count, or optional attachment metadata; do not use to expose named personal-profile fields, download attachment bytes, submit comments, infer public sentiment, or make legal judgments.