deliverables
How to write a document the user will read (report, itinerary, comparison, plan, notes) and save it to their Google Drive. Use when a thread's result is a document rather than a code change.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.1w
- Forks
- 3.0k
01 前言 Front Matter
- name
- deliverables
- description
- How to write a document the user will read (report, itinerary, comparison, plan, notes) and save it to their Google Drive. Use when a thread's result is a document rather than a code change.
03 SKILL.md 正文
Document deliverables
- File format: Write plain Markdown in your working directory named after the subject (
alaska-itinerary.md, neverreport.mdoroutput.md; use CSV for reusable tables). Start with a#title, stay under 14 KB, and avoid HTML or local image paths. - Content: Lead with the recommendation or answer, state key assumptions near the top, compare options in tables, and link sources inline with dates for time-sensitive facts (prices, hours, availability).
- Iterative edits: Update existing files in place rather than creating
-v2copies; git tracks history andsave_to_driveupdates the same Drive file when given the samepath. - Saving to Drive: When
save_to_driveis listed onvoice_agent, call it once the deliverable is final withpath(relative to your working directory) and the#title astitle(Markdown → Doc, CSV → Sheet,.pptx→ Slides). Never save scratch notes or intermediate files, and never upload deliverables viagoogle_drive__tools (usepresent_cardonly to list existing Drive files, events, or email threads). - Reply as a cover note: Because the user sees the Drive link next to your reply, do not paste or summarize the document or mention file names/paths—state only assumptions, what to double-check, and at most one question.
04 同仓库更多 Skills
retail-virtual-tryon
Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image/video generation pipelines, local testing, and evaluation.
retail-product-search
Creates product search agents with semantic search and RAG on Google Cloud (Vector Search on Gemini Enterprise Agent Platform, BigQuery, embeddings). Use when the user wants to "build a product search agent", "create an e-commerce search", "make a shopping assistant", "set up semantic catalog discovery", "ingest products into Vector Search", or "deploy a retail RAG agent". Handles the full pipeline: catalog data ingestion to BigQuery, Gemini Enterprise Agent Platform Vector Search collection setup, ADK agent scaffolding, evaluation, and Cloud Run deployment.
routines
Use for a recurring unattended task (cron; pull data, open a PR, post a digest), or to test/dry-run a routine first. Explains authoring and testing via the routine tool.
policy
Inspect the per-workspace tool-policy overlay (.lha/policies.jsonl) that gates destructive or sensitive tool calls, and tell the user what to change if they want a rule added or removed.
google-workspace
Read/write Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides via the `gws` CLI. Needs an OAuth client or service account configured first. Use for any Google Workspace task.
find-skills
Discover/install NEW agent skills from external sources (skills.sh). Use for capabilities you lack, e.g. "find a skill for X". Do NOT use to list skills you already have; see `<available_skills>`.