Update to Tavily

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,102 +1,58 @@
 ---
 name: tavily-research
 description: |
-  Conduct comprehensive AI-powered research with citations via the Tavily CLI. Use this skill when the user wants deep research, a detailed report, a comparison, market analysis, literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", "what does the market look like for", or needs multi-source synthesis with explicit citations. Returns a structured report grounded in web sources. Takes 30-120 seconds. For quick fact-finding, use tavily-search instead.
+  Research a topic in depth with Tavily. Use this skill when a question needs many sources gathered and weighed together: analysing a market, policy, technology or trend, comparing options across several criteria, reviewing the literature, or any request to research, investigate or analyze something in depth. A single fact or answer to find, even one with many clues, is a tavily-search task. For one CRM record use tavily-entity, for a table of matches use tavily-list, and for a recurring check use tavily-monitor.
 allowed-tools: Bash(tvly *)
 ---
 
-# tavily research
+# Tavily research
 
-AI-powered deep research that gathers sources, analyzes them, and produces a cited report. Takes 30-120 seconds.
+Use this when the answer has to be built from many sources. A single fact or
+answer to find is a search: follow `tavily-search` instead.
 
-## Before running
+Search and read pages as `tavily-search` describes. Load it only if it isn't
+loaded yet.
 
-Research requires authentication. Run the requested command directly when
-`tvly` is already authenticated; do not add a status check to every invocation.
+## Steps
 
-If `tvly` is missing, follow the [tavily-cli setup](../tavily-cli/SKILL.md#setup).
-If an installed CLI reports an authentication error, use `tvly login` for
-authentication only, or `tvly init --skip-skills` when guided verification is
-also useful. Browser-based OAuth is preferred when an interactive user can
-complete it. `--no-browser` prints the sign-in link instead of opening it, but
-still waits for a localhost callback. In an unattended agent or CI environment,
-leave authentication to the user or use a securely provided `TAVILY_API_KEY`.
-Do not start a second login immediately after guided setup has completed.
+### 1. Ask only when the answer would change the research
 
-## When to use
+Ask when a term has two meanings, the user assumed a place, or a name is two
+different entities. Otherwise start.
 
-- You need comprehensive, multi-source analysis
-- The user wants a comparison, market report, or literature review
-- Quick searches aren't enough — you need synthesis with citations
-- Step 5 in the [workflow](../tavily-cli/SKILL.md): search → extract → map → crawl → **research**
+### 2. Split the question
 
-## Quick start
+Split into subtopics that do not overlap and that together cover the question.
+Carry the user's limits with every subtopic: dates, places, and what is out of
+scope. Use 3 subtopics when you are unsure, 4 for a comparison with separate
+criteria, 5 for separate entities, regions or domains, and more only for a
+large set.
 
-```bash
-# Basic research (waits for completion)
-tvly research "competitive landscape of AI code assistants"
+### 3. Research the subtopics together
 
-# Pro model for comprehensive analysis
-tvly research "electric vehicle market analysis" --model pro
+**With subagents:** choose a title of 3 to 6 words, create
+`research_notes/{title}/` and `reports/` in the working directory, and start
+one general-purpose subagent per subtopic in the same turn. Give each the
+subtopic, the key questions, the user's limits, the absolute path of its notes
+file, and this first step: read `references/researcher.md` at its absolute path
+next to this skill.
 
-# Stream results in real-time
-tvly research "AI agent frameworks comparison" --stream
+**On your own:** run each subtopic's searches in parallel, as `tavily-search`
+describes, and extract the main sources for each. Keep the findings and their
+URLs in your context. Don't write notes files.
 
-# Save report to file
-tvly research "fintech trends 2025" --model pro -o fintech-report.json
+### 4. Fill thin parts, then write
 
-# JSON output for agents
-tvly research "quantum computing breakthroughs" --json
-```
+Before writing, run another round for any part of the question that would
+leave its section thin.
 
-## Options
+### 5. Write and deliver the answer
 
-| Option | Description |
-|--------|-------------|
-| `--model` | `mini`, `pro`, or `auto` (default) |
-| `--stream` | Stream results in real-time |
-| `--no-wait` | Return request_id immediately (async) |
-| `--output-schema` | Path to JSON schema for structured output |
-| `--citation-format` | `numbered`, `mla`, `apa`, `chicago` |
-| `--poll-interval` | Seconds between checks (default: 10) |
-| `--timeout` | Max wait seconds (default: 600) |
-| `-o, --output` | Save the JSON response to a file |
-| `--json` | Structured JSON output |
+Follow `references/report-writer.md`. On your own, write it once, as
+your reply. Save it to `reports/{title}.md` only when the user asked for a
+file, and then give the path after the report. With subagents, have one agent
+write `reports/{title}.md` from the notes, then give the user the full report
+in your reply, followed by its path.
 
-## Model selection
-
-| Model | Use for | Speed |
-|-------|---------|-------|
-| `mini` | Single-topic, targeted research | ~30s |
-| `pro` | Comprehensive multi-angle analysis | ~60-120s |
-| `auto` | API chooses based on complexity | Varies |
-
-**Rule of thumb:** "What does X do?" → mini. "X vs Y vs Z" or "best way to..." → pro.
-
-## Async workflow
-
-For long-running research, you can start and poll separately:
-
-```bash
-# Start without waiting
-tvly research "topic" --no-wait --json    # returns request_id
-
-# Check status
-tvly research status <request_id> --json
-
-# Wait for completion
-tvly research poll <request_id> --json -o result.json
-```
-
-## Tips
-
-- **Research takes 30-120 seconds** — use `--stream` to see progress in real-time.
-- **Use `--model pro`** for complex comparisons or multi-faceted topics.
-- **Use `--output-schema`** to get structured JSON output matching a custom schema.
-- **For quick facts**, use `tvly search` instead — research is for deep synthesis.
-- Read from stdin: `echo "query" | tvly research - --json`
-
-## See also
-
-- [tavily-search](../tavily-search/SKILL.md) — quick web search for simple lookups
-- [tavily-crawl](../tavily-crawl/SKILL.md) — bulk extract from a site for your own analysis
+If this conversation already produced a report on the subject, build on it:
+research only what is new or needs checking again.