# Gen2WebSearch

> Search DuckDuckGo, summarize linked result pages with robust content extraction, and save logs by domain/date using CommonCode FolderNavigator.

- Skill: `davesteadman/gen2websearch` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add davesteadman/gen2websearch`
- Raw SKILL.md: https://api.skillmd.com/api/skills/davesteadman/gen2websearch/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: DaveSteadman (https://skillmd.com/u/davesteadman)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/davesteadman/gen2websearch

---


# Gen2WebSearch

Combines search from LoggedWebSearchPlus with page extraction quality from Gen2WebText, and domain-aware folder resolution via CommonCode FolderNavigator.

## Execution

python gen2_web_search.py <domain> --query <search_query> --max <number> --timeout <seconds> --page-timeout <seconds> --words <number> --sleep-ms <milliseconds> --date-context <none|month_year|year> --date <YYYY-MM-DD>

## Arguments

- domain required alphabetic string only A-Z or a-z
- --query required search query
- --max optional default 8 range 1 to 25
- --timeout optional default 20 range 5 to 60
- --page-timeout optional default 15 range 5 to 60
- --words optional default 200 range 80 to 400
- --sleep-ms optional default 0
- --date-context optional default none. Appends date hints to the query using natural tokens:
	- none uses the query as-is
	- month_year appends `<mon> <yyyy>` (example `feb 2026`)
	- year appends `<yyyy>`
- --date optional reference date in YYYY-MM-DD. Used only to derive date-context tokens; if omitted, today is used.

## Output

On success returns JSON with domain, query, effective_query, date_context, query_reference_date, count, results, log_path, status.
Each result includes title, url, snippet, rank, page_summary, page_words, page_status.

On error returns JSON with domain, query, error, results, count, status.

## Logging

Writes to:
{OPENCLAW_ROOT}/data/datastore3/01-Mine/<domain>/YYYY/MM/DD/{QueryName}.txt

File name is derived from the query text.
Path resolution is handled by `FolderNavigator.from_fixed_point()` and `get_today_path(area="mine", domain=..., create=True)`.