web-search
Discover a bounded set of fresh web source candidates from one explicit search query, preserve provider evidence and reported cost, and prepare source selection for fetching and research.
- License 许可
- Apache-2.0
- 所属仓库
- runxhq/runx
- 最近更新
- 2026-11-14
- Stars
- ★ 103
- Forks
- 108
01 前言 Front Matter
- name
- web-search
- description
- Discover a bounded set of fresh web source candidates from one explicit search query, preserve provider evidence and reported cost, and prepare source selection for fetching and research.
02 资源文件 12
- 参考文档eval_queries.json2.1 KB
- 参考文档evals/evals.json766 B
- 参考文档evals/files/bounded-query.json274 B
- 参考文档references/catalog.md142 B
- 参考文档run.yaml4.5 KB
- 参考文档tests/bounded-discovery.yaml1.0 KB
- 参考文档tests/composes-in-workflow.yaml97 B
- 参考文档tests/empty-discovery.yaml750 B
- 参考文档tests/invalid-publication-time-stops-before-provider.yaml230 B
- 参考文档tests/unusable-candidates.yaml949 B
- 脚本web-search.mjs2.7 KB
- 脚本web-search.test.mjs721 B
03 SKILL.md 正文
Web search
Discover sources for a specific question. The initial search method uses the
selected Exa account for one query and at most 20 results. It normalizes source
identity, removes exact duplicate URLs, rejects malformed non-web candidates
and preserves the provider operation alongside the result. It does not silently
choose another provider, execute extra queries, fetch full pages or write a
research conclusion. Exa is the initial executable backend; additional backends
need their own declared operations and result mapping.
Search procedure
Choose one concrete information need per query. Include the relevant entity, decision and discriminating terms. Prefer direct evidence: official documentation, first-party announcements, original reports or research. Use domain restrictions when the task requires authoritative sources. Use publication-date bounds for a time-sensitive question, remembering that a publication date is not necessarily the event date. Do not add filters that exclude the contrary evidence you need.
Limit queries and results to the caller's actual budget. Search may consume paid credits. The result includes reported cost when available; missing cost remains unknown. The result cap is not a monetary spending limit. This package adds no billing authority or automatic retry after an uncertain paid request.
Result and composition
search_result contains the query, provider request ID, usable source candidates,
discard counts and reported cost. provider_operation retains the exact native
provider evidence and account binding. An empty provider result returns
no_results; a nonempty response with no usable candidates returns
unusable_results. Neither means the question has been researched exhaustively.
Titles, dates and any returned excerpt are discovery metadata, not verified claims
or full page content. Fetch selected URLs through web-fetch and feed the actual
retrieved packets to research. Check contradictions, source diversity and
coverage before drawing conclusions. research over supplied evidence does not
perform fresh discovery by itself. Reuse adequate existing evidence rather than
repeating a paid search.
04 同仓库更多 Skills
webhook-handoff
Validate a runx execution context and deliver a governed payload once to an n8n Cloud workflow webhook or a Zapier Catch Hook, with exact approval and the receiver's acknowledgement receipted.
web-fetch
Fetch and extract one public web source, optionally restrict its hosts, and return the content by digest with full provenance.
vuln-triage
Prioritize actual exact-coordinate vulnerability findings, preserve unknown exposure and partial coverage, and return practical remediation or an unsent advisory draft.
Govern X (Twitter) account work through three lanes: evidence reads, typed act plans for posting and account hygiene, and gated execution with per-act provider evidence. Nothing reaches a live timeline or mutates an account without an explicit approval recorded in the receipt.
team-delegate
Divide bounded work across an operator-selected team and return exact member assignments with source context, scope ceilings and acceptance checks.
taste-profile
Build a scoped taste profile packet from examples, preferences, and explicit dislikes so downstream agents can make style decisions without inventing the user's taste.