From 52126d6b54af47f2a39cdb1a3550ce1ee8e4d5f6 Mon Sep 17 00:00:00 2001 From: aadithyan rajesh Date: Tue, 29 Sep 2026 17:48:35 +0530 Subject: [PATCH 1/2] fix(plugin): add web search highlights guidance --- commands/search-web.md | 2 +- skills/context-dev/SKILL.md | 6 +++--- skills/context-search/SKILL.md | 7 ++++--- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/commands/search-web.md b/commands/search-web.md index c922578..a27d84b 100644 --- a/commands/search-web.md +++ b/commands/search-web.md @@ -7,6 +7,6 @@ description: Search the live web with Context.dev and answer from current source 1. Turn the user's request into a focused search query. Preserve explicit freshness, country, inclusion, and exclusion constraints. 2. Confirm the `context` MCP server is enabled and authenticated. If authentication is required, use the `connect-context-dev` skill. -3. Call `web-search`. Use domain filters when the user requests official or site-specific sources. +3. Call `web-search`. Use domain filters for official or site-specific sources, and enable `highlightsOptions` when the answer needs relevant source passages. 4. Answer from the returned results and cite the source URLs. Clearly separate sourced facts from any inference. 5. If the results are weak, refine the query once rather than inventing an answer. diff --git a/skills/context-dev/SKILL.md b/skills/context-dev/SKILL.md index c76c230..ea5bee2 100644 --- a/skills/context-dev/SKILL.md +++ b/skills/context-dev/SKILL.md @@ -55,7 +55,7 @@ Choose the narrowest operation that directly returns the needed result. | Starting URL to linked pages in one response, up to 500 pages | `POST /web/crawl` | [Crawl](https://docs.context.dev/crawl/overview) | | Starting URL or sitemap to a background crawl, up to 25,000 pages | `POST /batch/submit` with `input.mode: "crawl"` | [Async crawls](https://docs.context.dev/crawl/async) | | URL list to Markdown or HTML in the background, up to 25,000 URLs | `POST /batch/submit` | [Batches](https://docs.context.dev/batches/overview) | -| Search query to ranked web results, optionally with Markdown | `POST /web/search` | [Search](https://docs.context.dev/search/overview) | +| Search query to ranked web results, optionally with Markdown or highlights | `POST /web/search` | [Search](https://docs.context.dev/search/overview) | | Research task to structured JSON and source URLs | `POST /web/answers` | [Answers](https://docs.context.dev/answers/overview) | | Uploaded document up to 50 MiB to Markdown | `POST /parse` | [Parse](https://docs.context.dev/parse/overview) | | Domain, name, work email, ticker, direct URL, or transaction descriptor to company profile | `POST /brand/retrieve` | [Brand](https://docs.context.dev/brand/overview) | @@ -139,10 +139,10 @@ An uncached domain or email lookup with `behavior: "fail"` and `timeoutOpts.mill | Operation | Credits | | --- | --- | -| `POST /web/scrape` | 1, or 2 with `sharedParams.actions`. Highlights +3 when passages are returned; JSON +4 on success; product +1 on success or a missing page; product AI fallback +6 when used; PDF OCR +1 per recovered page on a fresh fetch. 0 when every output fails, except a target 404, which charges the base (+1 with product). | +| `POST /web/scrape` | 1, or 2 with `sharedParams.actions`. Highlights +1 when passages are returned; JSON +4 on success; product +1 on success or a missing page; product AI fallback +6 when used; PDF OCR +1 per recovered page on a fresh fetch. 0 when every output fails, except a target 404, which charges the base (+1 with product). | | `GET /web/urls` | 1, or 2 with `search` | | `POST /web/crawl` | 1 per page; rate-limit weight 10 | -| `POST /web/search` | 1 per 10 results, with or without page content | +| `POST /web/search` | 1 per 10 results; Markdown and highlights each add 1 per 10 results when returned | | `POST /web/answers` | 10 (`fast`) or 100 (`ultra`, the default), charged only on success | | `POST /parse` | 1, plus 1 per OCR-recovered page | | `POST /brand/retrieve`, `GET /web/styleguide` | 10 | diff --git a/skills/context-search/SKILL.md b/skills/context-search/SKILL.md index c756c81..e29e997 100644 --- a/skills/context-search/SKILL.md +++ b/skills/context-search/SKILL.md @@ -14,9 +14,10 @@ already have the exact page URL. 1. Choose `get-news-search` when the request is specifically about one company's coverage; otherwise use `web-search`. 2. Preserve named entities, dates, and constraints in the query or company identifier. 3. Set filters, freshness, or country only when the request calls for them. -4. Use the smallest result count that can answer the question. -5. Prefer authoritative or primary sources when the user asks for official information. -6. Summarize the relevant findings and cite the returned source URLs. +4. Enable `highlightsOptions` when the answer needs relevant source passages, or `markdownOptions` when it needs complete page content. +5. Use the smallest result count that can answer the question. +6. Prefer authoritative or primary sources when the user asks for official information. +7. Summarize the relevant findings and cite the returned source URLs. If the user provides a known URL, use `web-scrape` with `formats: { markdown: true }` instead. If a search result must be read in full, scrape only the selected result rather than every result. From ace31b29906a4086d604e76d2d778cf78c5e97d8 Mon Sep 17 00:00:00 2001 From: aadithyan rajesh Date: Tue, 29 Sep 2026 21:14:39 +0530 Subject: [PATCH 2/2] chore(plugin): bump version to 2.3.0 --- .cursor-plugin/plugin.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.cursor-plugin/plugin.json b/.cursor-plugin/plugin.json index fbdeaf5..fb913e3 100644 --- a/.cursor-plugin/plugin.json +++ b/.cursor-plugin/plugin.json @@ -1,7 +1,7 @@ { "name": "context-dev", "displayName": "Context.dev", - "version": "2.2.0", + "version": "2.3.0", "description": "Search, scrape, crawl, extract, parse, monitor, and process the live web with Context.dev.", "author": { "name": "Context.dev",