web-research SKILL.md skillA
web-research from phuetz/code-buddy is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add phuetz/code-buddy/web-research@git:20260617.8591299Pins git:20260617.8591299 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- phuetz/code-buddy
- Path
cowork/.claude/skills/web-research/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260617.8591299, committed Jun 17, 2026
- Size
- 3,873 bytes
- Repository stars
- 48
- License
- a license file GitHub does not identify
Autonomous multi-source web research: fetch several web pages, extract their main content, and synthesize a cited Markdown brief. Use whenever the user wants to research a topic, gather and compare sources, or produce a referenced write-up from the web.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Autonomous web research → cited Markdown brief Gather information from several web pages and synthesize a **cited** Markdown brief. This composes the other skills: it fetches with the bundled libraries (lean, zero install), and for JS-heavy pages it hands off to the **`web-automate`** skill (Playwright); you can also feed local files through **`doc-ingest`**. Work in **visible steps** and **never fabricate** — every claim must trace to a fetched source. ## Backends - **Lean (default, no install):** `urllib` (stdlib) + the bundled `beautifulsoup4` + `lxml` read static pages — `python3 -c "import bs4, lxml"`. - **JS-rendered pages:** if the lean fetch returns little/no text (SPA), use the **`web-automate`** skill to render with Playwright and grab the DOM text. ## Workflow (one step at a time) 1. **Plan**: write the research question and a short list of candidate URLs (or use `web-automate` to scrape a search-results page for links first). 2. **Fetch + extract** each source: a short Python script (heredoc via `bash`) that downloads the page, strips `script`/`style`/nav, and keeps the main text — print each source's URL + a length so progress is visible. …
Read the whole file at its exact version.
How to install
mdr add phuetz/code-buddy/web-research@sha256:d1c5077bede2f982The line at the top of this page pins the label git:20260617.8591299, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_nx5qc5z6ef2fepwo)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jun 17, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3873 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
phuetz/code-buddy · 48 stars · license a license file GitHub does not identify · pushed 2026-10-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nx5qc5z6ef2fepwo GET https://markdownregistry.com/api/v1/resolve?ref=phuetz/code-buddy/web-research GET https://markdownregistry.com/api/v1/blob/d1c5077bede2f982ff2a449c2506a448844ce6f1e827b17b69adc02d23d0369a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from phuetz/code-buddy
Every file in phuetz/code-buddy