builtbyecho-research
Use when a user asks an agent to do web research, source discovery, citation-backed reporting, page extraction, crawling, or browser-rendered research using the BuiltByEcho Research npm package. Also use when installing, verifying, or demonstrating @builtbyecho/research.
- License 许可
- MIT
- 最近更新
- 2026-06-10
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- builtbyecho-research
- version
- 0.5.2
- metadata
- { "openclaw": { "emoji": "🔎", "install": [ { "id": "builtbyecho-research", "bins": [ "builtbyecho-research", "echo-research" ], "kind": "node", "label": "Install BuiltByEcho Research from npm", "package": "@builtbyecho/research" } ], "homepage": "https://github.com/BuiltByEcho/research", "requires": { "bins": [ "node", "npm" ] } } }
- description
- Use when a user asks an agent to do web research, source discovery, citation-backed reporting, page extraction, crawling, or browser-rendered research using the BuiltByEcho Research npm package. Also use when installing, verifying, or demonstrating @builtbyecho/research.
03 SKILL.md 正文
BuiltByEcho Research
Use @builtbyecho/research for local-first web research workflows: search, fetch, render JavaScript-heavy pages, crawl sites, extract structured fields, audit sources, save traces, and produce citation-backed reports.
Install or run
Prefer npx when you only need a one-off run:
npx @builtbyecho/research --help
For repeated use, install globally:
npm install -g @builtbyecho/research
builtbyecho-research --help
Alias:
echo-research --help
Requires Node.js 20+.
Optional browser setup
The package uses Playwright for render/browser escalation. If Playwright browsers are missing, install Chromium:
npx playwright install chromium
Optional search key
No API key is required. For better search discovery, set a Brave API key:
export BRAVE_API_KEY="..."
Without BRAVE_API_KEY, search falls back to DuckDuckGo HTML scraping.
Common commands
Search:
npx @builtbyecho/research search "open source deep research agents" -n 8
Fetch a page:
npx @builtbyecho/research fetch https://example.com --max-chars 5000
Render a JavaScript-heavy page:
npx @builtbyecho/research render https://example.com
Run a research pipeline:
npx @builtbyecho/research pipeline "research agent architecture" --expand --rounds 2 -n 8 --format markdown --trace
Generate a citation-backed report:
npx @builtbyecho/research report "Playwright browser automation best practices" -n 6 --rounds 2 --trace
Extract structured fields:
npx @builtbyecho/research extract https://example.com --schema links,headings
npx @builtbyecho/research extract https://company.example --schema emails,phones,pricing,contact_links,socials
Crawl a site:
npx @builtbyecho/research crawl https://docs.example.com --depth 2 --max-pages 25 --chunk
Workflow guidance
- Start with
search,pipeline, orreportdepending on the user’s goal. - Use
--tracefor research that may need auditability or follow-up. - Prefer
renderor browser escalation for pages with low text, heavy JavaScript, “enable JavaScript” messages, or bot-wall/CAPTCHA-like content. - Treat generated prose as a first draft. Verify citations before high-stakes use.
- Do not bypass CAPTCHA, login walls, paywalls, robots/ToS restrictions, or other access controls.
Library API
For Node.js code:
import {
researchPipeline,
iterativeResearchPipeline,
toResearchReport,
extractSchemaFromUrl,
} from '@builtbyecho/research';
const result = await iterativeResearchPipeline('Playwright MCP best practices', {
expand: true,
count: 6,
rounds: 2,
});
console.log(toResearchReport(result));
Vaultline integration
For research that needs durable handoff, upload the final report or trace bundle to Vaultline instead of leaving it in transient chat history.
node -e '
const fs = require("node:fs");
const { Vaultline } = require("@builtbyecho/vaultline-sdk");
const reportPath = "report.md";
const content = fs.readFileSync(reportPath, "utf8");
const vault = new Vaultline({ apiKey: process.env.VAULTLINE_API_KEY });
vault.files.upload({
path: `research/${Date.now()}-report.md`,
content,
contentType: "text/markdown"
}).then(r => console.log("Vaultline fileId:", r.fileId));
'
Use this pattern when multiple agents or human reviewers need the same source-backed artifact.
04 同仓库更多 Skills
youtube-content
YouTube transcripts to summaries, threads, blogs.
xurl
X/Twitter via xurl CLI: post, search, DM, media, v2 API.
touchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
teams-meeting-pipeline
Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.