Menü
Use when researching web pages with Miller: fetch token-optimized markdown via browser39, import it as web content, then search/read bounded windows through Miller's content corpus.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Use before changing existing indexed files with Miller edit, especially symbol rewrites, text replacements, renames, or refactors.
Use when an agent needs extractor-recognized code-shape facts such as routes, htmx attributes, Alpine directives, SQL DDL/DML, or data-document structure.
Use when starting a Miller task, choosing a Miller tool, or choosing a Miller search mode.
Use when tracing Miller bridge paths in supported providers: dotnet-web URL literals and fetch/axios client requests to ASP.NET signals, client requests to Next.js route handlers or Nuxt server routes, Next.js/Nuxt route references to file routes, Vue/React references to route definitions, or backend-http client requests to Express/FastAPI/Flask/Django/Spring/Go/gin/echo/Rails/NestJS/Laravel/Phoenix/axum/actix/Symfony/Ktor route facts.
Use when orienting on an unfamiliar code area with Miller, explaining a module, finding entry points, or gathering context before a change.
Use when assessing blast radius with Miller, choosing tests for a change, answering who uses a symbol, or planning a refactor.
Basierend auf der SOC-Berufsklassifikation
| name | miller-web-research |
| description | Use when researching web pages with Miller: fetch token-optimized markdown via browser39, import it as web content, then search/read bounded windows through Miller's content corpus. |
Use this workflow when web content should become searchable/readable through Miller without writing files under the repo.
Check for browser39 first:
command -v browser39
If it is missing, tell the user:
browser39 is required for Miller web research. Install it with: cargo install browser39
Fetch into a temp markdown file, then import that file into Miller as web content:
tmp="$(mktemp -t miller-web.XXXXXX.md)"
cmd="$(mktemp -t miller-web.XXXXXX.jsonl)"
out="$(mktemp -t miller-web.XXXXXX.out.jsonl)"
url="https://example.com/page"
printf '{"id":"1","action":"fetch","v":1,"seq":1,"url":"%s","options":{"selector":"article","max_tokens":12000,"strip_nav":true,"include_links":true,"include_images":false}}\n' "$url" > "$cmd"
browser39 batch "$cmd" --output "$out"
title="$(python3 - "$out" "$tmp" <<'PY'
import json, sys
source, target = sys.argv[1], sys.argv[2]
with open(source, 'r', encoding='utf-8') as f:
row = json.loads(f.readline())
markdown = row.get('markdown') or ''
title = row.get('title') or row.get('url') or 'web page'
with open(target, 'w', encoding='utf-8') as f:
f.write(markdown)
print(title)
PY
)"
miller content add-markdown "$tmp" --url "$url" --display-path "$title" --json
Search only imported web content:
miller content search "important phrase" --kind web
Read a bounded line window from a hit:
miller content read --source-id SOURCE_ID --line 120 --context-lines 10
docs or any tracked directory.content search --kind web first, then content read with a small window.