メニュー
Search the web using DuckDuckGo. Use when you need to find information, facts, documentation, or current events on the internet.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when opening a PR and driving it to green CI — push the branch, write a high-level PR description, watch checks, fix failures, and keep looping until green; also use when an already-open PR gets new commits.
Use when the user starts, resumes, switches, saves, or recalls a named task or ongoing work across sessions (e.g. "remember this", "continue X", "what was I doing on Y", "track this task").
Git commit workflow. Load when finishing any code-change task (after verification) to commit and push, or when explicitly staging/committing.
Use when modifying or adding a transform, loss, model, method, package, task-model, config, docs page, or example in a Lightly AG repo (lightly-ssl or lightly-train) and you need repo-specific conventions.
Spawn a subagent to run a task. Use when you want to delegate work to a separate pi instance.
Use when configuring or replicating LT-DETR v2 (ltdetrv2-s/m/l/x) COCO benchmarks via the lightly-train wrapper — model alias map, global vs per-rank batch size, recipe invariants, ECDet config mapping, cluster pins, and common gotchas.
| name | web-search |
| description | Search the web using DuckDuckGo. Use when you need to find information, facts, documentation, or current events on the internet. |
Search the web using DuckDuckGo via the ddgs CLI tool.
ddgs text -q "search query" -m 10
| Flag | Description | Example |
|---|---|---|
-q | Search query | -q "AI agents" |
-m | Max results | -m 15 |
-t | Time limit | -t w (week), -t m (month) |
-o | Output file | -o results.json |
Returns numbered results:
1.
title Result Title
href https://example.com
body Snippet text...
To save as JSON:
ddgs text -q "query" -m 10 -o /tmp/results.json
Extract full content from a URL:
ddgs extract -u https://example.com -f text
Formats: text_markdown, text_plain, text_rich
# Basic search, 10 results
ddgs text -q "python tutorial" -m 10
# Recent results only (this week)
ddgs text -q "AI news" -m 15 -t w
# Save to JSON for programmatic use
ddgs text -q "machine learning" -m 20 -o results.json
# Extract content from a page
ddgs extract -u https://github.com/example/repo -f text
⚠️ Always output to a dedicated temp directory, not the current working directory.
# WRONG - writes to cwd
ddgs text -q "query" > results.txt
# RIGHT - output to temp dir
ddgs text -q "query" -m 15 > /tmp/agent-research/results.txt
cat /tmp/agent-research/results.txt
Run multiple searches concurrently using subshells:
mkdir -p /tmp/agent-research
(ddgs text -q "query1" -m 15 > /tmp/agent-research/01.txt) &
PID1=$!
(ddgs text -q "query2" -m 15 > /tmp/agent-research/02.txt) &
PID2=$!
(ddgs text -q "query3" -m 15 > /tmp/agent-research/03.txt) &
PID3=$!
wait $PID1 $PID2 $PID3
cat /tmp/agent-research/0*.txt
# 5 results (default)
ddgs text -q "search terms"
# 20 results
ddgs text -q "search terms" -m 20
# From specific site only
ddgs text -q "search terms site:github.com" -m 10