本文へ移動
cccskills
無料GitHub で公開

assetseeker

Search free commercial-use creative assets across multiple online sources — photos, illustrations, icons, video footage, music, sound effects, and fonts. Use when the user needs to find assets for videos, PPTs, articles, or any content creation. Trigger on phrases like "find me a photo of", "search for icons", "I need background music", "find video footage", "search fonts", "找一张图片", "搜素材", "帮我找图标/视频/音乐/字体". Covers Pexels, Unsplash, Pixabay, Iconify, Freesound, Google Fonts and more — with API-backed search where available.

インストール方法を見る

含まれるファイル(4)

  • SKILL.md9.9 KB
  • references/asset_catalog.md12.0 KB
  • references/google_fonts_index.json411.7 KB
  • scripts/seek_assets.py49.7 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Asset Seeker — Online Creative Asset Search

Overview

Search free commercial-use creative assets across the internet from curated, high-quality sources. Covers photos, illustrations, icons, video footage, music, sound effects, and fonts — all vetted for license safety (CC0 / free commercial use).

Backed by the research from the "创作者素材库大盘点" video — every source has been verified for license terms, China accessibility, and API availability.

When to Use This Skill

Activate when the user needs to find online assets for content creation:

  • "Find me a photo of mountains for a video thumbnail"
  • "Search for laptop icons in outline style"
  • "I need drone footage of city traffic for B-roll"
  • "Find calm piano background music"
  • "Search for a bold Chinese font for my title"
  • "找一张科技感的图片" / "帮我搜个图标" / "有没有免费商用的视频素材"

Do NOT use for: local file search, video editing, or asset management tools (Eagle/Billfish).

Supported Sources

Photos

SourceAPIFree TierChina AccessLicense
Pexels (default)✅ Photos + Videos200 req/hr, 20k/month✅ DirectNo attribution required
Unsplash✅ Photos50 req/hr (demo)✅ DirectAttribution appreciated
Pixabay✅ Photos + VideosFree✅ DirectNo attribution required

Illustrations & Vectors

SourceAPINotes
unDraw❌One-click recolor; all free
Storyset❌ (Freepik API paid)Editable characters + animations
Humaaans / Open Doodles / Open Peeps❌Direct download from site

Icons

SourceAPIFree TierNotes
Iconify (default)✅ Open APINo key needed200+ icon sets, 300k+ icons
Noun Project✅5,000/month freeNeeds OAuth

Video Footage

SourceAPIFree TierChina Access
Pexels Video (default)✅200 req/hr, 20k/month✅ Direct
Pixabay Video✅Free✅ Direct
Mixkit🎭 Playwright scraperFree, no attribution✅ Direct
Coverr✅Needs application✅ Direct

Music & Sound Effects

SourceAPINotes
Freesound (default for SFX)✅OAuth, community-largest SFX library
Pixabay Music❌ Music API unavailableWeb download only; no attribution
YouTube Audio Library❌Manual; some need attribution

Fonts

SourceAPINotes
Google Fonts (default)✅ Metadata API1,500+ font families, OFL
100font❌Best CN free font directory

Workflow

Step 1 — Understand the request

Determine:

  • Asset type: photo / icon / video / music / sfx / font / illustration
  • Keywords: what the user is searching for
  • Style hints: orientation, color, mood, style

If the type is ambiguous, ask briefly. Otherwise proceed.

Step 2 — Check API keys

Run the prerequisite check:

SKILL_DIR="${SKILL_DIR:-${CLAUDE_SKILL_DIR}}"
python3 "${SKILL_DIR}/scripts/seek_assets.py" sources

This lists all available sources and whether their API keys are configured. Without any API key, only Iconify (icons) will work — tell the user and suggest setting up at least PEXELS_API_KEY (free, most versatile).

Step 3 — Search

# Photo search (searches Pexels + Pixabay + Unsplash in parallel when keys are set)
python3 "${SKILL_DIR}/scripts/seek_assets.py" search photo "mountain sunset"

# Icon search (Iconify — always works, no key needed)
python3 "${SKILL_DIR}/scripts/seek_assets.py" search icon "laptop"

# Video search (via Pexels API)
python3 "${SKILL_DIR}/scripts/seek_assets.py" search video "city traffic"

# Video search (via Mixkit Playwright scraper — no API key needed)
python3 "${SKILL_DIR}/scripts/seek_assets.py" search video "sunset" --source mixkit

# Sound effect search
python3 "${SKILL_DIR}/scripts/seek_assets.py" search sfx "whoosh"

# Font search
python3 "${SKILL_DIR}/scripts/seek_assets.py" search font "bold sans-serif"

# Limit results
python3 "${SKILL_DIR}/scripts/seek_assets.py" search photo "cat" --max 10

# Filter by orientation
python3 "${SKILL_DIR}/scripts/seek_assets.py" search photo "landscape" --orientation landscape

# Human-readable output
python3 "${SKILL_DIR}/scripts/seek_assets.py" search icon "arrow" --format text

Step 4 — Present results

For each result, show:

  • Thumbnail/preview URL (when available)
  • Source name + license
  • Download link or instructions
  • Any attribution requirements

For Iconify, also show the icon set name and suggest usage (e.g., <span class="iconify" data-icon="mdi:laptop">).

Step 5 — Download (if needed)

python3 "${SKILL_DIR}/scripts/seek_assets.py" download <url> --output poster_bg.jpg

For sources without direct API download, open the page URL in browser or instruct the user to download manually.

Commands

search — Find assets

python3 seek_assets.py search <type> <keyword> [options]

Types: photo, icon, video, music, sfx, font

Options:

  • --max N — Results per source (default: 10)
  • --source S — Specific source (e.g., --source pexels, --source iconify)
  • --orientation landscape|portrait|square — Photo/video orientation
  • --color red|orange|yellow|green|... — Photo color filter (Pexels/Pixabay)
  • --format json|text — Output format (default: json)

sources — List available sources

python3 seek_assets.py sources
python3 seek_assets.py sources --type photo

Shows each source's status: API key configured, free tier limits, China accessibility.

download — Download a single asset

python3 seek_assets.py download <url> --output <path>

Environment Variables

# Photo & Video (get free key at pexels.com/api)
export PEXELS_API_KEY="your-pexels-api-key"

# Photo (get free key at unsplash.com/developers)
export UNSPLASH_ACCESS_KEY="your-unsplash-access-key"

# Photo & Video (get free key at pixabay.com/api/docs)
export PIXABAY_API_KEY="your-pixabay-api-key"

# Sound Effects (get key at freesound.org/apiv2/apply)
export FREESOUND_API_KEY="your-freesound-api-key"
# Optional: OAuth token for higher rate limits
export FREESOUND_TOKEN="your-oauth-token"

# Fonts (get key at console.cloud.google.com)
export GOOGLE_FONTS_API_KEY="your-google-fonts-api-key"

# Noun Project icons (get key at thenounproject.com/developers)
export NOUN_PROJECT_KEY="your-noun-project-key"
export NOUN_PROJECT_SECRET="your-noun-project-secret"

Priority order: At minimum, set PEXELS_API_KEY (free, covers photos + videos). Iconify works without any key.

Get API Keys

ServiceSignup URLTime to get key
Pexelshttps://www.pexels.com/api/~2 min
Unsplashhttps://unsplash.com/developers~5 min (needs app registration)
Pixabayhttps://pixabay.com/api/docs/~2 min
Freesoundhttps://freesound.org/apiv2/apply/~1 day (manual approval)
Google Fontshttps://console.cloud.google.com/~5 min

Requirements

# Core (stdlib, no pip needed for photos/icons/fonts)
pip install requests

# Optional: for Mixkit Playwright scraper
pip install playwright && python -m playwright install chromium

Manual Sources (no API — agent provides direct guidance)

These sources are documented in the skill's knowledge base but have no programmatic API. When the user asks for these types, the agent provides curated recommendations with direct links:

  • Illustrations: unDraw, Storyset, ManyPixels, DrawKit, IRA Design, Open Doodles
  • Video (no API): Mixkit, Coverr, Mazwai, Videvo
  • Music (no API): Pixabay Music, YouTube Audio Library, Freepd, Uppbeat
  • Fonts (no API): 100font (100font.com), 猫啃网 (maoken.com)
  • Emoji: Fluent Emoji, Twemoji, OpenMoji, Noto Emoji
  • AI Tools: remove.bg, Suno, 即梦, 可灵 Kling

When the user needs these, the agent should consult references/asset_catalog.md for the full curated list.

References

  • references/asset_catalog.md — Complete curated source catalog with URLs, licenses, China accessibility, and notes (extracted from the creator-assets research)

Project Structure

assetseeker/
├── SKILL.md                   # This file (in skills/assetseeker/)
├── README.md                  # English README
├── README_CN.md               # Chinese README
├── references/
│   └── asset_catalog.md       # Full curated source catalog
└── skills/
    └── assetseeker/
        ├── SKILL.md
        ├── references/
        │   └── asset_catalog.md
        └── scripts/
            └── seek_assets.py # Main CLI

Related Skills

  • video-podcast-maker — Video production pipeline that consumes these assets
  • imagencn — AI image generation when real photos don't fit the need

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.

日本語の概要は準備中です。原文の説明を表示しています。

Agents365-ai/365-skills842026年10月3日 更新

asta

無料

Query the Semantic Scholar academic corpus through AI2's Asta MCP server: keyword or title search with venue and date filters, who-cited-a-paper traversal, author profiles and publications, DOI/arXiv/PMID lookup, and ~500-word full-text snippets for evidence, with citation counts and h-index. Use when the user asks for papers on a topic, who cited a paper, an author's work, recent literature since a date, or a venue-scoped paper list. Requires the Asta MCP server.

日本語の概要は準備中です。原文の説明を表示しています。

Agents365-ai/365-skills842026年10月3日 更新

Extract and organize frames from a Bilibili video (bangumi episode, UP upload, or a local file) into scenery shots and per-character image groups, using anime-specific person detection + CCIP character-identity embeddings. Two modes — cluster everyone, or pull out one (or several) named characters via reference folders. Use when the user wants to collect, extract, or organize anime frames/screenshots by character or by scenery from a Bilibili video. Read-only download for personal viewing/analysis; uploads nothing.

日本語の概要は準備中です。原文の説明を表示しています。

Agents365-ai/365-skills842026年10月3日 更新

bbc-skill

無料

Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not post/edit/delete.

日本語の概要は準備中です。原文の説明を表示しています。

Agents365-ai/365-skills842026年10月3日 更新

Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using excalidraw-brute-export-cli.

日本語の概要は準備中です。原文の説明を表示しています。

Agents365-ai/365-skills842026年10月3日 更新

Use whenever the user wants to interact with Figshare - searching public datasets/articles, downloading Figshare files, listing their own articles/collections/projects, creating or updating articles, or uploading files (including large multi-part uploads) via the Figshare v2 REST API. Trigger on mentions of "figshare", figshare DOIs (10.6084/m9.figshare.*), figshare.com URLs, or phrases like "upload my dataset to figshare", "publish to figshare", "get figshare article".

日本語の概要は準備中です。原文の説明を表示しています。

Agents365-ai/365-skills842026年10月3日 更新

Agents365-ai のスキルをすべて見る

このスキルの問題を報告する