Communitygithub.com

Jo5i4swastaken/Skills-Locker

代理媒體作業系統 — 將任何媒體需求(背景音樂、音效、圖片、圖示)解析為凍結的本地檔案 + 分類帳記錄。

Skills-Locker 是什麼?

這個技能為 AI 代理(例如 Claude Code、Cursor、Codex)提供了一個統一的媒體解析介面。當需要背景音樂、音效、圖片或圖示時,代理只需呼叫一個 `resolve` 指令。該技能會自動串聯完整的處理流程:首先檢查專案快取和全域快取,然後搜尋 HeyGen 目錄,下載最佳匹配的媒體檔,將其凍結到本地 `.media/` 目錄,並在清單中註冊。代理最終只會收到一行結果(例如 `resolved bgm_001 → .media/audio/bgm/bgm_001.mp3 (bgm, 25s)`),所有搜尋過程中的雜訊都保留在磁碟上,保持對話脈絡的清晰。此技能支援跨專案的媒體資產重用、批次匯入現有資產、並透過 `.media/index.md` 提供完整的庫存讀取功能。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Jo5i4swastaken/Skills-Locker/tree/HEAD/skills/media-use

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

media-use

將媒體需求解析為凍結的本地檔案。一個指令、四種型別、零上下文雜訊。

使用時機

每當創作需要媒體(背景音樂、音效、圖片或圖示)時,請呼叫 resolve。media-use 會搜尋 HeyGen 目錄,下載最佳匹配項目,將其凍結到本地,並註冊到清單中。代理只會收到一行結果;所有搜尋雜訊都保留在磁碟上。

Resolve

node <SKILL_DIR>/scripts/resolve.mjs --type <type> --intent "<description>" --project <dir>

回傳一行結果:resolved <id> → <path> (<type>, <metadata>)

型別

型別功能提供者
bgm背景音樂HeyGen 音訊目錄 (10k+ 首曲目)
sfx音效內建 19 個檔案庫 + HeyGen 目錄
image照片、背景圖HeyGen 素材搜尋 (75k+ 向量素材)
icon圖示、標誌HeyGen 素材搜尋 (type=icon)

範例

# 背景音樂
node <SKILL_DIR>/scripts/resolve.mjs --type bgm --intent "upbeat tech launch" --project .
# → resolved bgm_001 → .media/audio/bgm/bgm_001.mp3 (bgm, 25s)

# 音效
node <SKILL_DIR>/scripts/resolve.mjs --type sfx --intent "whoosh" --project .
# → resolved sfx_001 → .media/audio/sfx/sfx_001.mp3 (sfx, 0.57s)

# 圖片
node <SKILL_DIR>/scripts/resolve.mjs --type image --intent "gradient tech background" --project .
# → resolved image_001 → .media/images/image_001.jpg (image)

# 圖示
node <SKILL_DIR>/scripts/resolve.mjs --type icon --intent "rocket" --project .
# → resolved icon_001 → .media/images/icon_001.png (icon, transparent)

旗標

旗標說明
--type, -t媒體型別:bgm, sfx, image, icon
--intent, -i需求描述(自然語言)
--entity, -e用於快取比對的實體名稱(選填)
--project, -p專案目錄(預設:.)
--adopt批次匯入現有 assets/ 目錄到清單
--json輸出 JSON 格式而非一行結果

運作方式

  1. 檢查專案 .media/manifest.jsonl 是否有完全吻合的提示詞
  2. 掃描現有 assets/ 目錄中未註冊且符合需求的檔案
  3. 檢查全域快取 ~/.media/ 是否有可重複使用的素材
  4. 透過提供者搜尋(HeyGen 音訊目錄、HeyGen 素材搜尋)
  5. 將檔案凍結至 .media/<type>/,註冊到清單,重新產生 index.md

代理只會收到一行結果。候選項目、分數、來源資訊都保留在磁碟上。

採用現有專案

大多數 HyperFrames 專案都已將素材放在 assets/ 中。media-use 可以採用它們:

node <SKILL_DIR>/scripts/resolve.mjs --adopt --project .
# → adopted 9 assets from assets/
#   bgm_001 → assets/bgm/mango-fizz.mp3 (bgm, 146.6s)
#   image_001 → assets/images/avatar.jpg (image, 400×400)

ffprobe 會提取真實的時長和尺寸。在解析過程中,assets/ 中未註冊且符合需求的檔案會被當場採用。

讀取庫存

解析或採用後,讀取 .media/index.md 即可查看完整庫存:

# .media · 4 assets

id         type   dur   dims       path                          description
bgm_001    bgm    25s   —          .media/audio/bgm/bgm_001.mp3  upbeat tech launch
sfx_001    sfx    0.6s  —          .media/audio/sfx/sfx_001.mp3  whoosh
image_001  image  —     1920×1080  .media/images/image_001.jpg   gradient tech background
icon_001   icon   —     200×200    .media/images/icon_001.png    rocket

跨專案重用

解析時會自動快取素材。後續對相同提示詞的解析會命中全域快取 ~/.media/ — 無需重新下載,無需呼叫提供者。使用 organize --promote <id> 明確推廣某個素材,使其可在所有專案中重用。

檔案

  • .media/manifest.jsonl — 機器單一真相來源,每行一條 JSON 記錄
  • .media/index.md — 代理可讀的表格(id, type, dur, dims, path, description)
  • ~/.media/ — 全域跨專案重用快取(以內容定址,SHA-256)

使用的 CLI 工具

工具用途必要?
ffprobe採用時探測時長、尺寸、編碼格式是
heygen音訊目錄、素材搜尋用於提供者

安裝 heygen CLI(單一靜態二進位檔,無需執行環境)並進行驗證:

curl -fsSL https://static.heygen.ai/cli/install.sh | bash   # 安裝最新版至 ~/.local/bin
heygen update                                               # 若已安裝:需 >= v0.1.6
export HEYGEN_API_KEY=<your-key>                            # 或:heygen auth login --key <key>

需要 heygen >= v0.1.6 — 提供者會使用已列入白名單的 --headers 'X-HeyGen-Client-Source: media-use' 旗標發送請求,此功能新增於 v0.1.6。asset search 是一個預發佈指令,不會顯示在 heygen --help 中,但仍可正常執行。如果 PATH 中沒有 heygen(或沒有有效的金鑰),提供者會向 stderr 輸出一行診斷訊息,解析將退回為「無提供者能解析」的狀態。

Individual skills in this repo

This repo contains 11 individual skills — each has its own dedicated page.

Jo5i4swastaken/Skills-Locker

Implements the "100% Retrieval Strategy" by Vercel. Injects a compressed docs index into AGENTS.md/CLAUDE.md to guarantee the agent always uses your global skills and best practices.

Jo5i4swastaken/Skills-Locker

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

Jo5i4swastaken/Skills-Locker

Rewrite text to make ideas and sentences clearer and easier to understand. Use when the user wants to simplify prose, untangle a tangled sentence, reduce jargon, sharpen vague claims, or make writing accessible to a wider audience. Works on any text: docs, emails, blog posts, reports, marketing copy, slide bullets, academic prose. TRIGGER on phrases like: "make this clearer", "clarify this", "simplify this", "rewrite for clarity", "plain language", "reduce jargon", "make it easier to understand", "untangle this", "explain this simply", "tighten this up", "make this readable". Returns the rewritten text only — no diff, no commentary.

Jo5i4swastaken/Skills-Locker

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Jo5i4swastaken/Skills-Locker

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

Jo5i4swastaken/Skills-Locker

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Jo5i4swastaken/Skills-Locker

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Jo5i4swastaken/Skills-Locker

Author a HyperFrames slideshow composition — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching sequences, and hotspot navigation. Use as an intent check when the user asks for a presentation, pitch deck, slide deck, interactive deck, or page-to-deck conversion that might be a slideshow; if the user did not explicitly ask for a slideshow / slide show, confirm before authoring.

Jo5i4swastaken/Skills-Locker

When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms, or wants to do social listening and engagement triage. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' 'viral content,' 'what should I post,' 'repurpose this content,' 'tweet ideas,' 'LinkedIn carousel,' 'social media strategy,' 'grow my following,' 'TikTok video,' 'Reels,' 'Shorts,' 'video script,' 'video hook,' 'short-form video,' 'create a reel,' 'social listening,' 'brand mentions,' 'competitor monitoring,' 'top posts to comment on,' 'find people asking for,' 'carousel,' 'slide-by-slide,' or 'document post.' Use this for social media content creation, repurposing, scheduling, short-form video scripting, and social listening. For broader content strategy, see content-strategy. For paid ads, see ad-creative. For earned media, see public-relations.

Jo5i4swastaken/Skills-Locker

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

Jo5i4swastaken/Skills-Locker

Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.

相關技能