本文へ移動
cccskills
無料GitHub で公開

content-repurposing

Turn public social videos, transcripts, posts, creator research, or the user's own source material into platform-specific LinkedIn posts, X posts and threads, short-form scripts, newsletters, blog outlines, carousel briefs, and content calendars. Use when the user wants to reuse a strong idea without copying the source.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md3.7 KB
  • skill.meta.json710 B

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。

Content Repurposing

Convert source material into original, voice-matched content for the channels the user actually needs.

Inputs

  • Source URLs, transcripts, posts, research reports, or owned source material.
  • Target audience, brand or company voice, platforms, formats, objective, and desired quantity.
  • Optional Brand Core, voice guide, campaign, offer, CTA, and publishing window.

Workflow

  1. Confirm which sources may be transformed and whether they are owned, quoted, or used only as inspiration.
  2. For a video source, use transcript-intelligence to obtain or analyze its transcript. Do not download, transcode, or edit the video, and do not introduce an FFmpeg dependency. If the user already supplied a transcript or captions, work from them directly. If only a URL is available and the current environment cannot call the transcript provider, ask for the transcript or captions; do not improvise a terminal-only media workflow.
  3. Use outlier-post-finder or creator-profile-teardown when the user wants to repurpose a winning pattern rather than a single source.
  4. Extract content atoms: hooks, stories, claims, proof, frameworks, questions, examples, objections, visuals, and calls to action. Retain the source and support for every factual atom.
  5. Choose only formats that fit the audience and objective. Define the platform constraint, distinct angle, and intended action for each output.
  6. Rewrite from the user's perspective and voice. Use create-linkedin-content and create-x-content for final platform tuning when those formats are requested.
  7. Produce ready-to-edit drafts, not a list of generic ideas. Vary the structure by platform and include attribution notes where a source materially influenced the output.
  8. Self-check for voice, factual support, repetition, plagiarism risk, platform fit, and whether each derivative stands on its own.

Runtime paths

  • Transcript or text supplied: fully terminal-free. Repurpose the supplied material directly.
  • Public video URL with GooseWorks MCP: use transcript-intelligence, then call the managed provider through the live call_data_provider schema. No terminal or separate provider key is required.
  • Public video URL with GooseWorks CLI: use transcript-intelligence and its declared provider dependency, then continue with the transcript.
  • Public video URL without either provider path: explain that the transcript cannot be fetched in this environment and request pasted captions or a transcript.

Output

  • Source inventory and content-atom table.
  • Repurposing map showing source atom, target format, audience, angle, and CTA.
  • Platform-ready drafts grouped by channel.
  • Optional carousel or visual briefs for goose-graphics when requested.
  • Suggested publishing sequence and content calendar when requested.
  • Attribution notes, factual checks, and items requiring user review.

Guardrails

  • Adapt ideas, evidence, and structures; do not plagiarize distinctive language or creative expression.
  • Quote only short, necessary excerpts and retain attribution.
  • Do not flatten every platform into the same draft with a different character count.
  • Do not invent facts, personal experience, customer proof, or first-person claims for the user.
  • Do not require FFmpeg or a local terminal. This skill transforms source meaning into written content; it does not process video files.

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

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

gooseworks-ai のスキルをすべて見る

このスキルの問題を報告する