Communitygithub.com

getedgehq/skills

Build a YouTube strategy, evidence-backed idea slate, and title plus thumbnail package using Paddy Galloway's public method. Use when planning a channel, choosing concepts, or preparing a video before filming.

Was ist skills?

skills is a Claude Code agent skill that build a YouTube strategy, evidence-backed idea slate, and title plus thumbnail package using Paddy Galloway's public method. Use when planning a channel, choosing concepts, or preparing a video before filming.

Funktioniert mit✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/getedgehq/skills/tree/HEAD/galloway-youtube-outlier-packaging

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Paddy Galloway's YouTube Outlier Packaging

Based on Paddy Galloway's public method. Not affiliated with or endorsed by Paddy Galloway.

When to use

Use this skill to turn a channel brief into a focused strategy, prioritize video ideas, or prepare a title and thumbnail package before production. It also supports reviewing a channel whose uploads rarely exceed its usual view range. The central decision is which viewer promise deserves production effort, followed by how to communicate and fulfill that promise. [S1][S4]

Produce a readable strategy page with a supporting packaging appendix. Keep the page useful for decisions; put the evidence ledger, title candidates, and thumbnail briefs in the appendix. For a single upload, use the existing channel strategy and complete only the relevant fields. Do not force a full channel planning exercise into a narrow packaging request. Follow templates/output-template.md for either scope.

The method primarily concerns long form YouTube. Treat Shorts, business models, and device-specific production as optional context when they affect the brief. Galloway's numerical recommendations are working heuristics, not guarantees. Preserve the user's constraints, label missing data, and distinguish public recommendations from this package's operational adaptations. references/method.md explains those boundaries; references/sources.md identifies the fetched evidence.

Procedure

  1. Establish scope and inputs. Read references/method.md. Gather niche, audience, recent comparable uploads, view counts, production capacity, access, budget, and the decision deadline. Separate observed information from estimates. Use the template's intake fields to record unresolved inputs without inventing evidence.

  2. Choose a sustainable model and starting territory. Use references/method.md to select a low frequency, high frequency, or weekly approach. Identify one or two sub-niches to win first. Explain how the model fits the team and leaves time for ideation, packaging, and intros. [S1][S3][S5]

  3. Name the visible advantage. Follow references/method.md to identify distinctive knowledge, skill, personality, or access. Attach a concrete proof point and a filming implication to every claimed advantage. Generic enthusiasm is insufficient evidence of differentiation. [S1]

  4. Map three viewer groups. In templates/output-template.md, describe core, casual, and new viewers and why each would click and stay. Use references/method.md to broaden understandable stakes while preserving the channel's subject and expertise. [S1][S6]

  5. Build and tag the idea pool. For a strategy pass, brainstorm at least 100 ideas, using internal outliers, external outliers, and innovation. Record source links, baselines, and uncertainty using references/method.md. For a single upload, inspect relevant existing ideas and comparables instead of padding a new pool. [S1][S2]

  6. Shortlist through explicit gates. Apply demand or novelty, viewer fit, creator advantage, and package clarity from references/method.md. Write a one sentence premise and revise failed gates before filming. Consult examples/worked-examples.md for illustrations of reframing without unsupported claims. [S4][S6]

  7. Explore title angles. Draft at least ten materially different titles for the lead idea. Use references/method.md to vary stakes, contrast, novelty, and unanswered questions. Pair each promising angle with a visual concept rather than selecting a title in isolation. [S2]

  8. Develop visual alternatives. Generate at least five thumbnail concepts and prepare three distinct variants. Follow references/method.md for focal elements and the glance test. If image creation is unavailable, supply production-ready briefs and explicitly mark rendering as unfinished. [S1][S3][S6]

  9. Choose the combined promise. Review scroll stopping, curiosity, and believable value together. Use checklists/review-checklist.md to reject ambiguity, clutter, or an unsupported implied outcome. Record the chosen pair, alternatives, required shots, and selection rationale in templates/output-template.md. [S4][S6]

  10. Confirm delivery and execution. Plan visual or verbal promise confirmation in approximately the first five seconds, followed by the actual investigation or payoff. Apply references/method.md to catch missing footage, access, and quality problems. Set a decision deadline that allows publication and learning. [S4][S6]

  11. Review and repeat. Complete checklists/review-checklist.md, then schedule comparison with the channel baseline, retention curves, and audience reached. Use references/method.md to define a prompt follow-up when a format works, while continuing experiments. Return to the idea pool with the resulting evidence. [S1][S2][S5]

Files in this skill

Individual skills in this repo

This repo contains 18 individual skills — each has its own dedicated page.

getedgehq/agent-evals

Build evals for an AI agent that already does real work. Use when someone asks "how do I know my agent is right", wants to test an agent before trusting it, compare models on cost versus quality, or turn production failures into tests. Walks from first tasks and yes/no verifiers, to isolated environments, to a trace-driven improvement loop.

getedgehq/cli-ux-review

Audit a command-line tool for user-friendliness — clear situation / next-step / options in every output, colour-highlighted runnable commands, no raw jargon, no silent hangs. Invoke for "CLI UX audit", "review my CLI", "is this CLI intuitive", or before any CLI release.

getedgehq/generate-image

Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.

getedgehq/harness-first

Diagnose and fix an unreliable, expensive, or unsafe LLM agent by auditing its harness (golden set, judge, cost caps, data layer, action approvals, tracing) before blaming or swapping the model. Use when someone says an agent is "burning tokens", "hallucinating", "brittle", gives inconsistent answers, asks whether to switch to a cheaper/better model, or wants to ship an agent or prompt change to customers.

getedgehq/http-error-triage

Run before concluding anything from an HTTP error on a third-party API. Separates a real credential/entitlement problem from a CDN or WAF block, a wrong endpoint, or a client-signature ban. Use whenever an API returns 401/403/402/429 and you are about to say "the key is dead", "credits are exhausted", "the plan lacks access", or "we are rate limited".

getedgehq/linkedin-media-prep

Convert, crop, resize, and compress images and videos for optimal LinkedIn upload quality and file size. Use when the user wants to prepare a photo, image, or video for LinkedIn (profile picture, cover photo, post image, article featured image, post video, or video ad), optimize file size for LinkedIn, crop and resize for LinkedIn dimensions, convert HEIC/RAW/PNG/MOV to LinkedIn-ready JPEG or MP4, or mentions LinkedIn media requirements, specs, or limits.

getedgehq/monid

>-

getedgehq/opendraft

An 18-agent pipeline that turns one topic line into a drafted

getedgehq/people-search

Find and rank professional people for recruiting, partnerships, sales, or research from user-provided data, public web sources, an authenticated search session, or a connected provider. Use for people discovery, LinkedIn or Sales Navigator search design, profile-list ranking, or provider filter translation.

getedgehq/rocketlist

Turn a CV into a shortlist of live startup roles from Rocketlist's public job board, including adjacent job titles the person would never have searched for, each with its published salary, the evidence for the fit, and a direct apply link. Use for "find roles I would be a strong fit for", career pivots, remote or VC-backed job hunts, and salary-visible role discovery.

getedgehq/security-audit-checklist

Run a comprehensive security audit across application code, cloud infrastructure, containers, CI/CD pipelines, and infrastructure-as-code. Covers privacy compliance, OWASP basics, secret leakage, API security, IAM misconfigurations, storage exposure, Kubernetes hardening, and network security. Use when the user asks to audit, review, or harden app or cloud security, check for secrets, scan for XSS/SQLi, verify security headers, review Terraform/CloudFormation, audit AWS/GCP/Azure configs, or perform any security-focused review.

getedgehq/shadcn-first

>-

getedgehq/skills

Develop or review a branded long-form YouTube channel using Simon Kaiser's public creator-led approach: audience fit, recurring formats, natural brand integration, Time with Brand, and an organic, paid, and Shorts strategy. Use for channel strategy, format briefs, and pilots.

getedgehq/skills

Build or review a buyer-centered strategic narrative using Andy Raskin's public method. Use for sales or investor deck stories, homepage positioning, keynotes, launch narratives, and why-now messaging.

getedgehq/skills

Turn a product URL, launch brief, or approved script into a production-ready launch video. Use for product reveals, feature announcements, SaaS launches, and narrated product films; not for generic explainers or editing existing footage.

getedgehq/strip-image-ai-metadata

Strip C2PA and AI-generation metadata from images (PNG, JPEG, WebP) to remove "Generated by AI" / "ChatGPT" / "DALL-E" labels that platforms like LinkedIn, Instagram, and X display. Use when the user wants to clean AI-generated images before posting, remove AI attribution from photos, strip C2PA manifests, sanitize image metadata for professional use, or verify whether an image contains C2PA data.

getedgehq/top-down-comms

>-

getedgehq/workplan

Create, update, or close work plans for multi-step tasks. Use when starting refactors, bug lists, feature work, migrations, or any task with 2+ steps. Also use after auto-compaction to re-orient. Triggers: "workplan", "work plan", "create a plan", "what's the plan", "where was I", or when Claude detects

Verwandte Skills