Menu
SkillsMP has collected 79 skills from jordangaston/claude-plugins. Open a skill to review its source and details.
Showing 40 of 79 collected skills.
Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art".…
Run Charlie Munger's two-track analysis on a decision — first the rational forces that actually govern the outcome, then the psychological biases that may be distorting the judgment. Use this skill whenever the user is making or reviewing a significant…
Apply the full Farnam Street latticework of ~100 mental models to analyze a problem or decision. Use this skill whenever the user asks to think through a decision, analyze a problem from multiple angles, stress-test a plan, or explicitly mentions mental…
Evidence-based rules for what actually moves short-form video performance (TikTok, Reels, Shorts), distilled from Layers Research's 2026 TikTok Posting Report (23M videos, 13.3T views). Use this skill whenever the user asks about posting strategy mechanics —…
Create shortform videos (TikTok, Reels, Shorts) that win attention and convert, using Kane Kallaway's Lego Brick framework. Use this skill whenever the user wants to plan, script, critique, or improve shortform video content — including requests like "write a…
A skill for systematically building and operating design systems. It designs everything end to end — from documents (requirements, brand guidelines) through Design Tokens, a component system, and governance. It integrates the application of thinking…
Apply Robert C. Martin's "Screaming Architecture" principle at every scale — the whole system, and each name, function, class, schema, and API contract inside it — should scream what it DOES (its intent and use cases), not which framework or mechanism built…
Apply the Refactoring UI framework (Adam Wathan & Steve Schoger) to design, review, guide, or implement frontend interfaces without being a designer. Use when the user wants to design a UI from a feature/requirements, make an existing interface look more…
Design, adapt, optimize, and ship small, domain-specific language models (SLMs) — the practitioner's playbook from Guglielmo Iozzia's *Domain-Specific Small Language Models* (Manning). Use whenever someone is working with SLMs or trying to make an LLM run…
Evaluate the quality of a search or information-retrieval system: choose the right ranking metrics, build a relevance-judgment (qrels) set, and turn the scores into ship / no-ship decisions. Use when measuring search, retrieval, or RAG-retrieval quality;…
Run a full feature sprint from user stories to verified, demoed, shipped code with minimal supervision. Use when the user hands over a set of user stories / acceptance criteria and wants them built end-to-end overnight (or unattended): analyze reference…
Implement a single work-item-spec. Orchestrates five phases (understand, plan, implement, review, finalize), each in a separate sub-agent to keep context clean. Use when the user asks to implement a work item or invokes /implement-feature.
Library of 46 camera movement prompt blocks for AI video generation (Seedance, Kling, Veo, Runway, Higgsfield). Use this skill EVERY time the user needs a camera move for a video prompt, asks "what camera movement should I use", wants a…
Turn a seed idea into a polished AI video-generation prompt. Picks the right mode — T2V (text-to-video), I2V (image-to-video), or V2V (video-to-video) — then builds the prompt: for T2V, an 8-part structure [medium] + [shot] + [angle] + [movement] + [focus] +…
Design principles for building accurate, domain-specific (vertical) AI agents that customers pick because they are more accurate. Use when designing or reviewing an agent's tools, system prompt, context layout, or tool architecture — deciding how many tools…
Turn a script into a shot-by-shot storyboard: shot-type vocabulary (ECU→EWS), camera angles, movement notation, continuity rules (180-degree line, match-on-action, eyeline match, screen direction), panel layout and annotation format, and a shot-list workflow…
Generate the same location across many images from consistent camera angles using the scene-sheet method — a three-step prompt workflow that establishes a scene once, locks its geometry, lighting, and shadows into a five-angle coverage sheet, then stages…
Generate consistent AI product shots across images using the product-sheet method — a three-step prompt workflow that creates a product hero shot, locks its form, materials, finish, color, and branding into a five-view product sheet, then places it in new…
Turn plain text into a performance-ready ElevenLabs script using audio tags, punctuation, and pacing controls for Eleven v3. Use this skill whenever the user wants voiceover or TTS from ElevenLabs — writing or improving a script, adding emotion, laughter,…
Write UGC hooks that stop the scroll and testimonial scripts that sell, for AI-generated UGC clips (VEO, Sora, Kling). Use this skill whenever the user wants to write, script, batch, critique, or fix UGC ads, spokesperson scripts, testimonial scripts, or…
Make marketing and content copy genuinely funny using Scott Dikkers' (founding editor of The Onion) system — the "something's wrong" thesis and the 11 Funny Filters. Use this skill whenever the user wants to write, punch up, or diagnose humor in headlines,…
Act as an evidence-based goal-setting coach and a tough-but-fair thinking partner, grounded in peer-reviewed behavior-change research (implementation intentions, self-determination theory, mental contrasting/WOOP, progress monitoring, accountability,…
Build a complete, reusable identity kit for a new faceless AI virtual influencer, modeled on a real reference creator, ready for later slideshow/content production. Produces the persona doc, voice pack, world bible, master reference + 5-view character sheet +…
Source and curate scene images for a faceless persona account (TikTok slideshows, IG carousels) so every published image reads as a real photo the persona took herself. Covers candid-biased scraping queries, dimension forensics to reject AI/stock images, the…
Produce a full batch of post-ready TikTok slideshow decks for an EXISTING faceless AI virtual influencer, end to end: format/topic planning, scripts in the persona's voice, exclusive per-deck verified backgrounds, AI-generated hero (hook/payoff) slides,…
Diagnose whether a piece of content is inseparable from the product it markets — and make it more so. The core principle is that business content should be inseparable from the product, meaning the thing that makes the content good is the product working. Use…
Generate consistent AI characters across images using the character-sheet method — a three-step prompt workflow that creates a character, locks their face, body, hair, and outfit into a five-view character sheet, then places them in new scenes without drift.…
Turn a seed idea into a polished AI image-generation prompt using a 6-part structure: [medium], [subject], [action/pose], [environment], [style/vibe], [technical specs]. Use this skill whenever the user wants a prompt for generating an image with any model —…
Create high-performing faceless TikTok slideshows (Photo Mode carousels) using the hook/build/payoff structure. Use this skill whenever the user wants to create, write, script, critique, or improve TikTok slideshows, photo carousels, slide posts, or faceless…
Diagnose a brand's ad account and turn research into a prioritized creative roadmap — two-way persona analysis (who your ads target vs. who actually buys), the one-to-two-sentence diagnosis, evidence ranking, and the icebox/quarterly/monthly roadmap system.…
Run structured creative research across three realities — customer (generational context, micro-moments, emotional mapping), brand (production capacity, cost, and what the business is actually optimizing for), and presentation (which format the brain in each…
Run the performance creative loop for paid social ads — customer language mining, emotional insight extraction, concept development, static-first testing, and content analysis of results. Use this skill whenever the user is working on ads, ad creative, paid…
Build and critique static image ads for paid social — the three-layer method (strategy, design, copy), the seven core formats, and the copy mechanics behind winning image creative. Use this skill whenever the user is making, reviewing, or troubleshooting…
Diagnose and build competitive advantage using Michael Porter's framework — the value chain, the three generic strategies (cost leadership, differentiation, focus), cost analysis, and differentiation analysis. Use whenever the user wants to figure out how a…
Diagnose and strengthen a brand using Marty Neumeier's Brand Gap framework — the five disciplines of brand-building (Differentiate, Collaborate, Innovate, Validate, Cultivate). Use this skill whenever someone wants to evaluate a brand's positioning, close the…
Develop a brand strategy — the central, unifying idea that aligns a company's positioning, messaging, name, and identity. Use this skill whenever the user wants to position or reposition a brand, name a company/product/feature, write a brand brief or brand…
Apply the Imagineering Pyramid — Lou Prosperi's framework derived from Walt Disney Imagineering's theme-park design principles — to develop, refine, audit, or "plus" any creative idea, product, feature, experience, or piece of communication. Use this skill…
Craft, develop, diagnose, or revise narrative stories using the principles of dramatic structure and character. Use this skill whenever the user wants help writing a story, novel, screenplay, short story, or narrative scene; developing a plot, premise, or…
Structure writing and thinking using Barbara Minto's Pyramid Principle — lead with the answer, group supporting ideas, and open with a Situation-Complication-Question-Answer story. Use this skill whenever the user is writing or restructuring a memo, report,…
Design a software system from requirements. Explores the codebase, writes a use case document, then writes a technical design document. Both documents land in docs/. Trigger on: 'design this system', 'write the design', 'system design for', or when…