Start with the job, then find an open-source answer

dreamifly-batch turns a prompt list into repeatable Dreamifly image or video jobs. Before spending credits, it validates parameters, estimates cost, and offers a dry run; after generation it saves media, metadata, and structured results locally with caching, retries, and resumable failures. Expensive video or premium-model jobs require confirmation.

ba-workbench helps business analysts turn questions about markets, customers, competition, finance, and operations into structured analysis and decision documents. It combines more than 100 frameworks, reusable templates, and eight BA role profiles for industry research, business cases, competitor analysis, and stakeholder planning.

smart-procurement-navigator-international helps teams decide whether to bid and turn tender documents into a complete, reviewable response. It parses qualifications and scoring rules, maps tasks and deadlines, assists with chapter drafting, checks common rejection causes, and supports both China procurement rules and the listed international frameworks.

Business Analysis Workbench helps analysts turn a vague business question into structured analysis and a decision-ready document. It guides work from strategy, market, and customer questions through competition, financial modeling, requirements, and solution evaluation, with reusable frameworks and professional templates. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

B2B PM Workbench helps product managers turn complex enterprise-product questions into requirements, designs, and delivery-ready documents. Its staged workflow covers research, prioritization, permission, approval, multi-tenant, and AI-product decisions, with outputs such as PRDs, design documents, diagrams, and acceptance criteria. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

AI PM Workbench helps teams take an AI product from opportunity assessment to a governed launch plan. It guides model and architecture choices, prompt and context design, RAG and agent patterns, evaluation, UX, safety, and pricing while making quality, latency, cost, and risk explicit trade-offs. It also covers red teaming and the EU AI Act. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

yoonmoon separates Korean writing support into humanization, translationese cleanup, proofreading, restyling, and AI-writing detection, with an end-to-end route when several steps are needed. It preserves names, numbers, quotations, dates, and claims, and warns that detection is probabilistic rather than proof of authorship.

Provide an approved script, talking-head or voiceover media, and gathered B-roll, and the skill guides Claude through a structured vertical-video edit. It applies A-roll/B-roll cutting, eased camera movement, themed motion graphics, sound design, and a brand style before HyperFrames renders the MP4. A bundled check verifies dimensions, duration, H.264/YUV420p output, and audio; Claude Code, HyperFrames, Node.js, and ffmpeg are required.

oss-launch scans a repository, asks only for missing project details, and generates a tailored open-source file set such as a license, README, contribution and security policies, changelog, CI, and GitHub templates. Its scripts can build a clean package and re-check gaps, while optional launch guidance covers metadata, releases, demo media, and community posts.

kimiflow runs an explicitly invoked feature or bug-fix loop through clarification, diagnosis, planning, implementation, verification, review, and commit approval. Tested scripts enforce blocker resolution, red-and-green evidence, durable state, and other gates instead of relying on the model’s self-report. It can also maintain a local codebase map and learning memory, with optional Obsidian integration; jq is required, and the workflow stops for explicit approval before committing.

Give the skill a PDF, DOCX file, or pasted manuscript and choose either an author self-check or a draft reviewer report. It evaluates nine dimensions on a 1–5 scale, adjusts expectations for conferences versus journals, and can respond in Chinese, English, or both. The report highlights major issues, concrete revisions, and a simulated recommendation, but it is only a pre-submission aid and does not represent or guarantee an actual editorial decision.

WebGL Animation Skills helps an AI coding agent build interactive 3D scenes, generative backgrounds, and particle effects for the web. Its GLSL, Three.js, and particle-system skills cover shaders, GLTF motion, scroll-linked scenes, and GPU resource disposal, with practical paths for common WebGL work. Target projects still need device-specific performance and memory testing.

Give a coding agent a video brief and use these skills to move from script and storyboard through scene construction, narration, captions, editing, and rendering. The pack includes workflows for short explainers, data-driven vertical recaps, progressive diagram and chart reveals, whiteboard drawing, and isometric scenes. It works with Claude Code, Cursor, Codex, and many other agents.

This pack gives AI coding agents four focused workflows for TikTok, Reels, and YouTube Shorts. Use it to design a stronger opening and pacing, create word-timed highlighted captions from a transcript, build a frame-accurate countdown that lands on zero, or generate branded lower thirds across a speaker roster. It installs through the skills CLI or as a Claude Code plugin and is intended for constructing video templates and motion components.

Kinetic Typography Skills helps an agent turn headlines, lyrics, and captions into animated type. It supports character, word, and line staggered reveals, split-text transitions, variable-font weight changes, text on a path, and implementations across CSS, GSAP, Framer Motion, or Remotion. The pack suits social clips, title cards, and lyric videos; the chosen rendering environment still determines how the animation is built and exported.

Text Message Video Skills renders a scripted conversation or CSV as an animated iMessage, WhatsApp, or SMS-style video. Bubbles appear one at a time, typing indicators pulse, send sounds land with each message, and the thread scrolls as the exchange grows. The same template can render many conversations, making it useful for short-form story content. The skill handles presentation and timing; the author remains responsible for the script and its platform context.

Consciousness Loop gives an agent a self-scheduling executive cycle: wake, sense, integrate companion skills, decide, act or defer, and schedule the next wake. Its cadence adapts from short intervals when state is changing to longer or event-only pauses when idle. A scheduler, recurring runner, queue, or event hook is required; without one it degrades to a single pass and a suggested next wake. “Consciousness” here means functional coordination, not subjective experience.

Use Universal Designer as the first stop for a frontend, motion, or 3D request in Claude Code. It inspects the project stack, chooses among 24 specialist skills, and applies integration checks for conflicts, performance, accessibility, responsiveness, and cleanup; the skill coordinates those tools rather than replacing their design or animation logic.