AI Agent Workflow Collection

Merge, consolidate, and evolve Single Source of Truth (SSOT) documents by integrating new research or notes into an existing master document. Use this skill whenever the user wants to merge two or more documents, combine old and new research into one file, update a living document with new findings, consolidate notes into a master doc, or says things like "merge these docs", "integrate this into my doc", "update my SSOT", "combine these notes", "add this research to my master doc", "consolidate", or "weave this in." Also trigger when the user uploads two documents and asks to unify, reconcile, or synthesize them — even if they don't use the word "merge." Do NOT use for simple summarization, file format conversion, or translation tasks.

Generate production-ready Framer Code Overrides and Code Components in React/TypeScript. Use this skill whenever the user mentions Framer code, code overrides, code components, Framer property controls, Framer animations, or asks to build any interactive behavior inside Framer — even if they just say "make this element do X in Framer" or "I need a Framer component for Y." Also trigger when the user references framer-motion in a Framer context, asks about createStore for shared state, or wants to add property controls to a component. Always use this skill instead of generic React advice when the target environment is Framer.

Generate a polished, self-contained HTML questionnaire file that the client fills out in-browser and submits via email or clipboard. Use this skill whenever the user says "make a client form", "build an intake form", "turn these questions into a form", "design approval form", "I need more buy-in from [client]", "something more polished than an email", "interactive questionnaire", or whenever they want an elevated, visual, interactive alternative to a plain-text email questionnaire. Works at any project stage — kickoff, design direction approval, scope clarification, revision rounds, content gathering. Always trigger this skill (instead of drafting a plain markdown or email questionnaire) when the user signals they want visual polish, tappable binary choices, embedded reference previews, or a stronger nudge for the client to actually respond — even if they don't use those exact phrases.

Process raw, unstructured "brain dumps" (notes, ideas, conversation fragments, meeting notes, voice-to-text transcripts) and transform them into two structured outputs: a clean outline that preserves original voice, and a professional summary with action items. Use this skill whenever the user pastes a wall of unstructured text and wants it organized, uploads a .txt or .md file of raw notes, or says things like "organize these notes", "clean up this brain dump", "structure this", "make sense of this mess", "sort these thoughts", "parse my notes", "turn this dump into something useful", or "organize my raw notes." Also trigger when the user uploads a text file and asks to extract action items, summarize discussions, or impose structure on chaotic content — even if they don't use the word "organize." Do NOT use for formal document merging (use doc-merge), meeting transcript summarization from audio/video tools, or simple text summarization where structure is already present.

Dismantle work into phased plans with model+effort routing, or execute the next phase of an existing plan. Two modes — "/plan-pipeline dismantle " and "/plan-pipeline run ".

Distill the current chat thread into a concise knowledge update and integrate it into an existing knowledge base file already available in context — a Claude Project knowledge file, a Cowork folder doc, or a .md file in a Claude Code repo. Use this skill whenever the user says "update the KB", "save this to the doc", "document this discussion", "log this to [filename]", "add this to my notes", "capture what we just figured out", "fold this back into the project", "update [doc] with what we discussed", or any variant that means "take what just happened in this conversation and write it into the existing knowledge base." Trigger even when the user doesn't name the target file, as long as a KB file is clearly present in the project / folder / repo context. Do NOT use this skill for merging two uploaded documents (use doc-merge), for organizing a raw brain dump that has no existing target file (use messy-notes-organizer), or for first-time KB creation from scratch.

Schedules a minimal one-token remote Haiku session to fire at the exact moment the user's 5-hour Claude token window refreshes, so the new window starts immediately. Use whenever the user mentions their session is ending soon, wants to "kickstart" a new token window, says "my 5-hour session ends in X minutes", "schedule a session refresh", "kickstart my token window", or wants to maximize usable tokens per hour by pre-starting the next window.