# Glossary

One-line definitions for every defined term in this vault. Follow the wikilink for full context.

- **[[concept-claude-skills|Claude Skill]]** — A portable, reusable text-file instruction set that defines *how* Claude should perform a structured task and fires across chats via a trigger description.
- **[[concept-claude-projects|Claude Project]]** — A persistent Claude workspace that holds reference material, brand voice docs, and long-lived context defining *where* you work.
- **[[concept-higgsfield-mcp|Higgsfield MCP]]** — A custom Model Context Protocol connector that lets Claude directly invoke Higgsfield's image/video generation APIs from inside a chat.
- **[[concept-beat-image-video|Beat Image / Beat Video Generation]]** — A workflow that segments a script into visual *beats* and emits a sequential storyboard of static images or cinematic motion clips.
- **[[concept-face-lock|Face Lock]]** — A prompting technique that injects identity-preservation language so a creator's face stays consistent across AI-generated thumbnail variants.
- **[[framework-skill-anatomy|Skill Anatomy]]** — The three-part Skill file structure: Frontmatter (routing description), Instructions (execution logic), Examples (few-shot calibration).
- **[[framework-build-or-skip|Build-or-Skip Matrix]]** — A 3-gate filter (Recurring, Structured, Delegatable) for deciding whether a task deserves to become a Skill.
- **[[framework-six-hook-patterns|Six Hook Patterns]]** — A hardcoded menu of psychological hook formulas: Contrarian, Curiosity Gap, Pattern Interrupt, Identity Callout, Stat Shock, Before/After.
- **[[claim-vending-machine-usage|Vending-Machine Thinking]]** — Alex's pejorative for treating an LLM as a one-shot prompt-in / content-out machine; the failure mode Skills and Projects are designed to replace.
- **[[claim-description-importance|Description Primacy]]** — The claim that a Skill's trigger description matters more than its instruction body because routing precedes execution.
- **[[claim-time-savings|50% Time-Savings Claim]]** — Alex's headline ROI estimate for using Skills + Higgsfield MCP versus a tab-switching baseline workflow.
- **[[contrarian-vending-machine|LLMs-as-OS Reframe]]** — The contrarian insight that LLMs should be treated as operating systems with infrastructure (Projects, Skills, MCP) built around them.
- **[[contrarian-description-over-instructions|Routing-Trumps-Execution]]** — The contrarian insight that routing logic (descriptions) is a more common failure point than execution logic (instructions).
- **[[entity-alex|Alex (Grow with Alex)]]** — Sole speaker and creator; practitioner-educator on AI-assisted content workflows.
- **[[entity-claude|Claude]]** — Anthropic's LLM family used as the orchestration engine for the entire workflow.
- **[[entity-higgsfield|Higgsfield]]** — AI image/video generation company providing the MCP connector that powers visual workflows in the video.
- **[[entity-chatgpt|ChatGPT]]** — OpenAI's conversational LLM, referenced only as a rhetorical contrast (\"ChatGPT thinking\").
- **[[quote-vending-machine|The Vending Machine Fallacy (quote)]]** — Alex's thesis sentence framing the misuse of LLMs.
- **[[quote-skill-definition|Defining a Skill (quote)]]** — \"Tool with instructions, not knowledge. Travels across every chat.\"
- **[[quote-description-matters|Importance of Descriptions (quote)]]** — \"Writing the description well matters more than writing the skill itself.\"
- **[[action-install-higgsfield-mcp|Install Higgsfield MCP]]** — Settings → Connectors → Add custom connector → paste MCP URL → authenticate.
- **[[action-audit-repetitive-tasks|Build-or-Skip Audit]]** — Weekly procedure for classifying tasks and selecting Skill candidates.
- **[[action-create-hook-generator|Hook Generator Skill]]** — Build a Skill that forces hook outputs into the six psychological pattern buckets.
- **[[action-build-thumbnail-skill|Face-Locked Thumbnail Skill]]** — Build a Skill combining brand typography rules and Face Lock identity preservation.
- **[[prereq-claude-projects-knowledge|Project Fluency (prereq)]]** — Ability to set up and populate Claude Projects with brand, audience, and reference assets.
- **[[prereq-basic-prompting|Basic Prompt Engineering (prereq)]]** — Ability to author constrained, formatted, multi-step prompts with negative constraints and few-shot examples.