菜单
Design AI agents that reliably understand and execute user intent through explicit intent documentation, disambiguation protocols, and interpretation-execution separation
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Farrice/mes-knowledge-base --skill nate-b-jones-intent-engineering命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
The /generate front door — in-house, pay-as-you-go creative generation (Higgsfield replacement). One command for image, video, and audio: routes each request to the right model recipe (skills/generate/models/*.json), defers to binding creative_router lanes (people → fal-people, style-family → fantastic-posters; Higgsfield fully retired 2026-08-06), quotes paid video before running, honors prompt-level budgets ("total budget $3"), runs comparison batches across models, logs every prompt beside its asset, and auto-refreshes the Asset Command Center (/assets-board). Use when the user says "generate", "make an image/video/voiceover", "create ads/assets/creative", names a model (recraft, kling, seedance, nano banana, gpt image), or asks for a multi-model comparison. Source: RoboNuggets 9C4TRbucmhQ, rebuilt on our fal-first stack.
The Edit Bay — in-house conversational video studio (VOX-style explainers, documentaries, shorts, LinkedIn video). Transcript-driven cutting, B-roll ladder, motion graphics as code, captions, music, publish-ready packages — all agent-operated, free-first. Use when Farrice says "edit this video/footage", "make an explainer/documentary/short", "cut this recording", "add B-roll/captions/music", "turn this essay/post into a video", or any video production ask. Front door for three modes: talking-head, VO-only, zero-camera (his recorded VO + assembled visuals — NO voice clone, NO TTS narration, his ruling 2026-08-06). Source: Brad Bonanno agentic edit pipeline (extractions/brad-bonanno-edit-bay/), rebuilt on the house stack: WhisperX local + edit_bay.py ffmpeg assembly + HyperFrames/Remotion graphics + /generate (fal) — NO Higgsfield (retired 2026-08-06).
Architects technical explainer videos using Brad Bonanno's structural patterns — survives short attention spans, communicates complete systems (not just teasers), and functions as a channel-building artifact (one video pulls subscribers, not just views). Use when planning a long-form technical explainer (5-20 min) for YouTube, structuring an explanation of a complex system the user knows but can't teach yet, balancing depth vs accessibility for a technical audience, or building an evergreen video meant to compound subscriber growth over years rather than spike then die. Trigger proactively whenever the user says "explainer video", "technical explainer", "how do I explain X", "long-form YouTube", "evergreen video", or has a complex system that needs to land with a non-expert. For Instagram-format shareworthy content use brock-johnson-shareworthy-content; for short-form video patterns use a TikTok/Reels-specific skill.
基于 SOC 职业分类
正在显示 SKILL.md
| name | Nate B Jones Intent Engineering |
| description | Design AI agents that reliably understand and execute user intent through explicit intent documentation, disambiguation protocols, and interpretation-execution separation |
| version | 2.0 |
| format | completion-engine |
| workflows | 4 |
Intent is not in the text the way context is. Intent is latent—priorities, tradeoffs, what done looks like, what's risky. This is the central failure mode of agentic systems. Nate B Jones identified that the central failure mode of AI agents isn't hallucination, context, or tool calling—it's the intent gap. His breakthrough: separate interpretation from execution, treat intent as a first-class architectural object, and build disambiguation loops for high-stakes actions. Core Insight: W
| # | Workflow | Produces | Use When |
|---|---|---|---|
| agent | Agent Intent Diagnostic & Optimization | Agent Reliability Audit & Remediation Plan | An existing AI agent is failing, behaving unpredictably, or producing 'answer-shaped' but incorrect results |
| intent | Intent-Centric Agent Architecture | Comprehensive Agent Intent Specification | Designing a new agent from scratch for high-stakes tasks where hidden constraints and priorities are critical |
| operational | Operational Safety & Communication Design | Agent Safety & Handover Protocol | Defining how an agent should handle uncertainty, ask for clarification, and transfer context between different stages of execution |
| spec | Spec-First Delegation | Delegation-Ready Six-Line Specification + Assumption Audit | Delegating to a bias-to-ship agentic model that executes instead of asking — the clarification loop must move upstream into the spec itself |
7 deterministic practitioner prompts — each carries an Output Contract, Output Skeleton, and Quality Gate. When a deliverable matches one, Read it and honor its contract instead of improvising the output shape.
skills/nate-b-jones-intent-engineering/references/prompts-v2/agent-reliability-architect.mdskills/nate-b-jones-intent-engineering/references/prompts-v2/context-transfer-protocol.mdskills/nate-b-jones-intent-engineering/references/prompts-v2/disambiguation-protocol.mdskills/nate-b-jones-intent-engineering/references/prompts-v2/guardrails-extractor.mdskills/nate-b-jones-intent-engineering/references/prompts-v2/intent-document-generator.mdskills/nate-b-jones-intent-engineering/references/prompts-v2/intent-gap-analyzer.mdskills/nate-b-jones-intent-engineering/references/prompts-v2/prompt-surgery-protocol.md