메뉴
The implementation layer of Boris Cherny's 4-level AI-adoption ladder: level diagnosis, task-lifecycle forging, verification environments, loops/routines, fan-out missions, chat-native harnesses. Trust = artifacts, never claims.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/Farrice/mes-knowledge-base --skill ray-amjad-agentic-coding-ladder명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
| name | Ray Amjad — Agentic Coding Ladder |
| description | The implementation layer of Boris Cherny's 4-level AI-adoption ladder: level diagnosis, task-lifecycle forging, verification environments, loops/routines, fan-out missions, chat-native harnesses. Trust = artifacts, never claims. |
| version | 1.0 |
| workflows | 9 |
| source | YouTube XLA-sTSJ-Wc (2026-07-17) — watched via /watch, transcript + 48 frames |
Boris Cherny's ladder describes the stages of agentic-coding adoption; Ray Amjad demonstrates the buildable mechanisms for climbing it — with receipts. The unit of trust is the artifact (recording / PR / MP3), never the agent's claim. Load
genius.mdbefore any workflow.
| Workflow | Produces | Use When |
|---|---|---|
| ladder-diagnostic | Level diagnostic card (actual vs perceived + missing mechanism) | Anyone claims (or wonders) what level they're at |
| task-lifecycle-forge |
| Paste-ready Task Lifecycle file (CLAUDE.md block or skill) |
| A repo needs spec-in → recording+PR-out autonomy |
| verification-environment | Provisioning plan (surface→instrument→artifact table + build order) | Verification is shallow; agent claims can't be trusted end-to-end |
| level-up-plan | One-rung climb plan with trust exit-test | Diagnosis done; time to climb exactly one level |
| Workflow | Produces | Use When |
|---|---|---|
| loop-hunter | Routine sheet (evidence-backed loop specs + meta-loop) | Recurring manual work suspected; the 2→3 climb |
| fanout-mission | Coordinator fan-out mission prompt (7-part grammar) | A queue of similar tasks + a trusted per-item lifecycle |
| chat-native-harness | Harness blueprint (runtime, skills, channels, grammar) | Moving lifecycles off the laptop into Slack-native ops |
| Workflow | Produces | Use When | Stacks With |
|---|---|---|---|
| system-ladder-audit | System audit card (mechanics table + top-5 upgrades) | Auditing a built Claude Code system, incl. Antigravity | boris-claude-code, orchestration-doctrine |
| adoption-brief | ≤2-page client-facing adoption brief | Consulting/diagnostic engagements | geoff-woods-ai-thought-partner, Proof-to-Market offers |
boris-claude-code — philosophy ↔ execution: Boris's plan-first/self-verifying concepts ground every workflow here; run his agentic-product-engineering-validation for the product frame, then task-lifecycle-forge for the mechanism.nick-saraev-agentic-workflows — bottleneck thinking feeds loop-hunter evidence harvesting.nate-b-jones-trust-architecture — deepens the trust-ledger phase of level-up-plan.geoff-woods-ai-thought-partner — wraps adoption-brief for non-technical operators.extractions/ray-amjad/reference-corpus/ — his real Task Lifecycle file + Sentry fan-out prompt9 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/ray-amjad-agentic-ladder/references/prompts-v2/adoption-brief.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/chat-native-harness.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/fanout-mission.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/ladder-diagnostic.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/level-up-plan.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/loop-hunter.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/system-ladder-audit.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/task-lifecycle-forge.mdskills/ray-amjad-agentic-ladder/references/prompts-v2/verification-environment.mdThe /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.
SOC 직업 분류 기준