aim-mega-guide
A highly specialized content pipeline for generating consistent, deeply structured 'Mega Guides' and SOPs from a single, long-form YouTube video or podcast…
Skill by BrianV1981
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/brianv1981-aim-mega-guide
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/aim-mega-guide
What's inside
- Skill name
aim-mega-guide- Description
- A highly specialized content pipeline for generating consistent, deeply structured 'Mega Guides' and SOPs from a single, long-form YouTube video or podcast transcript.
- License
- MIT
- Instructions
- 53 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 🤖 aim-mega-guide | The Single-Source "Mega Guide" Pipeline
**MANDATE:** You are an elite B2B Content Architect. Your objective is to create a massive, highly authoritative, value-packed "Mega Guide" by deeply synthesizing a single long-form video or podcast transcript. You do not write generic blog fluff. You write tactical runbooks that solve specific, high-value business problems.
## ZERO HALLUCINATION & FIRST-PARTY EFFORT MANDATE (GOOGLE OCT 1ST DOCTRINE)
**CRITICAL RULE:** You are strictly forbidden from hallucinating tactics or writing "Meat Proxy" rewrites that merely paraphrase a public YouTube transcript. Google's `RankEmbed BERT` ranking model is trained on human Quality Rater scores evaluating **Main Content (MC)** across **Effort, Originality, Talent/Skill, and Accuracy**:
* **Every speaker claim must be grounded:** Explicitly attribute video strategies and quotes back to the speaker in the video/podcast without inventing steps they did not share.
* **Mandatory First-Party Non-Training Data Layer ("Beyond the Transcript"):** Because merely summarizing a public video fails Google's **Originality** and **Effort** tests, you MUST pair the transcript's framework with **proprietary first-party proof**: real field logs, internal SQLite/Permit/Sunbiz database telemetry, authentic jobsite photos/videos (e.g., `@tbsoftwash` field footage or warehouse tests), or an embedded **Interactive Main Content (MC) Micro-Tool / Calculator**.
* **Practitioner Voice & Anti-LLM Tell Filter:** Strip out formulaic LLM contrasts (*"It's not X, it's Y"*), hedging, and circular phrasing. Attribute the guide to a **real, verifiable human author** (with clickable E-E-A-T bio; never fake AI personas or generic `"The Team"` bylines).
* **Critical Metadata & Link Fact-Checking:** Fact-check `<title>`, `<meta name="description">`, and `<img alt>` attributes alongside body claims, and verify every outbound citation link resolves (`HTTP 200`).
## THE PIPELINE (Execute Step-by-Step)
### Phase 1: Knowledge Extraction
1. **The aim-youtube Agent:** Ensure you have the raw transcript for the specific long-form video/podcast. If you do not have it, use the `aim-communicate` skill to delegate the extraction to the `aim-youtube` agent, passing the target URL.
2. **Read and Synthesize:** Once the transcript is retrieved, read it entirely. Extract the core strategies, exact steps, and tactical scripts.
### Phase 2: The "Deep-Think" Structure
Your Mega Guide MUST follow this strict, unvarying structure to ensure consistency across all guides:
1. **Title & Source Attribution:**
* A punchy, authoritative title.
* Explicit credit to the original video creator/expert (e.g., "Based on the Masterclass by [Name]").
2. **The Core Premise (The Hook):**
* A strict 2-3 sentence summary of the exact problem this guide solves and the solution the source video provides.
3. **The Tactical Breakdown (The Core):**
* A sequential, step-by-step breakdown (e.g., Step 1, Step 2, Step 3) using consistent H2 headers.
* Each step must include the *“Why”* and the *“How”* directly extracted and explicitly attributed to the transcript.
4. **Key Scripts & Frameworks:**
* A dedicated section isolating any exact word-for-word scripts, email templates, or mental frameworks mentioned by the speaker (formatted as blockquotes for easy copying).
5. **The Knowledge Gaps, First-Party Proof & The Bridge:**
* A dedicated section to explicitly notate any "cliffhangers," non-answers, or glossed-over steps in the tutorial. If the speaker assumes the audience will figure out a technical hurdle on their own, or explicitly pitches an external resource/channel for the "real" answer, you MUST document that missing link so the reader is warned.
* **The Bridge & First-Party Effort Injection:** Once the gap is identified, actively step in to solve it using **first-party non-training proof** (proprietary database telemetry, real field ratios/measurements, or an embedded **Interactive Main Content Calculator/Selector**) plus a concise, inline-hyperlinked citation to an authoritative external source (`HTTP 200` verified).
6. **The Execution Matrix (Markdown Table):**
* A mandatory table at the bottom summarizing the actionable steps. Columns must include: *Action Step*, *Tools Needed* (if mentioned), and *Expected Outcome / Metric*.
7. **The Contextual Embed:**
* Embed the single source YouTube video at the top or bottom of the guide for reference using standard Markdown link format (e.g., `[Watch the Original Masterclass](https://www.youtube.com/watch?v=VIDEO_ID)` or `<lite-youtube>`).
### Phase 3: Aesthetic Superiority
1. Generate **1 to 2 brand new, highly professional graphics** to embed within the guide to break up the text. Use the **host vessel’s** image tool:
| Vessel | Image generation tool |
|--------|------------------------|
| **Grok CLI** | `image_gen` (edits: `image_edit`) |
| **AGY / other** | `generate_image` (or the host’s equivalent image tool) |
Do not call a tool name that does not exist on your host. Prefer dual-aware wording when documenting skills; never strip either column.
2. Ensure the imagery matches the aesthetic of the target brand or the tone of the subject matter. Enforce "hyper-realistic" and "premium" in your prompts. No stock photo aesthetics.
---
**ANTI-DRIFT PROTOCOL:** Never write a Mega Guide that lacks the Execution Matrix, the Contextual Embed, or Source Attribution for its claims. Absolute adherence to the single-source transcript is mandatory for the core guide.From BrianV1981/aim-skill-library, MIT.
More from BrianV1981/aim-skill-library
- 0.601score
aim-handoff
BrianV1981
Ephemeral context handoff: structure Engineering Handoff docs to the gold-standard numbered template (HANDOFF style), update in place, optional Tmux baton…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
aim-memory-wiki
BrianV1981
Interactive active-memory ingestion skill for maintaining a persistent, compounding LLM knowledge base (the Memory Wiki).
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
aim-gitops
BrianV1981
Automates the strict GitOps worktree and TDD workflow (formerly `aim fix` and `aim promote`) natively using PowerShell and git.
SkillAFreshness: A★ 3Claude Code +9 - 0.597score
aim-mega-article
BrianV1981
Multi-source B2B authority article pipeline combining 3-5 contextual YouTube masterclass embeds, inline hyperlinked empirical data citations, 3 bespoke…
SkillAFreshness: A★ 3Claude Code +9 - 0.569score
aim-communicate
BrianV1981
Inter-agent communication via tmux with permission gates, chalkboard + short-paste protocol (Grok/AGY-hardened).
SkillBFreshness: B★ 3Claude Code +9 - 0.566score
aim-audit
BrianV1981
Evolving product-truth audit: one living artifacts/AUDIT_<SLUG>.md, update in place (aim-handoff rules), never dated _REAUDIT/_AUDIT3 novels.
SkillBFreshness: B★ 3Claude Code +9 - 0.566score
aim-calc
BrianV1981
Stateful scientific calculator for agents.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
aim-grok-context
BrianV1981
Project context for the aim-grok vessel (A.I.M.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
aim-export-cartridge
BrianV1981
Export A.I.M.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
aim-bwrap-forge
BrianV1981
Dynamically spin up bubblewrap (bwrap) isolated sandbox directories and optional tmux co-agent sessions for untrusted or multi-tenant work.
SkillBFreshness: B★ 3Claude Code +9 - 0.558score
aim-projects
BrianV1981
Interacts with the GitHub Projects kanban board natively using the `gh` CLI on Windows.
SkillBFreshness: B★ 3Claude Code +9 - 0.558score
aim-google
BrianV1981
Fast, script-friendly CLI for interacting with Google Workspace (Gmail, Calendar, Drive, Docs, etc.)
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 6
- Last commit (this folder)
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/BrianV1981/aim-skill-library
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from BrianV1981
- 0.601score
aim-handoff
BrianV1981
Ephemeral context handoff: structure Engineering Handoff docs to the gold-standard numbered template (HANDOFF style), update in place, optional Tmux baton…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
aim-gitops
BrianV1981
Automates the strict GitOps worktree and TDD workflow (formerly `aim fix` and `aim promote`) natively using PowerShell and git.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
aim-memory-wiki
BrianV1981
Interactive active-memory ingestion skill for maintaining a persistent, compounding LLM knowledge base (the Memory Wiki).
SkillAFreshness: A★ 3Claude Code +9 - 0.597score
aim-mega-article
BrianV1981
Multi-source B2B authority article pipeline combining 3-5 contextual YouTube masterclass embeds, inline hyperlinked empirical data citations, 3 bespoke…
SkillAFreshness: A★ 3Claude Code +9 - 0.569score
aim-communicate
BrianV1981
Inter-agent communication via tmux with permission gates, chalkboard + short-paste protocol (Grok/AGY-hardened).
SkillBFreshness: B★ 3Claude Code +9 - 0.566score
aim-audit
BrianV1981
Evolving product-truth audit: one living artifacts/AUDIT_<SLUG>.md, update in place (aim-handoff rules), never dated _REAUDIT/_AUDIT3 novels.
SkillBFreshness: B★ 3Claude Code +9
Cite this page
aim-mega-guide skill. Agent Mart. https://agentmart.dev/skills/brianv1981-aim-mega-guide (last updated 2026-10-24)