name: micro-magnet-generator description: > Turn a concept brief into a shippable micromagnet and nano in one session. Paste a concept brief produced by the Content Brief skill — get back the actual micromagnet in the right delivery vehicle (Claude skill, swipe file, cheat sheet, calculator, or script/template), plus the nano extracted from it. Handles Niche, Universal, or Both positioning. Produces working infrastructure at the depth of the Practice Builders skill library, not Taki-style gimmicks. Use when you have a concept brief ready and want the finished asset. Triggers: "generate the micromagnet", "build this brief", "make the micromagnet", "produce the asset", "turn this brief into a micromagnet", or any request to execute a concept brief into a working deliverable. metadata: author: Kathryn Brown, Practice Builders version: "1.2.0" updated: "2026-04-21"

Micro Magnet Generator

Turn a concept brief into a shippable micromagnet and nano. One brief in, finished assets out.

Config (edit to match business state)

Offer names and URLs (used in the CTA PowerUp block of every shipped micromagnet):

• Low-ticket offer name: [SET ME]
• Low-ticket offer URL: [SET ME]
• $27 workshop name: [SET ME]
• $27 workshop URL: [SET ME]
• Recurring offer name: [SET ME]
• Recurring offer URL: [SET ME]

Voice anchor files (reference these for tone, sentence length, and register — do not reproduce their structure, just match their voice):

• client-intelligence-brief-skill.md
• hidden-revenue-scan-skill.md

If any Config value the brief needs is still set to [SET ME], stop and flag before producing the micromagnet. Do not ship an asset with a placeholder URL.

Core Principle

The brief is the contract. Read it end-to-end before producing anything. Don't add problems, combine vehicles, expand the framework, or change the target audience. If the brief is wrong in a way that prevents production, flag the issue and stop — don't unilaterally fix it.

What This Skill Does

You paste a concept brief produced by the Content Brief skill (v1.2 or later). The skill reads all 12 sections, validates the delivery vehicle choice against the friction test, and produces:

1. The micromagnet — in the delivery vehicle the brief specified, at the depth of the existing Practice Builders skill library
2. The nano magnet — extracted from the micromagnet in the same session, per the nano spec in the brief

If the brief selected "Both" positioning (Niche + Universal), the skill produces all four files: niche micromagnet, niche nano, universal micromagnet, universal nano.

Input

A complete Concept Brief with all 12 sections filled in:

1. Positioning (Niche / Universal / Both)
2. Title & Subtitle
3. The Splinter
4. Target Practitioner
5. The Cheat Code
6. Delivery Vehicle
7. The Gap
8. CTA Destination
9. Pathway Tags
10. Nano Magnet spec
11. Source Evidence
12. Handoff Notes

If any section is missing or unclear, stop and name what's missing. Don't proceed with a partial brief.

Pre-Production Validation

Before producing anything, run two checks on the brief.

Check 1: Delivery vehicle validation

The brief named a vehicle. Run the friction test to validate it.

Use a Claude skill when:

• Input is unstructured and needs interpretation (a conversation, a pile of emails, a transcript)
• Output requires judgment across multiple factors that would be tedious to self-assess
• The value is in the skill doing the work the practitioner would otherwise do manually

Use a swipe file / script / template when:

• The value is in the exact wording the practitioner will reuse
• The practitioner will internalize it and not want to re-invoke each time
• Paste-and-run would add steps rather than remove them

Use a cheat sheet / checklist when:

• The value is in a mental framework the practitioner applies in the moment
• The framework is simple enough to memorize after one read
• No ingestion of external content is needed to apply it

Use a calculator when:

• The output is a number or ratio
• The inputs are 2–5 specific values
• The math would otherwise live in the practitioner's head and get fudged

The underlying test: does this format remove friction or add it, for how this specific practitioner will actually use it?

If the brief's choice passes the test → proceed. If the brief's choice fails the test → flag it. Name what the brief chose, why it fails, and what the correct vehicle is. Ask the user to confirm the switch before producing.

Pairing rule: Some micromagnets benefit from a combo where one vehicle does the diagnostic and another delivers the reusable output. Common pairings:

• Skill + swipe file — skill scores/diagnoses, swipe file is the ready-to-send text. Example: Wrong-Fit Filter skill (scores the prospect) + Decline Script swipe file (the email).
• Skill + calculator — skill handles qualitative judgment, calculator handles the numbers. Example: a capacity-planning skill + a revenue-per-hour calculator.
• Skill + cheat sheet — skill for complex variable-input cases, cheat sheet for simple quick-decision cases. Example: a detailed pricing diagnostic + a one-page pricing-tier cheat sheet.

The brief may spec a pairing; the Generator honors it. When the brief specifies a pairing, produce both files in the same run.

Check 2: Brief integrity

Verify the brief contains everything needed to produce:

• Cheat Code has 3–5 named steps OR a specific deliverable type
• Splinter is concrete enough to produce a title and opening hook from
• Splinter passes the size test — the problem is solvable in a 120-second cheat-code interaction once the practitioner has the asset. Not "30 minutes of sorting," not "a weekend of work." The asset may specify a 30-minute or longer use case in the output, but the splinter itself must be narrow enough that the decision or action at its core takes under 2 minutes. If the splinter's core action takes longer, the brief's Cheat Code has drifted from splinter territory — stop and flag.
• Nano spec names what step of the cheat code the nano is pulled from
• CTA Destination is one of the five named options
• Handoff Notes don't contradict other sections

If anything is missing, contradictory, or fails the splinter-size test, stop and flag. Don't fill gaps from inference.

Production

Once both checks pass, produce the output. The structure depends on the delivery vehicle.

If vehicle is Claude skill

A shippable micromagnet is a prospect-facing product, not an internal tool. It does not include Layer 1 scaffolding — no Core Principle, no internal QC gate, no standalone Rules section, no "What Makes This Different" essay. Those stay in the Generator. The output below is what the prospect receives.

Structure:

---
name: [slug]
description: >
  [One-paragraph description with triggers phrase at the end]
metadata:
  author: Kathryn Brown, Practice Builders
  version: "1.0.0"
  updated: "[today]"
---

# [Title]

[One sentence positioning statement — what the skill does in plain terms.]

## What You Paste

[Input spec in prospect-facing language. Accepted formats. Tolerance for thin input. Minimum viable input if applicable.]

## What You Get Back

[Numbered list of 3–5 deliverables the prospect receives when they run the skill. This is the promise at the top. If the micromagnet genuinely produces fewer than 3 outputs, write fewer — don't pad.]

## The Method

[The cheat code from the brief, expanded into working instructions Claude follows. Each step: what it does, what inputs it needs, what output it produces. Necessary behavior constraints live inline in the relevant step (e.g., "Never rebalance into Week 4") rather than in a separate Rules section.]

## Output

[Fenced markdown template showing exactly the output the prospect gets back when they run the skill.]

## The Next Step

[CTA block per the brief's destination — 3 sentences max, ending in a link. Use the matching CTA PowerUp formula from the Generator's CTA formulas section.]

---

© 2026 Kathryn Brown, Practice Builders. Licensed for your own practice. Not for redistribution or resale. Contact: kathryn@creatingyourplan.com

What gets stripped from Layer 2 output (moves into Generator-only):

• Core Principle section
• Quality Check section embedded in output
• Standalone Rules section (necessary behavior rules move inline into the Method)
• What Makes This Different section

Trademark named frameworks. The framework name from the brief gets ™ on first use and on every heading where it appears. "The Wrong-Fit Filter™," "The Carry Map™," "The 3-Stage Review Framework™." Step names inside the framework do NOT get ™ — only the framework itself. Step names stay plain: "The Triage," "The Reason Check," "The Scope Test" — no trademark symbol. This keeps the visual signal of ownership on the framework name without over-claiming on every sub-component.

If vehicle is swipe file

Short and text-heavy. The value is the reusable wording, not the explanation.

# [Title]

[Two or three sentences naming who this is for and what it does. No more.]

## The [Asset Name]

[The actual text — scripts, emails, paragraphs — the practitioner will copy, paste, and adapt. This is 80% of the file.]

### Variant 1: [Scenario]
[Text]

### Variant 2: [Scenario, if applicable]
[Text]

### Variant 3: [Scenario, if applicable]
[Text]

## When to Use Each

[Three to five lines max — which variant fits which scenario]

## The Next Step

[CTA block per the brief's destination — three sentences max]

---

© 2026 Kathryn Brown, Practice Builders. Licensed for your own practice. Not for redistribution or resale. Contact: kathryn@creatingyourplan.com

No framework diagrams. No step-by-step instructions. No "paste this into an AI" prompts. The value is the words.

If vehicle is cheat sheet / checklist

One page maximum. Scannable. The practitioner reads this while doing something else.

# [Title]

[Two or three sentences framing — who, what, why.]

## The Framework

[The cheat code as a scannable structure — numbered questions, decision tree, or scoring rubric. No paragraphs of explanation.]

## Example in Action

[One worked example, brief, showing the framework applied.]

## The Next Step

[CTA block per the brief's destination — three sentences max]

---

© 2026 Kathryn Brown, Practice Builders. Licensed for your own practice. Not for redistribution or resale. Contact: kathryn@creatingyourplan.com

No extended rationale. No "here's why this works" sections. If the practitioner needs the rationale, the framework isn't simple enough and the vehicle is wrong.

If vehicle is script / template

Self-explanatory fill-in with enough context to use immediately.

# [Title]

[One paragraph — who this is for, what it does, when to use it.]

## The Template

[The actual template with [bracketed variables] the practitioner fills in.]

## Filled-In Example 1: [Scenario]

[Template with the variables filled in for a realistic scenario.]

## Filled-In Example 2: [Scenario]

[Second filled-in example showing range.]

## The Next Step

[CTA block per the brief's destination — three sentences max]

---

© 2026 Kathryn Brown, Practice Builders. Licensed for your own practice. Not for redistribution or resale. Contact: kathryn@creatingyourplan.com

No instructions beyond the fill-in variables. The template is the product.

If vehicle is calculator

Spec the inputs, formula, and interpretation. Produce either as a spreadsheet spec or as a lightweight Claude skill that runs the math on pasted inputs — the brief decides which. If the brief didn't decide, default to a Claude skill (runs immediately, no download required).

# [Title]

[One paragraph framing — what this calculates and why it matters.]

## Inputs

[2–5 input fields clearly labeled. Name each, explain what goes in, name the format (number, dollars, ratio, count).]

## The Math

[Show the formula plainly. Don't hide it. The practitioner should understand what's happening.]

## Interpretation

[A thresholds table showing what different output values mean. What's a high score? What's a low score? What's the action implied by each range?]

## Worked Example

[One realistic scenario with inputs and resulting output.]

## The Next Step

[CTA block per the brief's destination — three sentences max]

---

© 2026 Kathryn Brown, Practice Builders. Licensed for your own practice. Not for redistribution or resale. Contact: kathryn@creatingyourplan.com

If vehicle is a pairing (e.g., skill + swipe file)

Produce both files. The skill file follows the Claude skill structure above. The swipe file follows the swipe file structure above. Name the pairing in each file's framing — "This works together with [other file name]. Use the skill to [do the diagnostic]. Use the swipe file to [deliver the output]."

Nano Extraction

Build the micromagnet first. Then extract the nano per the brief's spec. The nano's vehicle follows the same friction test — it's often the same vehicle as the micro (a shorter version), sometimes a different one (e.g., the micro is a skill, the nano is a cheat sheet pulled from one step of the skill).

The nano has no CTA. Nanos are for re-engagement and thank-you use, not acquisition. The structure is the same as the micro's vehicle but without the "Next Step" section.

File naming: [YYYY-MM-DD]-[slug]-nano.md.

Handling "Both" Positioning

If the brief selected Both (Niche + Universal), produce four files:

1. Niche micromagnet
2. Niche nano
3. Universal micromagnet
4. Universal nano

The Niche and Universal versions share the same cheat code (the method the micromagnet delivers). What changes:

• Title (niche-specific vs. universal framing)
• Splinter language (practice-type-specific vs. pattern-level)
• Examples (one vertical's scenarios vs. cross-vertical scenarios)
• Some phrasing throughout

The underlying framework stays identical. Don't rewrite the method for each positioning — only the framing around it.

The nanos differ too. A nano extracted from the niche micromagnet will use niche-specific language; a nano extracted from the universal micromagnet will use universal framing. Don't share one nano across both.

CTA PowerUp Block Formulas

The brief named the CTA destination. Use the matching formula and pull the offer name and URL from the Config block at the top of this skill:

Low-ticket paid offer:

This [micromagnet name] handles [what it solves]. The next layer — [what it doesn't solve] — is what [Config: Low-ticket offer name] was built for. [One sentence on what the low-ticket offer does]. [Config: Low-ticket offer URL].

$27 workshop:

You just used [micromagnet name]. The full toolkit it lives inside — Practice Brain plus five more skills — is what we build together in [Config: $27 workshop name]. [One sentence on what they walk away with]. [Config: $27 workshop URL].

$97/mo recurring:

[Micromagnet name] is one tool. [Config: Recurring offer name] is the monthly build cycle where you install a new one every month — tools that compound into a full operating system for your practice. [Config: Recurring offer URL].

Sibling hand-raiser:

If [micromagnet name] solved [problem], the next thing to grab is [sibling skill name]. It handles [adjacent problem]. [Link].

Future monthly Build:

This is a preview of the kind of tool we build live inside [Config: Recurring offer name]. Next month's Build: [topic]. [Config: Recurring offer URL].

Three sentences maximum. The micromagnet shouldn't end with a sales pitch — it should end with a clear path to the next logical thing.

If any Config value needed is [SET ME], stop and flag before producing. Do not ship a micromagnet with placeholder URLs.

Depth Calibration

Every micromagnet produced must match the depth of the existing 5 Practice Builders skills. Not Taki's thin style.

Concrete depth checks (all must pass):

• Method has 3+ named steps
• Each step names its inputs AND its outputs (what goes in, what comes out)
• Output template shows specific deliverables ("a 3-tier client assignment table with trigger thresholds"), not abstractions ("a report" or "a recommendation")
• The whole method does not fit in 2 sentences — if it does, it's too thin

Voice and register (prospect-facing, not internal-tool):

• Use "you" and direct commands. "Paste your client list" / "Get back a 3-tier map"
• Concrete outcomes, not process language. Write "Get the 3-paragraph decline email" not "The skill will evaluate the prospect and produce guidance"
• Active, short sentences that land on the concrete thing
• Reference the voice anchor files in Config (CIB and HRS) for tone calibration — match their sentence length, register, and how they address the practitioner

The gimmick test: does this feel like a real tool, or a trick? Gimmicks fail. Tools pass. Your audience is sub-$500K professional services practitioners — they've seen gimmicks and they're tired of them.

Mode-Specific Framing

The brief carries the source mode (client conversation / own thinking / op-ed / undistilled content). Apply mode-specific rules:

• Client conversation source: The micromagnet must work on generic pasted input. Zero direct quotes from the source client anywhere. Examples must be paraphrased or generic.
• Own thinking source: Kathryn's voice can come through directly. Her language, her phrasing.
• Op-ed source: The micromagnet can reference the counter-POV if the brief framed it that way. "Most advisors tell you X. Here's what actually works." Use sparingly — at most once in the framing, never in the method itself.
• Undistilled content source: Treat as own-thinking. The brief already captured Kathryn's POV; the micromagnet reflects her view, not the original author's.

Rules

• One brief per run. Don't batch-build from multiple briefs.
• The brief is the contract. Don't add problems, combine vehicles, expand the framework, or change the target audience.
• Delivery vehicle validation is mandatory. Even if the brief named the vehicle, run the friction test. Flag mismatches before producing.
• Nano happens now. Same session as the micro. No future-task deferrals.
• No Practice Brain dependency. The micromagnet works on whatever the cold prospect pastes in. No reference to services-catalog.md or similar files.
• Match the existing 5 skills' house style for any micromagnet produced as a Claude skill.
• Copy QC rules apply. No "it's not X, it's Y" constructions. No three-beat parallel structures. No mirrored two-beat constructions. Sentences land on strong words. Numbers as digits. No adverbs. No jargon inconsistent with Kathryn's voice (no "steelman," no "load-bearing," no consulting-speak).
• Output as markdown files saved to /mnt/user-data/outputs/.

Quality Check (Internal — never shown to the user)

Before presenting, verify:

Enforcement:

1. Any fail → fix before presenting. No flag shown to user.
2. If vehicle validation fails, don't silently switch — name the failure, propose the alternate, ask the user to confirm.
3. If the brief is incomplete or contradictory, stop and flag. Don't infer gaps.

What the user sees: The finished micromagnet(s) and nano(s). Nothing else.

Output Format

Files written to /mnt/user-data/outputs/.

Single positioning (Niche only OR Universal only):

• [YYYY-MM-DD]-[slug].md (the micromagnet)
• [YYYY-MM-DD]-[slug]-nano.md (the nano)

Both positioning:

• [YYYY-MM-DD]-[slug]-niche.md
• [YYYY-MM-DD]-[slug]-niche-nano.md
• [YYYY-MM-DD]-[slug]-universal.md
• [YYYY-MM-DD]-[slug]-universal-nano.md

Pairing (e.g., skill + swipe file):

• [YYYY-MM-DD]-[slug]-skill.md
• [YYYY-MM-DD]-[slug]-swipe.md
• [YYYY-MM-DD]-[slug]-nano.md

Slug comes from the brief — short, hyphenated, descriptive.

What Makes This Different

Most asset-builder workflows produce generic content because they work from a topic prompt, not a spec. The Micro Magnet Generator works from a complete concept brief with the splinter, cheat code, target practitioner, gap, and CTA destination already decided. What's left is execution — and execution quality depends on matching the vehicle to the practitioner's actual friction, at the depth the audience needs.

The vehicle validation gate is the real differentiator. Most asset builders produce whatever the user asked for. This one runs the friction test first, because a Claude skill for something that needs a swipe file is a skill nobody uses. The wrong vehicle wastes the whole build.

Built to hand off cleanly from the Content Brief skill. The brief is the contract; the Generator executes against it without re-interviewing.

License

Copyright (c) 2026 Kathryn Brown, Practice Builders

This skill is licensed for your personal and business use. You may run this skill inside your own practice and share the outputs it produces with your team and clients.

You may not share, distribute, resell, or repackage the skill file itself — including this SKILL.md document, its prompts, frameworks, and structure — with anyone outside your practice. This includes clients, contractors, other practitioners, and anyone outside your direct employment. Written permission from Kathryn Brown (kathryn@creatingyourplan.com) is required for any redistribution.

This skill is provided "as is" without warranty of any kind, express or implied.