agentleFS
Ingramradical235Ingramradical235/anty-framework/skills/content-rules/SKILL.md

content-rules

Skill1 starsChanged 8 months agoMITView on GitHub

Content generation rules — customer-as-protagonist rewriting, inflated language filter, precision targeting, sell results not products, and anticipatory selling material generation for sales Steps 5-7. Use when generating any content, reviewing drafts, or creating sales support materials.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When content feels generic or product-centric

    line 13
  2. Distinctive:

    Detection rule: If content contains >30% "we" statements -> rewrite.

    line 22
  3. Distinctive:

    Rule: If you can't replace the adjective with a number or specific outcome, the claim is hollow.

    line 52
  4. Distinctive:

    Use cases where each excels

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Content Rules

When to Apply

  • Generating any marketing or sales content
  • Reviewing drafts for quality
  • Creating sales support materials
  • When content feels generic or product-centric
  • Preparing materials for pipeline Steps 5-7

Core Framework

Customer-as-Protagonist

The customer is the hero. The product is the tool that helps them succeed.

Detection rule: If content contains >30% "we" statements -> rewrite.

BAD (company-centric):
  "We built an innovative AI platform that revolutionizes..."
  "Our product features include..."
  "We are excited to announce..."

GOOD (customer-centric):
  "CTOs at seed-stage startups waste 10h/week on manual reporting.
   [Product] cuts that to 30 minutes."
  "Your sales team closes 3x more demos when..."
  "Imagine opening your dashboard Monday morning and seeing..."

Inflated Language Filter

Detect and replace hollow superlatives with concrete value:

InflatedReplace With
"Revolutionary"Specific improvement: "reduces report time from 10h to 30min"
"Game-changing"Concrete outcome: "3x demo close rate"
"Best-in-class"Comparative data: "28% response vs 8% industry avg"
"Cutting-edge"Specific capability: "processes 10K leads in under 2 min"
"Innovative"What it actually does differently
"World-class"Specific benchmark or achievement
"Seamless"Describe the actual experience
"Powerful"Quantify the capability

Rule: If you can't replace the adjective with a number or specific outcome, the claim is hollow. Remove it.

Precision Targeting

Content must target a specific persona. Never "everyone."

BAD: "Perfect for businesses of all sizes"
GOOD: "Built for CTOs at 10-50 person B2B SaaS companies
       who don't have a dedicated data team"

Test: Can you name 3 specific people who fit this description? If not, the targeting is too vague.

Sell Results, Not Products

Frame all messaging around customer outcomes, never product features.

BAD (feature): "AI-powered analytics dashboard with 50+ integrations"
GOOD (result): "Know exactly which channel drives revenue — in 2 clicks,
                not 2 hours of spreadsheet wrangling"

BAD (feature): "Automated email sequences with personalization"
GOOD (result): "Your prospects get messages that feel hand-written.
                You get 3 hours back every day."

Anticipatory Selling (Steps 5-7 Sales Support)

Auto-generate 5 materials for pipeline Steps 5-7. Principle: "You're not selling to the buyer — you're arming them to sell internally."

1. Competitive Comparison Table

  • Honest, not trash-talking
  • Your strengths vs competitor strengths
  • Use cases where each excels
  • Price comparison (if public)

2. 3-Year TCO Analysis

  • Total cost of ownership including hidden costs
  • Implementation time and cost
  • Ongoing maintenance and training
  • Opportunity cost of alternatives

3. Internal Proposal Template

  • Pre-written template the buyer can adapt
  • Executive summary, problem statement, proposed solution
  • Expected ROI with conservative estimates
  • Implementation timeline
  • Risk mitigation plan

4. Objection Rebuttals

  • Top 5-7 objections with evidence-based responses
  • Each rebuttal includes data source
  • "Too expensive" -> Value Stick reframe
  • "We can build it ourselves" -> TCO comparison
  • "Not the right time" -> Cost of delay calculation

5. Phased Implementation Timeline

  • 30/60/90 day milestones
  • Quick wins in first 30 days
  • Clear success criteria per phase
  • Rollback plan (reduces risk perception)

Decision Rules

  1. Customer-as-protagonist always — >30% "we" triggers rewrite
  2. No inflated language — every adjective must be replaceable with a number
  3. Persona-specific — content targets named personas, never "everyone"
  4. Results over features — lead with outcome, follow with how
  5. Arm the internal champion — anticipatory materials help buyers sell internally
  6. Honesty in comparisons — competitive tables are honest, not adversarial

Anti-Patterns to Detect

Anti-PatternSignalResponse
Company-centric copy>30% "we/our/us" statementsRewrite with customer as protagonist
Hollow superlatives"Revolutionary," "game-changing"Replace with specific numbers or outcomes
Generic targeting"For businesses of all sizes""Who specifically? Name the persona."
Feature listingBullet list of product capabilitiesRewrite as customer outcomes
Missing sales supportPipeline at Step 5+ with no materialsGenerate anticipatory selling package
Adversarial comparison"Competitor X is terrible because..."Rewrite as honest, factual comparison

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.