agentleFS
Sign inStart free
Vumb-VibeCoderVumb-VibeCoder/hook-everything/SKILL.md

hook-everything

Skill19 starsChanged 9 days agoMITView on GitHub

Build ethical psychological hooks, trust signals, and human-sounding copy across writing and product UX. Use when drafting or auditing copy, campaigns, or onboarding flows.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check whether the audience is in Central Route (high scrutiny, low construal) or Peripheral Route (fast-scrolling, low ability) processing, …

    line 18
  2. Very specific:

    Run python3 tools/slop_scan.py <file> --fix-hints (target <= 15/100) and reread the draft as a native reader with …

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Hook Everything (v5.1)

Architect invisible psychological pull, live market relevance, deep credibility, and natural human prose across marketing, writing, and product projects in any language.

When to Use

Use this suite when researching live market trends and Voice-of-Customer (VoC) language via skills/market-intelligence (while filtering out forced trend-jacking), calibrating tone and proof density to specific audiences via skills/audience-calibration, or brainstorming non-cliche hook concepts via skills/creative-ideation. It also governs layering 3-4 mechanisms simultaneously via skills/hook-compounding, designing zero-scam marketing campaigns (skills/marketing-hooks), structuring spatial layouts (skills/visual-ux-hooks), building product flows (skills/product-hooks), writing long-form pieces (skills/writing-hooks), and auditing text in any language so it passes all 85 rules in skills/anti-slop and scores <= 15/100 on tools/slop_scan.py.

The 7-Stage Execution Pipeline

  1. Scan Live Market & Filter for Organic Fit (skills/market-intelligence/SKILL.md) Query live market signals and 2-to-4 star user reviews. Apply the Organic Fit Gate so a market trend is woven in only if it causally impacts the user's problem.
  2. Calibrate to Audience & Channel (skills/audience-calibration/SKILL.md) Check whether the audience is in Central Route (high scrutiny, low construal) or Peripheral Route (fast-scrolling, low ability) processing, then set register and evidence density.
  3. Ideate via Bisociation (skills/creative-ideation/SKILL.md) Discard the first 3 default LLM ideas (First-3 Graveyard) and collide real user friction with 6 structural lenses.
  4. Establish Trust & Compose Hook Chords (skills/trust-architecture/SKILL.md + skills/hook-compounding/SKILL.md) Combine Trust Damper + Cognitive Anchor + Active Generator + Forward Vector and rotate chords horizontally.
  5. Apply Spatial & Perceptual Structure (skills/visual-ux-hooks/SKILL.md) Structure visual isolation (Von Restorff), choice caps (Iyengar & Lepper), skimmer eye-brakes, and response timing.
  6. Execute Domain Playbook (marketing-hooks, writing-hooks, or product-hooks) Draft the deliverables with micro-commitment ladders, regret elimination, and earned payoffs.
  7. Enforce 85-Rule Anti-Slop, Self-Review & 13-Point Value Gate (anti-slop + self-review + value-check) Run python3 tools/slop_scan.py <file> --fix-hints (target <= 15/100) and reread the draft as a native reader with skills/self-review/SKILL.md and rewrite anything that still sounds machine-made, then verify all 13 checks in value-check.

Bundled Skills & Tools (13 Skills + CLI Scanner)

Resource PathRole in the Suite
skills/psychology-map/SKILL.md30 empirical behavioral and trust mechanisms across 6 layers.
skills/trust-architecture/SKILL.mdABI trust model, inoculation, operational transparency, and costly signaling.
skills/market-intelligence/SKILL.mdLive web VoC/competitor mining and the Organic Fit Gate (no forced trends).
skills/audience-calibration/SKILL.mdELM Central/Peripheral routing and Construal Level calibration.
skills/creative-ideation/SKILL.mdFirst-3 Graveyard pruning and Koestler Bisociation hook generator.
skills/hook-compounding/SKILL.mdCombining 3-4 hooks simultaneously (5 Master Chords) and horizontal rotation.
skills/visual-ux-hooks/SKILL.mdVon Restorff isolation, Choice Overload, eye-tracking brakes, and timing thresholds.
skills/marketing-hooks/SKILL.mdHigh-conversion, zero-scam behavioral conversion architecture.
skills/writing-hooks/SKILL.mdOpeners, False-Summit retention bridges, 90/10 generation gaps, and pacing.
skills/product-hooks/SKILL.mdSandbox onboarding, Day 1-30 habit graduation, multiplayer loops, and offboarding.
skills/anti-slop/SKILL.md85 deep stylometric, cross-linguistic, and anti-hype rules.
skills/self-review/SKILL.mdCold reread as a native reader in any language, with up to 3 rewrite rounds.
skills/value-check/SKILL.md13-point ethical, payoff, organic-fit, and subtlety gate.
tools/slop_scan.pyZero-dependency Python CLI scanner (v5.1) measuring 18 stylometric and anti-hype indicators.
research/SOURCES.md31-row primary academic literature, rating key, and replication audit.
examples/before-after.md16 annotated transformations across all domains.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.

Check your setup, free