product-hooks
Skill19 starsChanged 9 days agoMITView on GitHub
Design sandbox onboarding, operational transparency, IKEA co-creation, Day 1-30 habit graduation, and humane offboarding. Sub-skill: load only when routed from the hook-everything entry skill, not for general writing or editing.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- hook-everythingSkill
- anti-slopSkill
- audience-calibrationSkill
- creative-ideationSkill
- hook-compoundingSkill
- marketing-hooksSkill
- market-intelligenceSkill
- psychology-mapSkill
- self-reviewSkill
- trust-architectureSkill
- value-checkSkill
- visual-ux-hooksSkill
- writing-hooksSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 47
Competence-Triggered Upsells (
M16+M13): avoid interrupting a user mid-workflow with a paywall modal.
≈ “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.
Files
Product & Project Hooks (Full-Lifecycle Architecture)
Make users adopt, return, and advocate for your product or project because it compounds their competence and psychological ownership - never because it traps them with dark patterns.
Phase 1: First-60-Seconds Activation (The Velvet Rope Sandbox)
Many products lose 60-80% of visitors at the signup wall (working heuristic, verify with your own data) because they demand high friction (email verification, password rules, credit card, company profile) when the user's motivation and trust are still near zero (Fogg B=MAP).
Combine 4 mechanisms simultaneously in the first 60 seconds (Chord 2):
- Deferred Registration (Value Before Auth) drops the visitor directly into an interactive canvas, live query runner, or pre-populated template. Let them perform their first real action anonymously, and ask for an account only to save, export, or deploy the artifact they just created.
- Operational Transparency (
M22, Buell & Norton 2011) displays the real domain steps (Parsing 14 AST nodes -> Checking circular imports -> 2 warnings found) over 1.5-2.5 seconds rather than a generic spinner when your system processes input. - Low-Failure Co-Creation (
M12, IKEA Effect) gives the user 2 effortless choices (e.g., clicking a filter pill, toggling a formatting rule, picking a column mapping) that immediately transform the preview. Psychological ownership forms the second their input shapes the output. - Credible Endowed Progress (
M6, Nunes & Dreze 2006) counts their anonymous sandbox actions as steps 1 and 2 of onboarding ("2 of 3 setup steps complete").
Phase 2: Day-1 to Day-30 Habit Graduation Architecture
A hook that works on Day 1 (onboarding checklists, endowed progress bars) becomes annoying clutter by Day 14. Graduate your product hooks across 3 lifecycle stages:
| Lifecycle Stage | Primary Psychological Goal | Active Hook Mechanism | What to Retire / Hide |
| Stage 1: Day 1 (Activation) | Reach the first concrete "Aha" outcome in < 60 seconds. | IKEA Co-Creation (M12) + Endowed Progress (M6) + Smart Defaults (M8). | Hide advanced settings, billing tiers, and secondary navigation (Choice Overload M28). |
| Stage 2: Day 3 - Day 14 (Habit Formation) | Bridge the gap between external prompts and internal triggers. | Stateful Ovsiankina Resumption (M9) + Plan-to-Finish Snooze + Competence Mirrors (M16). | Retire the onboarding progress bar immediately once complete; never leave a dead widget on the dashboard. |
| Stage 3: Day 30+ (Power User Mastery) | Compounding investment and speed/flow (< 400ms Doherty Threshold). | Keyboard/Macro Shortcuts, Compounding Stored Assets (custom rules, historical baselines), and Variable Domain Insights (M14). | Silence all beginner tooltips, tour prompts, and celebration modals. |
Phase 3: Multiplayer & Collaborative Network Hooks (Relatedness M16)
In B2B tools, developer projects, and collaborative apps, the most natural growth hook is Artifact-Driven Relatedness - never "Invite 5 friends to get dark mode" spam:
- The Read-Only Interactive Share Link lets a user share a live URL for any chart, diff, or doc where teammates can toggle filters or leave a comment without logging in.
- Co-Created Hand-Off Loops route User B directly to row 14 with a 1-click action button (
Ovsiankina M9+Fogg Ability M5) whenever User A tags them on a specific unresolved item ("Can you approve row 14?").
Phase 4: Ethical Upgrade Triggers & Humane Offboarding (Anti-Roach-Motel)
- Competence-Triggered Upsells (
M16+M13) avoid interrupting a user mid-workflow with a paywall modal. Trigger upgrade options immediately after the user completes a high-value action (the Peak-End peak), framing the paid tier around the exact volume or speed they just proved they need ("You just reconciled 48 payouts in 12 seconds. Free covers 50/month; enable unlimited batches for $19/mo"). - The Humane Pause & Offboarding Hook (
M19Benevolence +M26Regret Regulation) makes canceling or pausing a subscription a 1-click button in Settings. Offer a 1-Click "Hibernate Workspace (Free)" option that freezes billing while preserving all custom rules and data read-only. Users who hibernate instead of rage-quitting often return at up to 3x the rate when their next project starts (working heuristic, verify with your own data).
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
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.

