Install
$ agentstack add skill-m-binimran-creator-pack-hook-writer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
hook-writer
The hook is 80% of the result. Give options worth testing.
Hook angles (mix and match)
- Bold claim (you can back): "You're [doing X] wrong."
- Curiosity gap: "The reason your [thing] isn't working isn't what you think."
- Direct payoff: "3 ways to [result] without [pain]."
- Pattern interrupt / contrarian: "Stop [common advice]."
- Callout to the viewer: "If you [audience trait], watch this."
- Story open loop: "I almost quit - until this."
- Number/specific: specifics beat vague ("$0 to 10k saves in 30 days").
Process
- Write 5-10 hooks for the idea, across angles. Keep them short, concrete, and in the creator's voice. Pair the
spoken hook with an on-screen text version (sound-off).
Output
- A ranked list of hooks (spoken + on-screen text), with a one-line note on why each could work.
Guardrails
- The hook must match what the content delivers - no bait-and-switch (
brand-safety). - No fabricated numbers in a hook (
truth-telling). Keep it human, not clickbait-y AI.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: m-binimran
- Source: m-binimran/creator-pack
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.