This is a specialized hook optimizer for short-form video scripts, built with a specific philosophy: if you can't write a good opening, 90% of the time your content itself is the problem. It runs a three-phase diagnostic that checks content quality and material richness before touching your hook, explicitly stopping you if your script lacks data, stories, authority, or pain points. When it does optimize, it generates 10-15 alternative openings across three methods: extracting existing material, supplementing what's missing, and manufacturing suspense. The core principle is that openings must work independently without assuming viewers saw your title, must be speakable out loud, and should never give away the answer upfront. Built for the Chinese short video ecosystem but the diagnostic framework applies broadly.

skills.sh installs
27.3K
GitHub stars
11.4K
last updated
Aug 21, 2026

Install

$ npx -y skills add dontbesilent2025/dbskill --skill dbs-hook --agent claude-code

Installs into .claude/skills of the current project.

Files

This is a specialized hook optimizer for short-form video scripts, built with a specific philosophy: if you can't write a good opening, 90% of the time your content itself is the problem. It runs a three-phase diagnostic that checks content quality and material richness before touching your hook, explicitly stopping you if your script lacks data, stories, authority, or pain points. When it does optimize, it generates 10-15 alternative openings across three methods: extracting existing material, supplementing what's missing, and manufacturing suspense. The core principle is that openings must work independently without assuming viewers saw your title, must be speakable out loud, and should never give away the answer upfront. Built for the Chinese short video ecosystem but the diagnostic framework applies broadly.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/dontbesilent2025/dbskill
First seen
Apr 16, 2026

More from dontbesilent2025/dbskill

All 30

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs