/channel-formula

name: channel-formula
description: Use when extracting a channel's winning content formula from its own performance data — comparing top videos against flops on any YouTube/TikTok/Instagram channel in any niche (crime, tech, cricket, cozy, finance…) to codify what its audience actually comes for, or when a new video must be checked against the channel's proven pattern before scripting.

Channel Formula

• Every channel that works has an unwritten contract with its audience: a specific promise the winners keep and the flops break. This skill makes the contract **written**.
• Generic storytelling craft is necessary but not sufficient — a technically perfect story that breaks the channel's promise still dies. **Audience expectation beats craft.**
• The output is a reusable **channel profile**: formula, title pattern, packaging rules, and retention benchmarks, extracted from the channel's own data — never from assumptions about the niche.
• Built on the six levers — see **storytelling-hooks**. Recap: 1. Curiosity gap · 2. Emotional mirror · 3. Conflict engine · 4. Relatability · 5. Pattern + surprise · 6. Three-act.

When to Use

• A channel has some winners and some flops and nobody can articulate why.
• Before scripting for an established channel — check the premise against the formula first.
• After a flop, alongside **retention-audit** (audit finds *where* it died; this skill finds *what promise* was broken).
• Any platform, any niche: crime stories, cricket, tech reviews, cozy content, finance, faith, vlogs.

Intake (the evidence)

• **3–5 top videos**: title, thumbnail (screenshot fine), views/velocity, and if available retention at 0:30.
• **1–3 flops** from the same format — flops are as informative as winners; the formula lives in the *difference*.
• Channel's audience in one sentence, and what viewers do with the content (background listening? active watching? saving?).
• Never derive a formula from one video or from niche stereotypes — real data only. Too few videos? Say so and mark the profile "provisional".

Extraction Workflow

1. **Line up winners' titles side by side.** Find the shared skeleton: what kind of threat/promise/subject repeats? What resolution do they all point to? Write the pattern as a fill-in: `[recurring setup]... [recurring promise clause]`. 2. **Line up the thumbnails.** What is the focal subject in every winner? What emotion? What's never there? 3. **Name the core promise** in one sentence: what feeling does the viewer come to have? (Crime channel: "I saw the twist coming before the detective." Tech channel: "I avoided an expensive mistake." Fitness channel: "I can restart after falling off.") 4. **Autopsy the flops against it.** Which element of the promise did each flop break — premise, resolution, packaging tone, pacing? The broken element becomes a **"never" rule**. 5. **Set benchmarks from the channel's own winners** (retention at 0:30 / 2:00, typical velocity) — not from industry averages. 6. **Calibrate the levers.** Same six levers, channel-specific volume: how hot should tension run? What kind of conflict does this audience accept? How long should resolutions linger?

Profile Output Format

Deliver (and save, if the user wants it reused) a profile containing:

| Section | Content | |---------|---------| | Core promise | One sentence — the feeling viewers come for | | The formula | 2–4 numbered rules the winners share | | Evidence table | Winners + flops with the formula kept/broken | | Title pattern | Fill-in skeleton from the winners | | Packaging rules | Thumbnail focal subject, emotion, never-list | | Kill-zone rule | What the first 30s must show (confirm the click) | | Benchmarks | Retention/velocity targets from the channel's own data | | Lever calibration | Tension level, conflict type, resolution length | | Never-list | Every promise-break found in a flop |

• **Where to save:** the profile is channel-private strategy — save it as a personal skill (`~/.claude/skills/<channel-name>-formula/`) or a private note, **not** in a public repo.
• The profile **overrides generic skills where they conflict** — state this in the profile so future scripting sessions respect it.

Applying the Profile (every future video)

• Check the premise against the core promise **before** scripting — a formula-breaking premise gets reframed, not polished (a mentor-betrays-student premise on a "mentors you can trust" channel becomes "the red flags that expose a bad mentor").
• Title from the title pattern; thumbnail from the packaging rules; opening frame confirms the thumbnail.
• After publish, run **retention-audit**; feed every new winner/flop back into the profile. The formula is living — two lines of update per video.

Common Mistakes

| Mistake | Fix | |---------|-----| | Formula from niche stereotypes ("crime = shocking") | Extract from THIS channel's winners only | | Only studying winners | Flops define the never-list — the formula is in the difference | | One video treated as a pattern | 3+ winners minimum; otherwise mark provisional | | Formula written once, never updated | Update after every publish via retention-audit | | Channel profile committed to a public repo | Private skill/note — it's competitive strategy | | Formula treated as a cage | It constrains *premise and packaging*, not creativity within them |

Formula Checklist

• [ ] 3+ winners and ≥1 flop examined?
• [ ] Core promise stated in one sentence?
• [ ] Title pattern written as a fill-in skeleton?
• [ ] Every flop mapped to a broken rule (never-list)?
• [ ] Benchmarks taken from the channel's own data?
• [ ] Levers calibrated to the audience's tension tolerance?
• [ ] Profile saved privately for reuse?

Related

• **retention-audit** — post-publish diagnosis that feeds this profile.
• **titles-and-thumbnails** / **long-form-youtube** / **storytelling-hooks** — the generic craft the profile calibrates.