1---2name: channel-formula3description: 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.4---56# Channel Formula78- 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**.9- Generic storytelling craft is necessary but not sufficient — a technically perfect story that breaks the channel's promise still dies. **Audience expectation beats craft.**10- 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.11- 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.1213## When to Use1415- A channel has some winners and some flops and nobody can articulate why.16- Before scripting for an established channel — check the premise against the formula first.17- After a flop, alongside **retention-audit** (audit finds *where* it died; this skill finds *what promise* was broken).18- Any platform, any niche: crime stories, cricket, tech reviews, cozy content, finance, faith, vlogs.1920## Intake (the evidence)2122- **3–5 top videos**: title, thumbnail (screenshot fine), views/velocity, and if available retention at 0:30.23- **1–3 flops** from the same format — flops are as informative as winners; the formula lives in the *difference*.24- Channel's audience in one sentence, and what viewers do with the content (background listening? active watching? saving?).25- Never derive a formula from one video or from niche stereotypes — real data only. Too few videos? Say so and mark the profile "provisional".2627## Extraction Workflow28291. **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]`.302. **Line up the thumbnails.** What is the focal subject in every winner? What emotion? What's never there?313. **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.")324. **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**.335. **Set benchmarks from the channel's own winners** (retention at 0:30 / 2:00, typical velocity) — not from industry averages.346. **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?3536## Profile Output Format3738Deliver (and save, if the user wants it reused) a profile containing:3940| Section | Content |41|---------|---------|42| Core promise | One sentence — the feeling viewers come for |43| The formula | 2–4 numbered rules the winners share |44| Evidence table | Winners + flops with the formula kept/broken |45| Title pattern | Fill-in skeleton from the winners |46| Packaging rules | Thumbnail focal subject, emotion, never-list |47| Kill-zone rule | What the first 30s must show (confirm the click) |48| Benchmarks | Retention/velocity targets from the channel's own data |49| Lever calibration | Tension level, conflict type, resolution length |50| Never-list | Every promise-break found in a flop |5152- **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.53- The profile **overrides generic skills where they conflict** — state this in the profile so future scripting sessions respect it.5455## Applying the Profile (every future video)5657- 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").58- Title from the title pattern; thumbnail from the packaging rules; opening frame confirms the thumbnail.59- After publish, run **retention-audit**; feed every new winner/flop back into the profile. The formula is living — two lines of update per video.6061## Common Mistakes6263| Mistake | Fix |64|---------|-----|65| Formula from niche stereotypes ("crime = shocking") | Extract from THIS channel's winners only |66| Only studying winners | Flops define the never-list — the formula is in the difference |67| One video treated as a pattern | 3+ winners minimum; otherwise mark provisional |68| Formula written once, never updated | Update after every publish via retention-audit |69| Channel profile committed to a public repo | Private skill/note — it's competitive strategy |70| Formula treated as a cage | It constrains *premise and packaging*, not creativity within them |7172## Formula Checklist7374- [ ] 3+ winners and ≥1 flop examined?75- [ ] Core promise stated in one sentence?76- [ ] Title pattern written as a fill-in skeleton?77- [ ] Every flop mapped to a broken rule (never-list)?78- [ ] Benchmarks taken from the channel's own data?79- [ ] Levers calibrated to the audience's tension tolerance?80- [ ] Profile saved privately for reuse?8182## Related8384- **retention-audit** — post-publish diagnosis that feeds this profile.85- **titles-and-thumbnails** / **long-form-youtube** / **storytelling-hooks** — the generic craft the profile calibrates.
yaxeen