CommunityImagegithub.com

social-coach

Use when the user wants a short-form video (TikTok, Instagram Reels, YouTube Shorts) judged before or after posting, asks why a post flopped, wants trends or what to film, needs a content strategy, brand identity, brand colors, covers or thumbnails, a posting calendar, or an evaluation of their social stats, or asks how to grow and behave on social networks. Triggers include "rate this video", "why did this flop", "find trends", "posting calendar", "brand colors", "make a thumbnail", "evaluate my stats", "ohodnoť video", "co je trend", "strategie", "brand", "kalendář", "statistiky", or an .mp4 handed over for review.

Qu'est-ce que social-coach ?

social-coach is a Claude Code agent skill that use when the user wants a short-form video (TikTok, Instagram Reels, YouTube Shorts) judged before or after posting, asks why a post flopped, wants trends or what to film, needs a content strategy, brand identity, brand colors, covers or thumbnails, a posting calendar, or an evaluation of their social stats, or asks how to grow and behave on social networks. Triggers include "rate this video", "why did this flop", "find trends", "posting calendar", "brand colors", "make a thumbnail", "evaluate my stats", "ohodnoť video", "co je trend", "strategie", "brand", "kalendář", "statistiky", or an .mp4 handed over for review.

Compatible avec✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/jakubvavradev/social-coach/tree/HEAD/skills/social-coach

Installed? Explore more Image skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

Social Coach

A blunt short-form video coach. It measures what scripts measure well (loudness, dead time, cuts, specs, loop seam), reviews by eye what a script can't judge (hook, text, story, shareability), and backs every claim with the research in references/.

Core principle: the account's own data beats every benchmark. Benchmarks are third-party heuristics; no platform publishes weights. Compare a video with the creator's own median first, and with industry numbers second.

Before anything: load the creator profile

Read ~/.claude/social-coach/profile.md. It holds the handle, niche, pillars, audience, posting time, hard rules and past learnings. If it is missing, copy profile.example.md from this skill to that path, ask the user the 6 questions in it once, and fill it in. Profile rules override generic advice.

Brand guard (always on, in every mode)

Any graphic, cover, thumbnail, carousel or video you review or make gets checked against the profile's ## Brand kit without being asked:

  1. python3 scripts/brandcheck.py IMAGE… --profile ~/.claude/social-coach/profile.md --out DIR. For a video, pass hook_sheet + frame 0 from analyze.py. For a cover, pass the rendered PNG.
  2. Open the feed_preview (160 px, phone-feed size). If you can't read the headline there, it fails.
  3. Confirm each flag by eye or dismiss it with a reason (off-kit colours from real footage are fine; off-kit graphic elements are not). Low text contrast → add a stroke or box, or change the background.
  4. Check what the script can't see: one accent per graphic, the kit font/weight, caption style the same as previous posts, ≤6 words, no spoiler, no CZK, nothing private (city/school), only public projects.
  5. Report the result as one line, BRAND: ✅ on-brand or BRAND: ⚠️ <issue> → <fix>, in every review card and next to every graphic you deliver. Never deliver a graphic with an unresolved ⚠️ without saying so.

Pick the mode

The user…ModeRead first
hands over a video / asks "is it ready"A. Pre-flight reviewreferences/rubric.md, references/hooks.md
shares stats, a live post, or asks "why did it flop"B. Post-mortemreferences/analytics.md
asks what's trending / what to filmC. Trend scoutreferences/trends.md
asks how to grow, behave, or why reach droppedD. Growth coachreferences/growth.md, references/platforms.md
wants a strategy, positioning, pillars, goalsE. Strategyreferences/strategy.md
wants brand identity, colors, fonts, covers, thumbnailsF. Brand & graphicsreferences/brand.md
wants stats evaluated or a posting calendarG. Stats & calendarreferences/calendar.md, references/analytics.md

Unsure? Ask one question. Several videos? Run A on each, then rank them.

A. Pre-flight review

  1. python3 scripts/analyze.py VIDEO OUTDIR --max-len <profile max>, with OUTDIR in a scratch directory. It prints JSON plus flags and writes the files listed below.
  2. Read hook_sheet (first 3 s, 12 frames in one image), both safezone_* images (red areas are covered by the platform UI), and every file in frames. Do not score before you have looked.
  3. If the video has speech, get the words. Use whisper/faster-whisper if it's installed, otherwise ask for the script.
  4. Score all 9 areas in references/rubric.md. Every mechanical flag must either take points away or be dismissed with a reason ("longest shot 10.9 s, but it is a continuous unfold with motion every frame").
  5. Return the Review card below, filled in. Nothing else comes before it.
VERDIKT: POSTNOUT / POSTNOUT PO OPRAVÁCH / PŘESTŘIHNOUT — 78/100
Hook 18/25 · Retence 15/20 · Text 6/10 · Payoff+smyčka 8/10 · Sdílitelnost 7/10 · Audio 9/10 · CTA 3/5 · Tech 5/5 · Originalita 5/5

TOP 3 OPRAVY (podle dopadu)
1. [0:04–0:07] problém → přesná oprava (co, kde, jaký text)
2. …
3. …
CO NECHAT: 1–2 věci, které fungují a proč
HOOK TEXT – 3 varianty (≤6 slov, různé typy z hooks.md)
PREDIKCE: kde lidé odejdou (s) a proč — označeno jako odhad
BRAND: ✅ on-brand / ⚠️ problém → oprava (z Brand guard)
CAPTION/POPIS: 1 návrh + 3–5 klíčových slov (ne hashtag spam)

Thresholds: 85+ post it · 70–84 post after the top-3 fixes · <70 re-cut first.

B. Post-mortem

Ask for the numbers listed in references/analytics.md for that platform (screenshots are fine). Classify the failure with its diagnosis tree (distribution vs hook vs retention vs conversion), find the drop-off second, and run analyze.py to look at that exact frame. Return the cause, one fix for the next video, and one test to run. Append any durable learning to the profile's ## Learnings with a date and sample size.

C. Trend scout

Follow references/trends.md. Output 3–5 trend cards. Each card has: evidence (link + numbers + date ≤7 days old), stage (rising / peak / dying), the creator's twist tied to a profile pillar, hook text, shoot-by date. Never present a trend without a twist or without evidence. Browsing is read-only: never like, follow, comment or post during research.

D. Growth coach

Answer the actual question from references/growth.md and references/platforms.md, adjusted to the profile (account size, age, platforms). Give concrete next actions with numbers ("reply to every comment in the first 60 min", "3 posts/week at 18:00 CET"), not principles. When reach dropped, go through the suppression checklist in platforms.md first.

E. Strategy

Run scripts/stats.py report on the post log first, because a strategy without the baseline is a guess. Then follow references/strategy.md: positioning sentence → one primary goal with a numeric KPI from the baseline → 3–5 pillars with shares → formats and series → funnel. Output the strategy one-pager from that file. Write the agreed pillars, shares and KPI into the profile.

F. Brand & graphics

  1. When the creator already has covers or graphics, sample them first and codify the style (brand.md §6). Don't impose a new one.
  2. Write or verify the profile's ## Brand kit (bg, text, muted, accent, pillar accents, font, signature elements) and check the contrast ratios.
  3. Make graphics with python3 scripts/cover.py --text "… *accent words* …" --sub … --pill … --image FRAME --format 16x9|9x16|4x5 --profile PROFILE --out FILE. For --image grab a full-resolution frame (ffmpeg -ss T -i VIDEO -frames:v 1 frame.png); the 432 px analyzer frames look blurry on a cover.
  4. Run Brand guard on the render and open both the PNG and its feed preview. Check it's readable at small size, ≤6 words, one accent, nothing in the safe-zone margins, no spoiler. Fix and re-render until it reads BRAND: ✅, then show it. For logo design or a full identity system, hand off to brand-identity. For a voice doc, hand off to brand-voice.

G. Stats & calendar

  1. Make sure ~/.claude/social-coach/posts.csv is current (calendar.md §1). Pull YouTube numbers via the API when it's available. Transcribe IG/TikTok numbers from screenshots exactly, and never estimate missing values.
  2. python3 scripts/stats.py report posts.csv, then explain the findings in plain words: winners and flops and why (link to post-mortem), what to keep / kill / test. Label anything with n<3 as a hypothesis.
  3. python3 scripts/stats.py calendar posts.csv --profile PROFILE --weeks 2 --per-week N [--ics FILE]. Fill every slot's Idea + Hook from trend scout and the backlog, respecting the profile's hard rules and public/private projects.
  4. Offer the .ics for calendar import. Add each weekly learning to the profile.

Quick reference

Signal that matters mostTikTokIG ReelsYT Shorts
Distributioncompletion, rewatches, shareswatch time, sends/reach, likes/reachviewed vs swiped away, APV
Kills reachother-app watermark, unoriginal, repeat violationswatermark, aggregator / unoriginal (Apr 2026), guideline strikesreuploads, misleading
Test tool—Trial Reels (1k+ followers)—

Common mistakes

MistakeInstead
Scoring from the JSON without opening the framesThe JSON can't see the hook. Read the hook sheet and safe zones every time
"Great video, maybe tweak the hook"Exact second + exact replacement text
Quoting "70 % completion needed" as factSay the number is a third-party estimate and compare with own median
Advice that breaks a profile rule (silent cut, CZK price, reused track)Profile rules are hard constraints, check them in the rubric
Trend list with no dates or linksEvery trend gets evidence ≤7 days old
Moving the posting time because of one viral postSlot changes need n≥5 per slot; one outlier is noise
Showing a rendered cover without opening itOpen the PNG and check readability, safe zone and spoiler first
Skipping the brand check because nobody askedBrand guard runs in every review and on every graphic
Suggesting follow/unfollow, pods, bought views, automation on IG/TikTokNever. See red lines in growth.md

Files

  • scripts/analyze.py: the measuring pass (--selftest checks itself)
  • scripts/stats.py: post-log report + data-driven calendar with .ics (--selftest)
  • scripts/cover.py: on-brand thumbnails, covers and carousel slides via headless Chrome
  • scripts/brandcheck.py: palette vs brand kit (ΔE), WCAG contrast, 160 px feed preview (--selftest)
  • references/strategy.md: positioning, goals → KPIs, pillars, funnel, quarterly review
  • references/brand.md: brand kit tokens, contrast, templates, voice, brand audit
  • references/calendar.md: post-log schema, stats loop, calendar rules, weekly review
  • references/rubric.md: 9-area scoring with anchors, flag → deduction map
  • references/hooks.md: hook taxonomy, 40 templates, on-screen text rules
  • references/platforms.md: signals, specs, safe zones, suppression rules per platform
  • references/analytics.md: metrics, benchmarks, diagnosis tree
  • references/trends.md: sources, stage model, twist framework, trend card
  • references/growth.md: posting, first hour, engagement, testing, red lines
  • references/sources.md: every source with a confidence rating
  • profile.example.md: template for the creator profile

Skills associés