Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add DariuszCiesielski/polish-agent-skills --skill youtube-scriptsgit clone --depth 1 https://github.com/DariuszCiesielski/polish-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dariuszciesielski/polish-agent-skills/youtube-scripts)<a href="https://agentmods.dev/skills/dariuszciesielski/polish-agent-skills/youtube-scripts"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/youtube-scripts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dariuszciesielski/polish-agent-skills/youtube-scripts"><img src="https://agentmods.dev/badge/skills/dariuszciesielski/polish-agent-skills/youtube-scripts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.02470 |
| Opus 5.5 | $0.00035 | $0.00988 |
| Sonnet 5.5 | $0.00018 | $0.00494 |
| Haiku 4.5 | $0.00009 | $0.00247 |
Grade A, and why
youtube-scripts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Scripts — Skrypty video z wysoką retencją
Pisze skrypty na YouTube optymalizowane pod retencję widzów. Hook writing, struktura 3-aktowa, pattern interrupts, CTA placement.
Kiedy używać
- Pisanie skryptu na video YouTube (tutorial, vlog, thought leadership)
- Optymalizacja tytułu i thumbnail
- Poprawa retencji istniejących filmów
- Planowanie serii video
- Użytkownik mówi: "napisz skrypt", "video na YouTube", "jak zacząć film"
Zależności
- Opcjonalne:
voice-profile→ ton i styl autora - Opcjonalne:
copywriting→ formuły (PAS, AIDA) do intro - Opcjonalne:
content-repurpose→ video → inne formaty - Opcjonalne:
content-strategy→ topic clusters
Struktura skryptu: 3-aktowy model
AKT 1: HOOK + SETUP (0-30s) — 15% czasu
├── Hook (0-5s): zatrzymaj scrollowanie
├── Kontekst (5-15s): dlaczego to ważne
└── Promise (15-30s): co widz dostanie
AKT 2: WARTOŚĆ (30s - 80% filmu) — 70% czasu
├── Punkt 1 + przykład
├── Pattern interrupt
├── Punkt 2 + przykład
├── Pattern interrupt
├── Punkt 3 + przykład
└── (opcjonalnie: Punkt 4-5)
AKT 3: ZAMKNIĘCIE (ostatnie 15%) — 15% czasu
├── Podsumowanie (key takeaway)
├── CTA (subskrybuj / obejrzyj kolejne video)
└── Outro
Hook — pierwsze 5 sekund
Hook decyduje czy widz zostanie. 80% widzów odpada w pierwszych 30 sekundach.
Typy hooków:
| Typ | Przykład | Siła |
|---|---|---|
| Kontrowersja | "Przestań robić landing page. Poważnie." | ★★★★★ |
| Zaskakujący fakt | "93% startupów nie mierzy retention." | ★★★★★ |
| Pytanie | "Ile czasu marnujesz na ręczną pracę?" | ★★★★ |
| Before/After | "Rok temu: 0 klientów. Dziś: 47." | ★★★★ |
| Problem | "Twoja strona nie konwertuje. Oto dlaczego." | ★★★★ |
| Preview wyniku | "Pod koniec tego video będziesz wiedzieć jak..." | ★★★ |
| Historia | "Wczoraj straciłem klienta za 12 000 zł miesięcznie." | ★★★★★ |
| Demonstracja | [Pokaż efekt końcowy od razu] | ★★★★ |
Formuła hooka:
[HOOK] + [KONTEKST] + [PROMISE]
Przykład:
"93% startupów nie mierzy retention — i potem się dziwią że klienci odchodzą.
Dziś pokażę Ci 3 metryki, które musisz śledzić od pierwszego dnia.
Zostań do końca — dam Ci gotowy dashboard do skopiowania."
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 221 lines · 88 tokens per session scan A 75edd32f1582
youtube-scripts is a skill published in the GitHub repository DariuszCiesielski/polish-agent-skills (3 stars, last pushed 6mo ago), licensed MIT. It adds 88 tokens to every session and 2,470 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
roblox-lighting
Use when setting up or changing Roblox lighting, atmosphere, day/night cycles, or post-processing effects.
roblox-growth-design
Use for Roblox growth: diagnosing stats, discovery, retention, onboarding, experiments, LiveOps, thumbnails, and packaging.
roblox-data
Use when writing, changing, debugging, or auditing Roblox player saves: DataStore, ProfileStore, session locks, schemas, migrations.
roblox-input
Use when handling Roblox touch, gamepad, keyboard, mouse or motion input, on-screen action buttons, or cross-platform action binding.
roblox-networking
Use when adding, changing, or auditing RemoteEvents/RemoteFunctions: argument validation, rate limits, server authority, exploit prevention.
roblox-performance
Use when profiling or fixing Roblox performance: low FPS, lag, memory, network load, slow phones, hot paths.