write-copy

A video-copy extraction skill that uses text recognition and speech transcription to collect visible words and spoken narration from a video.

In plain words
What is it for?
Use it to produce organized copy in viewing order, including text by scene and timestamp, for marketing videos, demos, and tutorials.
Why use it?
It removes the need to manually watch a video and type out its on-screen text and narration.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gowtham012/claude-plugins/write-copy
Any agent
npx skills add gowtham012/Claude-plugins --skill write-copy
Clone the repo
git clone --depth 1 https://github.com/gowtham012/Claude-plugins

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 256 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.00256
Opus 5 $0.00021 $0.00128
Sonnet 5 $0.00008 $0.00051
Haiku 4.5 $0.00004 $0.00026

Measured 2d ago against content hash 8b79ec7f87fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-copy 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 2d 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.

video-insight/skills/write-copy/SKILL.md · 32 lines

What it actually says

Extract copy from video: $ARGUMENTS

Steps

  1. Call MCP tool mcp__video-insight__write_copy with video_path = $0.
  2. Read visible_text (OCR, in order of first appearance), full_transcript (narration), text_per_scene (by timestamp).
  3. Output organized copy:
## Copy: <filename>

### All Visible Text (in order of appearance)
1. "Dashboard" — scene_0 (0s)
2. "Get Started" — scene_2 (12s)

### Narration
"Welcome to the dashboard. Click analytics to see your data..."

### By Scene
**scene_0 (0s–12s)**
Visible: Dashboard, Analytics, Layers, Wallet
Narration: "Welcome to the dashboard"
Changes

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.

  1. 2d ago First seen · 32 lines · 42 tokens per session scan A 8b79ec7f87fa

Subscribe to this mod's changes

write-copy is a skill published in the GitHub repository gowtham012/Claude-plugins (5 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 256 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

ai-toolkit-trainer

Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.

artokun/comfyui-mcp · 93 tokens

26-thought-leadership-content-global

Use when a PERSONAL brand needs long-form WRITTEN content that builds authority rather than sells — LinkedIn posts, X threads, Substack and Medium essays, using PAS-Insight for founders, Story-Lesson-CTA for coaches, and Hook-List-Reveal for creators, with six hook formulas and a 1-to-5 repurpose. Trigger on 'LinkedIn…

minhnv0807/ai-business-skills · 167 tokens

26-thought-leadership-content

Dung khi mot CA NHAN can viet BAI DAI de xay uy tin, khong phai copy ban hang — 3 cau truc chuan cho thi truong VN gom PAS-Insight cho founder, Story-Lesson-CTA cho coach, Hook-List-Reveal cho creator; 6 cong thuc hook long-form; ky thuat nhip cau; do dai theo nen tang LinkedIn, Facebook, newsletter; ma tran tai su…

minhnv0807/ai-business-skills · 216 tokens

27-personal-brand-monetize

Dung khi mot CA NHAN da co nguoi theo doi va muon RA TIEN — 3 phien ban funnel cho founder, coach, creator; offer ladder tu mien phi den high-ticket; tam ly gia cho dich vu gan voi con nguoi; inbound vs outbound; dam phan brand deal cho creator; thue va phap ly ca nhan tai VN. Kich hoat khi user nhac 'kiem tien tu…

minhnv0807/ai-business-skills · 206 tokens

notebooklm

Full NotebookLM API via notebooklm-py CLI: create notebooks, add sources, generate podcasts, videos, infographics, slides, quizzes, flashcards, mind maps. Triggers on: "notebooklm", "create a podcast", "audio overview", "generate flashcards", "generate infographic", "/notebooklm".

Mathews-Tom/armory · 71 tokens

media-transcript

Pull a video's transcript (captions/subtitles) as clean text — the doc-ingest sibling for video. Any task that references a YouTube (or other yt-dlp-supported) URL can consume the spoken content as text instead of being blind to it.

sonichi/sutando · 0 tokens