dorkos: Skill for Claude Code

.agents/skills/capturing-product-media/SKILL.md

capturing-product-media is a skill for Claude Code, Codex from dork-labs/dorkos. It costs 104 tokens per session (4,213 once invoked), scanned A, original, MIT.

A workflow for capturing product screenshots and short video loops from a real application interface using prepared demo data. It also manages the list of shots, manual replacements, and saved versions.

In plain words
What is it for?
Use it to refresh media, capture a new feature demonstration, replace an automated capture with a human-made one, archive release media, or fix missing-media checks.
Why use it?
It keeps screenshots and videos accurate after interface changes and prevents marketing or documentation from showing outdated or fabricated screens.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

This is dork-labs/dorkos's own configuration. It tells Claude Code and Codex how to work on dorkos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dorkos configures →

Part of the flow plugin — 32 skills, 43 commands, 5 agents, 4 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to dork-labs/dorkos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dork-labs/dorkos/main/.agents/skills/capturing-product-media/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code, Codex.

Or install flow, the plugin that ships this one along with the rest of its 32 skills, 43 commands, 5 agents, 4 hooks.

Wrote 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.

agentmods badge for capturing-product-media

README.md
[![agentmods](https://agentmods.dev/badge/skills/dork-labs/dorkos/capturing-product-media/github.svg)](https://agentmods.dev/skills/dork-labs/dorkos/capturing-product-media)
Your own site
<a href="https://agentmods.dev/skills/dork-labs/dorkos/capturing-product-media"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/capturing-product-media/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.

agentmods 80×15 button for capturing-product-media

Your own site · 80×15
<a href="https://agentmods.dev/skills/dork-labs/dorkos/capturing-product-media"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/capturing-product-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,213 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00104 $0.04213
Opus 5 $0.00052 $0.02107
Sonnet 5 $0.00021 $0.00843
Haiku 4.5 $0.00010 $0.00421

Measured 10d ago against content hash c6c787c0bd1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

capturing-product-media 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 10d 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.

.agents/skills/capturing-product-media/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capturing Product Media

DorkOS product media is a general system: one shot registry (apps/e2e/capture/shots.ts) feeding the marketing site, docs, and changelogs, from real UI rendering seeded demo data — never mockups, never doctored screenshots. Automated captures can be beaten by human overrides, and any published set can be frozen into a versioned archive. This skill is the map: the registry, the phases, overrides, archives, docs embeds, the honesty rules, and how to add a shot.

When To Use

  • The UI changed and a screenshot or loop on the site or docs now looks stale or wrong.
  • A new feature needs a "money shot" (hero still or animated loop) on /features, or a docs page needs an embedded <ProductShot>.
  • A person wants to override an automated capture with hand-captured media.
  • A release calls for a fresh capture or a frozen archive of the shots its notes embed.
  • A media-guard test (features.test.ts or shots.test.ts) fails because an asset or registry entry is missing.

Commands

pnpm --filter @dorkos/e2e capture                  # record + process (the full refresh)
pnpm --filter @dorkos/e2e capture:record           # boot + drive + save raws to the library
pnpm --filter @dorkos/e2e capture:record --shards N # same, but record on N parallel isolated stacks
pnpm --filter @dorkos/e2e capture:process [run-id] # edit raws + apply overrides → product/ (default: latest)
pnpm --filter @dorkos/e2e capture:archive <label>  # freeze the current published set under archive/<label>/
pnpm --filter @dorkos/e2e test                     # unit tests: registry, partition, aspect guard, override discovery

--shards N (parallel record) splits the shots across N fully isolated stacks — each its own DORK_HOME (~/.dork-capture for shard 0, ~/.dork-capture-<i> after), server/Vite port pair (4344/4343 + i×10), and browser — recorded at the same time, then merged into one run. The process phase is unchanged: a serial run and a sharded run produce the same published asset set. Default is 1 (the serial path). Reach for it to shorten a full re-record when the box has spare cores; 2 shards is the reliable win, and returns fall off past that once per-shard boot+seed overhead dominates. --shards also works on capture (only the record phase parallelizes). Details: apps/e2e/capture/README.md (Parallel capture).

Read the full file on GitHub · 129 lines

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. 10d ago First seen · 129 lines · 104 tokens per session scan A c6c787c0bd1d

Subscribe to this mod's changes

capturing-product-media is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 4,213 once invoked, about $0.0005 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

hive.image-generation

Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…

aden-hive/hive · 149 tokens

slides-deck

Use when asked to create a slide deck, presentation, pitch deck, or talk outline — or to convert a markdown document into a slides format. Triggers on "create a deck", "slide deck", "presentation", "pitch deck", "talk slides", "convert to slides", or "markdown to slides".

tmj-90/gaffer · 67 tokens

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

thevibeworks/claude-code-docs · 62 tokens

slack-gif-creator

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.".

thevibeworks/claude-code-docs · 51 tokens

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

thevibeworks/claude-code-docs · 59 tokens

greeting

Replaces ordinary greetings with nautical ones.

thevibeworks/claude-code-docs · 11 tokens