gitroomhq/agent-media-v2
/SKILL.md
AI UGC video production via agent-media (selfie, character, subs, plus more soon). BEFORE running ANY agent-media command you MUST first Read reference/conversation-flow.md and walk the user through the 4 gates IN ORDER — (1) confirm script OR scene_action; if no speech, also propose background_music, (2) RUN `agent-media character list --json` YOURSELF (don't ask the user, don't mention char_xxx ids — present saved characters BY NAME if any, otherwise confirm the new description), (3) propose a director's brief with setting, lighting, wardrobe, props/product, and action; pass non-default motion/product handling through --scene-action, (4) duration with script-pacing awareness (2-4 words/sec). While jobs run, poll status and open portrait, character sheet, wireframe, and final video as each URL appears. When user says "no subs" → pass --subtitles false. When no script → pass --background-music. NEVER auto-pick a character. NEVER expose char_xxx ids. NEVER mention pricing/credits/USD.
$ install --global
skillsauthnpx skillsauth add gitroomhq/agent-media agent-media-v2Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 24, 2026, 6:46 AM101.5s12 files scanned
SKILL.md
- name:
- agent-media-v2
- description:
- AI UGC video production via agent-media (selfie, character, subs, plus more soon). BEFORE running ANY agent-media command you MUST first Read reference/conversation-flow.md and walk the user through the 4 gates IN ORDER — (1) confirm script OR scene_action; if no speech, also propose background_music, (2) RUN `agent-media character list --json` YOURSELF (don't ask the user, don't mention char_xxx ids — present saved characters BY NAME if any, otherwise confirm the new description), (3) propose a director's brief with setting, lighting, wardrobe, props/product, and action; pass non-default motion/product handling through --scene-action, (4) duration with script-pacing awareness (2-4 words/sec). While jobs run, poll status and open portrait, character sheet, wireframe, and final video as each URL appears. When user says "no subs" → pass --subtitles false. When no script → pass --background-music. NEVER auto-pick a character. NEVER expose char_xxx ids. NEVER mention pricing/credits/USD.
- version:
- 3.4.0
<!--
AUTO-GENERATED — do not hand-edit.
Source: packages/schema/src/v2/generators.ts
Regenerate: pnpm --filter @agentmedia/schema gen:v2-docs
-->
agent-media — Claude skill
agent-media is a CLI for AI UGC video generation. This skill tells you how to drive it. Loaded files are intentionally small — open the right reference file for the task you have, don't try to memorize everything.
🛑 HARD GATE — read this first, every conversation
Before calling ANY agent-media shell command, you MUST:
- Read
reference/conversation-flow.md— the full 4-gate protocol with templates. - Walk the user through 4 gates IN ORDER, one message each — do not bulk-fire:
- Gate 1: confirm the exact script (verbatim — typos land in the video)
- Gate 2: confirm character. YOU run
agent-media character list --json(do not ask the user "do you have a saved character?" — they don't know that's a thing). If the list is empty, just confirm the description from their original prompt. If non-empty, present each saved character BY NAME (not bychar_xxxid — that format is internal). The user picks by NAME or says "new"; you map name → id internally. 🛑 NEVER auto-pick. NEVER showchar_xxxids to the user. Never ask for a photo by default. - Gate 3: propose a full director's brief with pre-filled fields in 3 sections — A. Intent+Performance, B. Scene+Look, C. Output. Put visual direction into
--descriptionand action/product handling into--scene-action; there are no--preset,--vibe, or--voice-briefflags in the current Selfie API. - Gate 4: duration + script-pacing check. Count the words in the script and PROPOSE the duration that fits (5s ≈ 10-20 words, 10s ≈ 20-40 words, 15s ≈ 30-60 words at the natural 2-4 words/sec pace).
- Only then call the CLI.
The director's brief at Gate 3 is non-optional. It's where quality lives. Skipping it = generic output. PROPOSE smart defaults from the script + description; don't ask blank questions.
Calling the CLI without doing 1–3 is a protocol violation — the user gets a generic, mid video. Ask the extra questions.
NEVER discuss pricing
Do NOT mention credit costs, USD amounts, or pricing tiers in any reply. Do NOT ask the user to "confirm cost". The API handles billing transparently. If the user asks about cost, point them at https://agent-media.ai/pricing. That is the only acceptable surface for pricing.
What agent-media can do (router)
| Command | Use when | Deep-dive |
|---|---|---|
| selfie | AI UGC selfie video with generated actor, character sheet, storyboard board, and Seedance. | reference/generators/selfie.md |
| character create | Create a reusable AI character from a single photo. | reference/generators/character_create.md |
| subs | Burn styled subtitles onto an existing video. | reference/generators/subtitle.md |
agent-media skill update — pull the latest skill files into ~/.claude/skills/agent-media-v2/.
agent-media skill status — print local vs remote version.
What agent-media CANNOT do
These legacy v1 commands exist in the CLI binary for backwards compat but produce inferior output. They are hidden from agent-media --help for a reason. Never call them.
- ❌
agent-media ugc— uses a stale fixed actor library (200 actors picked at random). The actors look dated. Useagent-media selfie— it generates an on-model character from your description on every run. - ❌
agent-media show-your-app— built on the v1 actor pool + manual screen-composite step. The v2 product is on the roadmap. For now, runagent-media selfiefor the talking head and capture the screen separately. - ❌
agent-media laptop-ugc— v1 only. Same story as show-your-app; v2 product coming. - ❌
agent-media character-video— superseded byagent-media selfie --character <id>. The new command uses the current portrait → sheet → wireframe → Seedance pipeline. - ❌
agent-media text-to-video— no character control; output is generic and off-brand. Useagent-media selfiewith a saved character. - ❌
agent-media subtitle(singular) — v1 burner with fewer styles and shakier sync. Useagent-media subs(plural). - ❌
agent-media review— SaaS-review generator built on v1 actors. Compose withagent-media selfie+ a script you write. - ❌
agent-media product-acting— v1 product-in-hand generator. For now, useagent-media selfiewith a strong--scene-actiondescribing the product hold, demo, and interaction.
If the user wants a feature not listed in the router above, offer agent-media selfie when the request can be expressed as one actor, one setting, dialogue/action, and optional props/product handling.
Reference files (lazy-loaded)
Open these only when you need them:
reference/conversation-flow.md— the 3 gate questions, in order, with example wordingreference/subtitle-styles.md— all 17 subtitle stylesreference/realism-rubric.md— visual-quality guard the pipeline enforcesreference/errors.md— common errors + remediationreference/generators/selfie.md— AI UGC selfie video with generated actor, character sheet, storyboard board, and Seedance.reference/generators/character_create.md— Create a reusable AI character from a single photo.reference/generators/subtitle.md— Burn styled subtitles onto an existing video.
Related Skills
gitroomhq/Make Product In Hands
content-media
VerifiedTrustedCommunity
Generate a 5/10/15s vertical UGC video where your character holds, wears, and shows a product. Provide a character_sheet_url (R2-hosted) and the product image (product_image_url — any https URL — OR product_image_base64; re-hosted to R2 automatically). Two modes: script for a lip-synced talking-head product review (2-4 words/sec), OR scene_action for a silent demo / b-roll. Set subject (e.g. "a young woman") to lock the person's gender/appearance so a gendered product can't drift it. framing: "close_up" (chest-up, default) or "full_body" (head-to-toe, for turn-arounds / showing the whole outfit). Both the person and the exact product are locked from the reference images.
41SKILL.mdUpdated Jun 4, 2026
gitroomhq/Publish to Social
development
VerifiedTrustedCommunity
Publish a generated agent-media video to the user's connected TikTok, Instagram, or X. Connect channels (OAuth) and post or schedule via the REST API. Use after producing a video with make_ugc_video / make_simple_selfie.
41SKILL.mdUpdated May 31, 2026
gitroomhq/Agent-Media UGC Playbook
testing
VerifiedTrustedCommunity
Playbook for orchestrating an end-to-end UGC video on the agent-media vNext runtime. Read this before deciding whether to call the one-shot make_ugc_video skill or to chain the four primitives (make_portrait → make_character_sheet → make_simple_selfie → make_subtitles) manually.
41SKILL.mdUpdated May 29, 2026
gitroomhq/Make Wireframe
tools
VerifiedTrustedCommunity
Generate a photographic storyboard / wireframe board from a character sheet (R2-hosted) + script. Multi-panel grid showing the same person performing the action progression, 4 / 6 / 8 / 10 numbered panels.
40SKILL.mdUpdated May 31, 2026