Generate and Edit AI Media with PonyFlash
AI media work often spans separate generation, editing, and subtitle tools. PonyFlash combines SDK guidance with FFmpeg workflows for images, videos, speech, music, and exports.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "ponyflash" from https://skillstore.io/skills/ponyflash-ponyflash.md and its manifest at https://skillstore.io/api/skills/ponyflash-ponyflash/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "ponyflash". Generate a product hero image for a launch page.
Expected outcome:
The skill confirms API key readiness, selects an image model, submits the prompt, and returns the generated asset link with credit usage.
Using "ponyflash". Cut an 8 second clip and make it web ready.
Expected outcome:
The skill checks FFmpeg support, stages temporary files, trims the source, transcodes the output, and reports the final file path.
Using "ponyflash". Burn these subtitles into my vertical video.
Expected outcome:
The skill checks subtitle filter support, builds adaptive ASS captions, prepares temporary fonts, renders the final video, and removes temporary files.
Most static findings are false positives from Markdown code formatting, installation paths, FFmpeg command examples, and safely quoted helper scripts. I confirmed only the active font download URL assignments as low-risk network behavior and added a medium semantic finding for missing font integrity verification. No prompt injection text or malicious intent was found.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/ponyflash-ponyflash/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/ponyflash-ponyflash?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/ponyflash-ponyflash?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/ponyflash-ponyflash/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/ponyflash-ponyflash.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>ponyflash. (2026). ponyflash security audit report (audit version 4) [Author version 0.3.0]. Skillstore. https://skillstore.io/skills/ponyflash-ponyflash/audits/4@techreport{ponyflash-ponyflash-ponyflash-2026,
author = {ponyflash},
title = {ponyflash security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/ponyflash-ponyflash/audits/4},
note = {Author version 0.3.0}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ponyflash security audit report (audit version 4)"
version: "0.3.0"
type: report
authors:
- name: "ponyflash"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/ponyflash-ponyflash/audits/4"
identifiers:
- type: other
value: "skillstore:ponyflash-ponyflash:audit:4"
description: "Skillstore immutable audit report identifier"
Generate visuals, short videos, voice tracks, and background music for a campaign brief.
Trim clips, merge exports, transcode files, extract audio, or capture thumbnails with stable FFmpeg commands.
Convert subtitle text into adaptive ASS layout and burn captions into final video files.
Use PonyFlash to generate one 16:9 image of a modern product desk scene. Confirm API key readiness before generation.
Plan and generate a 4 second 16:9 video of a city sunrise. Suggest model settings and report credit usage after generation.
Check FFmpeg support, trim input.mp4 from 00:00:05 for 8 seconds, and save the final clip as clip.mp4.
Generate a short voiceover, prepare portrait video subtitles from my SRT file, burn them into the video, and keep only the final export.
Author
ponyflashLicense
MIT
Author version
v0.3.0
Skillstore revision
r1
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
52 downloads · 592 views
Create Pose-Controlled Images and Videos
by doany-ai
Pose and motion control workflows can be hard to route across image and video models. This skill selects the right RunComfy path and prepares clear CLI guidance.
Generate Wan 2.7 Videos on RunComfy
by runcomfy-com
Teams need repeatable text-to-video prompts without guessing every RunComfy option. This skill gives Claude, Codex, and Claude Code a focused Wan 2.7 workflow for prompts, audio URLs, durations, aspect ratios, and outputs.
Run RunComfy Models from the CLI
by runcomfy-com
Teams need a repeatable way to run RunComfy media models from scripts. This skill guides CLI install, authentication, model runs, polling, and downloads.
Create Consistent Video Storyboards
by supercmohq
Video concepts can lose continuity when clips are planned separately. This skill creates sequential storyboard sheets that preserve characters, products, settings, and visual states.
Create Reusable Photorealistic AI Actors
by supercmohq
Campaign teams need consistent fictional talent without supplying a person photograph. This skill creates one detailed adult identity that can guide later image and video generation.
Create and Edit Project Images
by openai
Producing consistent raster assets requires precise prompts, careful edits, and reliable output handling. This skill structures requests, creates or edits visuals, validates results, and saves project-ready files.