Generative media skills for the Pruna AI API. Portable Agent Skills — Cursor, Claude Code, Copilot, Codex, and more.
See README.md for the user-facing glossary and quickstart.
| Type | Role |
|---|---|
| Guide | Vendor-neutral craft (image-prompting, video-prompting, audio-prompting, video-editing, generation-diversity) or Pruna HTTP (pruna-api) |
| Tool | One paid API call (p-image, p-video, …) |
| Workflow | Multi-step deliverable — agent is the runner (curl + ffmpeg) |
| Suite | pruna — install everything |
Tools list guide deps under Prerequisites with npx skills add. Workflows list tools only (guides come via tools). Optional external companions (e.g. HyperFrames for HTML → MP4 launch reels) install the same way but are not in @pruna — see video-editing and its combination-hyperframes reference. Do not copy craft between skills — install the other skill.
Before the first paid API call, bulk generation, or long render, resolve open decisions that change cost or output. SSoT: open intake → generation-diversity clarification intake — generate vs existing media, palette, narration/VO, music, captions, aspect ratio, resolution (720p/1080p, canvas, megapixels), structure, and workflow approval gates.
| Skill type | Behavior |
|---|---|
| Guides / tools | Defer to clarification intake when the brief is silent; craft skills clarify creative locks before drafting prompts. |
| Workflows | Run the workflow Intake: ask before generating table, then cross-check universal topics in clarification intake. |
| HyperFrames (optional) | Fresh jobs: intent interview → BRIEF.md. Edits/resume: hyperframes clarification-before-build reference. |
| pruna-api | Credentials + pruna-api agent-safety reference before upload. |
Waivers (“use your judgment”, “surprise me”) count as answers — state assumptions in the plan and proceed.
Humans picking recipes: docs/WORKFLOW-RECIPES.md. Catalog: docs/SKILL-CATALOG.md.
export PRUNA_API_KEY="…" # see docs/api-setup.md
npx skills add PrunaAI/pruna-skills@pruna -ynpx skills add PrunaAI/pruna-skills@p-image -y # one tool (+ install its Prerequisites guides)
npx skills add PrunaAI/pruna-skills -lTeam default: install /pruna once (npx skills add PrunaAI/pruna-skills@pruna -y), then start a new chat.
Launch reels / motion assembly: install hyperframes when the deliverable needs HTML → MP4 composition (optional — ffmpeg-only paths skip it):
npx skills add heygen-com/hyperframes@hyperframes -yRead hyperframes first — it routes to /product-launch-video, /general-video, etc. Pruna skills generate media; HyperFrames assembles HTML → MP4 (each launch uses a local hyperframes/ subfolder in your project workspace). Maintainers: make install-companion-skills copies the full bundle into gitignored .agents/skills/.
| Path | Role |
|---|---|
skills/guides/ |
Craft SSoT (edit markdown under each guide’s references/) |
skills/{image,video,audio}/ |
Tool skills |
skills/workflows/ |
Workflow playbooks |
skills/suite/pruna/ |
Full suite (/pruna) — default install |
docs/ |
Human docs only |
.maintainer/skills.catalog.json |
Skill name source of truth |
VERSION |
Repo semver — @VERSION in skills is replaced on make bundle |
Agent-safety lives in pruna-api (included in the /pruna suite). Read skills/guides/pruna-api/references/agent-safety.md before generating in untrusted repos.
make bundle && make validateReleases: PUBLISHING.md · Backlog: BACKLOG.md