Skip to content

Adonis0123/adonis-skills / skills/prompt-studio

prompt-studio

Flagged

Turn a one-line image or video request into a finished asset: route it to an image, a code-rendered Code Video or a Model Video, search many GitHub prompt libraries for proven image prompts, video-model prompts (Seedance, Kling, Veo, Hailuo/MiniMax, Wan, Grok Imagine) and code-video templates, show the best 5 with their samples, model, author and license, write a generation brief, hand it to an available channel (host tool, Codex/Grok CLI, API, Hyperframes), then check and log the result. Use whenever the user wants a cover, illustration, poster, thumbnail, infographic, animation, motion clip, AI video, or a better prompt for one, even if they only say 'make me an image'. Also for Chinese-language requests for WeChat covers, illustrations, still-to-motion clips, and image/video prompt optimization. Not for general chatbot or coding prompts, photo editing without generation, UI implementation, or slide decks.

references/channels.md

View on GitHub
# Channels

This skill never generates. It hands a Generation Brief to a Channel.

## Detect what exists

`studio.mjs session` already reports CLI presence (codex, grok, ffmpeg), whether Node can run the helper (`nodeOk`), and the names of key variables. Do not probe those again. The table shows what each signal means. Hyperframes still needs its own version check, below.

| Check                                                                                          | Means                                                  |
| ---------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
| The current host exposes `image_gen` / `image_edit` / `reference_to_video` (Codex, Grok Build) | Host tool available                                    |
| `command -v codex`                                                                             | Codex CLI: images via its `image_gen`                  |
| `command -v grok`                                                                              | Grok Build CLI: images and video via its Imagine tools |
| An API key variable named in the Style Pack is set (check with `[ -n "$VAR" ]`, never echo it) | HTTP API available                                     |
| `node --version` ≥ 22 and `command -v ffmpeg`                                                  | Code Video rendering possible (Hyperframes)            |

These are discovery signals, not readiness checks: a CLI version does not prove login, and a set key variable does not prove valid credentials. Inspect the host’s actual tool list; before handoff check the selected channel’s authentication and supported parameters without generating or spending. The helper’s `nodeOk` means Node 18+ for the helper, not Hyperframes’ Node 22+ requirement. Session does not include the version number, so read `node --version` before calling Hyperframes runnable. If the host has no generation tool, hand off to an available channel.

## Priority

1. A Channel the user named in this request.
2. The Channel the Style Pack names as preferred.
3. The current host's own tool.
4. Other detected Channels: pick the first one that can produce the output type and say which in one line; ask only when none fits or the choice costs money.

## Invocation

Codex prompts go through stdin, not a shell argument: its `-i` flag swallows every argument after it, and quoting breaks on long prompts. `studio.mjs brief` writes a provenance file (source, license, paths). Pass the generation text — `content`, whose first line is the instruction below — not that markdown file. Feeding the provenance file in makes the model read headings before the prompt.

**Codex CLI (images)**

```bash
codex exec -s workspace-write -C "$PWD" -i ref1.png -i ref2.png - < prompt.txt
```

`prompt.txt` starts with: `Generate one image with image_gen and save it as <absolute path>.` Outside a Git repository add `--skip-git-repo-check`. Reference images go in as `-i` flags before the final `-`, which makes Codex read the prompt from stdin.

- One call makes one image. For 2–4 variants run that many calls in parallel (3–4 at most), each with its own output path.
- Codex returns its own fixed sizes (for example 1536×1024) and does not honour exact pixel sizes such as 1800×766. Generate at the nearest native shape, then fit it (see `image.md`).

**Grok Build CLI (images, video)**

Inside a Grok session, call its own `image_gen` (only `prompt` and `aspect_ratio`) and copy the returned file to the brief's output path; do not start a second, auto-approved Grok. The CLI form below is for other hosts.

```bash
grok -p "$(cat prompt.txt)" --always-approve --output-format json
```

This passes the prompt as one shell argument. Keep the double quotes so the shell does not split it. For long prompts use `grok --prompt-file prompt.txt --always-approve --output-format json` instead. Only use `--always-approve` inside a working directory you are willing to let it write to. In the prompt, name the tool (`image_gen`, `image_edit` or `reference_to_video`), the output path and every parameter. Grok has no text-only video: `reference_to_video` needs at least one reference image.

**HTTP API**

Write a short script that reads the key from the environment variable, submits the task, polls until it finishes (video is asynchronous; poll every 10–15 s with a timeout), and downloads the result. Print task id and status, never the key.

**Render engines**

See `code-video.md`.

## After the run

Confirm the file exists and is non-empty, then run the quality gate. A Channel exiting successfully is not proof that the asset is right.
canvas-designanthropics/skillsCreate 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.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall