release
Guided version bump — validate, tag, and create GitHub release
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/OSideMedia/higgsfield-ai-prompt-skill/HEAD/.claude/commands/release.md -o ~/.claude/commands/release.mdrelease.md
Walk through a release for version $ARGUMENTS (e.g. `/project:release 2.1.0`). If no version argument is provided, check CHANGELOG.md for the latest version and ask what the new version should be. Steps: 0. **Sanitize the version argument** — before using `$ARGUMENTS` in any shell command, confirm it is a bare semantic version matching `^[0-9]+\.[0-9]+\.[0-9]+$` (e.g. `2.1.0`). If it contains anything else (spaces, `;`, backticks, quotes, path separators), STOP and ask the user for a clean version string — never interpolate an unvalidated argument into the `git commit` / `git tag` / `gh release create` shell snippets below. 1. **Validate (strict)** — run `python3 validate.py --strict`. Stop if any check fails. 2. **Changelog check** — confirm CHANGELOG.md has an entry for this version. If not, ask what to add. 3. **Regenerate the user guide + manifest** — AFTER the frontmatter version/date are bumped: `python3 generate_user_guide.py`, then `python3 validate_user_guide.py` (manifest-fallback comparison; review any flagged drift), then `python3 validate_user_guide.py --write-manifest` and stage the refreshed `docs/user-guide/MANIFEST.json`. The PDF itself is a release artifact — it is git-ignored, never committed. 4. **Commit** — stage and commit any pending changes with message: `feat: v$ARGUMENTS — <summary from changelog>` 5. **Tag** — create git tag `v$ARGUMENTS` 6. **Push** — push commit and tag: `git push && git push --tags` 7. **GitHub release** — create release from the tag: `gh release create v$ARGUMENTS --title "v$ARGUMENTS" --notes-file -` using the changelog entry as notes. 8. **Attach the guide** — `gh release upload v$ARGUMENTS docs/user-guide/USER-GUIDE.pdf` so the PDF ships with the release instead of the git history. Confirm with the user before each destructive/visible step (commit, push, release).
Run pre-release validation checks on all SKILL.md files and JSON databases
>
Seedance 2.0 video prompt director. Converts plain-text scene descriptions into production-ready bilingual EN+ZH video prompts optimized for the Seedance 2.0 video generator. Handles action scenes (combat, pursuit, stunts), general scenes (landscapes, journeys, atmosphere), and dialogue scenes (confrontations, negotiations, interrogations). Use this skill whenever the user wants to create a Seedance video prompt, describes a scene for video generation, mentions Seedance, or asks for a cinematic scene breakdown.
>
>
>
>
Use when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts → images → videos across models on one surface. Covers what Canvas is, the node categories, the seven models that run inside Canvas, the named canvas patterns (Simple Seedance, Extend Video, Image Edit, StoryBoard With Elements, Long Video fan-out), the build-free / generate-paid cost model, reusable templates, assets-as-nodes, and Shared Canvas live collaboration. Also trigger on 'Higgsfield ComfyUI alternative', 'node workflow', or 'connect nodes to build a scene/campaign'.