agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required…
Use when a film needs product visuals — capturing real screenshots at a fixed DPR, the real OS pointer, masking sensitive data with labeled example data, avoiding third-party brand look-alikes, and recording provenance in .motion/assets.json.
$ npx -y skills add fusengine/agents --skill motion-assets --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/motion-assetsContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a film needs product visuals — capturing real screenshots at a fixed DPR, the real OS pointer, masking sensitive data with labeled example data, avoiding third-party brand look-alikes, and recording provenance in .motion/assets.json.
name: motion-assets description: "Use when a film needs product visuals — capturing real screenshots at a fixed DPR, the real OS pointer, masking sensitive data with labeled example data, avoiding third-party brand look-alikes, and recording provenance in .motion/assets.json." versions: fuse-motion: "1.0.0" user-invocable: false references: references/real-screenshots.md, references/pointer-and-brands.md, references/data-masking.md, references/provenance.md, references/templates/assets-json.md related-skills: motion-method, motion-craft, motion-render, motion-review, fuse-ai-pilot:fuse-browser-usage
<objective> Stage 3 of the `motion-method` pipeline: every product visual in a film is a real capture of the real product, taken at a fixed device pixel ratio, with sensitive data masked before capture and an "Example data" label wherever placeholder data replaces real values. Each asset is recorded in `.motion/assets.json` with its source URL, capture settings, masking applied, and sha256, so the critic's truth-safety criterion can be checked against a file rather than a promise.
It does not draw UI. A screen the product does not have is "invented UI" — a hard-fail in `motion-review`. </objective>
| Step | Who / Tool | What | |------|-----------|------| | Before capturing | read `fuse-ai-pilot:fuse-browser-usage` | Tool routing and batching rules for `mcp__fuse-browser__*` | | Capture N screens | `browser_shots_batch` (one call, N URLs) | Real screenshots — never a per-URL loop | | DPR must be pinned | CDP `Emulation.setDeviceMetricsOverride` (`deviceScaleFactor`) | Same approach as `docs/demo/statusline-mod/motion-capture.js` | | After capture | write `.motion/assets.json`, run the check script | Provenance + hash | | Draft review | `motion-critic` via `motion-review` | Truth-safety criterion uses `assets.json` |
---
| Concern | Rule | Reference | |---------|------|-----------| | **Real screenshots** | Captured from the running product, fixed DPR, fixed viewport | [real-screenshots.md](references/real-screenshots.md) | | **Pointer & brands** | Real OS pointer (hotspot, scaled with camera); no third-party brand look-alikes | [pointer-and-brands.md](references/pointer-and-brands.md) | | **Masking** | Replace sensitive values before capture; label "Example data" | [data-masking.md](references/data-masking.md) | | **Provenance** | Every asset in `.motion/assets.json` with source, settings, masking, sha256 | [provenance.md](references/provenance.md) |
---
1. **Real screenshots only** — no redrawn, mocked, or generated UI standing in for the product. 2. **Fixed DPR and viewport per film** — mixed DPRs give mismatched sharpness between beats. 3. **Mask before capture, not after** — replace values in the page; blur and pixelation are not masking. 4. **Label placeholder data "Example data"** — on screen, wherever real values were replaced. 5. **Sensitive-data list comes from the brief** — plus the user-level banned list; never write literal sensitive values into the repo. 6. **No asset without a provenance entry** — an unlisted file in the scene is treated as invented. 7. **Never client names, never real spend amounts** — in assets, labels, filenames, or examples. 8. **Real OS pointer, never a drawn arrow** — hotspot respected, scaled with the camera, recorded as `kind: pointer`. 9. **No third-party brand look-alikes** — another company's signature color, logo, or app chrome is a trademark risk; use the owner's brand or neutral placeholders.
---
<project>/.motion/ ├── brief.md # sensitive-data list (categories) ├── assets/ │ ├── raw/ # NOT committed — pre-mask captures, if any were needed │ └── <name>@<dpr>x.png # masked, labeled captures used by the scene └── assets.json # provenance (template: assets-json.md)
---
| Topic | Reference | When to Consult | |-------|-----------|-----------------| | **Real screenshots** | [real-screenshots.md](references/real-screenshots.md) | Capturing product screens; DPR, viewport, state setup | | **Pointer & brands** | [pointer-and-brands.md](references/pointer-and-brands.md) | A beat shows a cursor; anything borrowed from another company | | **Data masking** | [data-masking.md](references/data-masking.md) | Anything from the sensitive-data list could appear | | **Provenance** | [provenance.md](references/provenance.md) | Recording and checking where each asset came from |
| Template | When to Use | |----------|-------------| | [assets-json.md](references/templates/assets-json.md) | Writing `.motion/assets.json` and its check script |
---
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required…
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers:…
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to…
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication,…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before…