design-refs

Solid

Use only when autopilot-design dispatches visual-reference collection and brief creation. Not for top-level user requests or primary capability routing.

Web & Frontend 7 stars 1 forks Updated today MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
30
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# design-refs ## Language Rule Follow an explicit artifact or audience language when provided. Otherwise, write the brief, captions, and user-facing report in the conversation language according to `<agent-home>/roles/response-policy.md`. Preserve paths, URLs, query literals, tool IDs, and source titles. ## Resolve the Design 1. Use explicit `--design <path>`. 2. Otherwise select the latest applicable `design_state.yaml` under `<artifact-root>/designs/` or `<artifact-root>/spec/*/design/`. 3. If no state exists, report that `design-init` must run first. ## Procedure Do not start without enough context to avoid generic output. When brand, design system, references, and tone are all absent, run one focused clarification round covering product context, the intended variation, tone, length, audience, and constraints. Skip this for a small follow-up. Prefer an explicit gap over an invented brief. ### Step 1: Organize User Material Process `--refs <paths>` and user attachments: - JPG, PNG, or WebP → copy or symlink under `01_refs/_internal/user_provided/` - URL → append to `01_refs/_internal/references_url.md` - text brief → write `01_refs/brief_input.md` Preserve originals and record whether an item was copied or linked. ### Step 2: Collect Optional External References Unless `--no-web` is set, derive focused image-search queries from scope. Useful patterns include: - `ui`: `<feature> dashboard UI inspiration`, `<feature> mobile app UI` - `slide`: `<topic> presentatio...

Details

Author
dmlguq456
Repository
dmlguq456/hearting
Created
5 months ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category