remember-design-system
Use when an agent is about to build or refactor interface code and needs a compact, repository-specific brief covering existing tokens, components, routes, conventions, and verification commands.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- remember-design-system
- description
- Use when an agent is about to build or refactor interface code and needs a compact, repository-specific brief covering existing tokens, components, routes, conventions, and verification commands.
02 资源文件 1
- 参考文档agents/openai.yaml210 B
03 SKILL.md 正文
Remember The Design System
Build design context from the repository instead of guessing from the prompt. This is a preflight for UI work, not a request to redesign the product.
This workflow targets published beta 2.8.0-beta.2. Use npx -y @memi-design/cli@2.8.0-beta.2 --version to verify the exact package; a local memi must report that same version before these recipes run. The independent stable compatibility baseline is 2.7.9. See current release state and known limitations. npm availability alone does not establish native-binary success.
Build The Brief
Translate the user's task into a short intent, then run from the repository root:
memi agent brief . --frontend --intent "<user's interface task>" --max-bytes 16384 --json
The frontend brief already includes bounded token and story evidence. For a selected Figma or Paper node, use the harness connector and supply its normalized evidence:
memi agent brief . --frontend --intent "<task>" --design-evidence design/selected-node.json --json
Apply The Memory
- Prefer existing components and the project's conventions. Do not impose a new component library or CSS framework.
- Map every new component to atom, molecule, organism, template, or page.
- Reuse semantic CSS variables and Tailwind theme tokens. Do not introduce raw hex values when a token exists.
- Preserve route, state, loading, empty, error, focus, and responsive behavior identified by the brief.
- Resolve stale/conflicting mappings and missing required props before editing. Read cited source files when the bounded brief omits needed details.
- Treat inferred story IDs and host-supplied mappings as evidence, not rendered verification. Run the actual project tests.
Handoff
Before editing, state the components and tokens you will reuse. After editing, cite files changed, evidence followed, checks run, and any design assumptions that remain.
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.