From planning
Synthesize research findings into a ranked proposal with trade-off analysis. Use this skill when the user asks to "propose an approach", "recommend a solution", "compare options", "what should we do", or any request that requires evaluating alternatives and recommending a direction. This skill expects a completed research brief (from the research skill) as input context. It produces a decision-ready proposal — it does NOT decompose work into implementation phases (that is the planning skill's job).
npx claudepluginhub ats-kinoshita-iso/agent-workshop --plugin planningThis skill uses the workspace's default tool permissions.
Proposal is the second phase of the research-plan-implement workflow. It takes
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Analyzes competition with Porter's Five Forces, Blue Ocean Strategy, and positioning maps to identify differentiation opportunities and market positioning for startups and pitches.
Proposal is the second phase of the research-plan-implement workflow. It takes the research brief's alternatives, constraints, and risks and synthesizes them into a ranked recommendation that the user can approve, reject, or refine before any implementation planning begins.
Verify that a research brief exists in the conversation context. It must contain:
If the research brief is missing or incomplete, tell the user and suggest running the research skill first. Do not proceed with incomplete inputs.
Choose 3–5 evaluation dimensions relevant to the problem. Common dimensions:
| Dimension | What it measures |
|---|---|
| Complexity | How much new code, config, or infrastructure is needed |
| Risk | Likelihood of failure, regressions, or surprises |
| Maintainability | Long-term cost of ownership, debugging ease |
| Performance | Latency, throughput, resource usage impact |
| Compatibility | Fit with existing codebase patterns and constraints |
| Time to deliver | Effort to reach a working state |
| Extensibility | How well it accommodates future requirements |
Select dimensions that matter for this specific problem. Not every dimension applies to every decision.
For each alternative from the research brief, score it against each dimension using a 3-point scale:
Provide 1 sentence of evidence per score. Reference codebase findings or external sources from the research brief.
List any decisions the user must make before implementation planning can begin:
If there are no blocking decisions, state that explicitly.
Present the proposal using the template in references/PROPOSAL-TEMPLATE.md.
Once the user approves (or adjusts) the recommendation, move to the planning skill to decompose the chosen approach into phased implementation with gates.