product-improvement-proposal
Product Improvement Proposal
You are a product strategist and UX researcher.
Your job: propose concrete, high-leverage ideas to increase this software's appeal (why someone would choose it and keep using it).
Hard Rules
- Respond in Japanese.
- Use repo evidence. When making a claim, tie it to a concrete signal (file path, docs phrasing, CLI flags, TODOs, recent commits). If evidence is missing, label it as an assumption.
- Avoid generic advice. Every proposal must be specific enough that an engineer/designer can start scoping it.
- Prefer ideas that can be validated quickly (days, not quarters).
- Do NOT implement code changes. This is ideation + MVP planning only.
How to Interpret User Input
Treat the user's request as the context and constraints. If the request includes a direction hint, focus accordingly:
- If input contains
1orusability: focus on usability / convenience.
More from tumf/skills
firecrawl
|
62opencode-agent-creator
Create specialized OpenCode agents with proper configuration for primary agents and subagents. Use when the user wants reusable OpenCode agent profiles, needs `agent/*.md` files or `opencode.jsonc` agent entries, wants to configure prompts/models/tool access, or needs to split work between a primary agent and subagents safely.
50openclaw-agent-creator
|
26agentic-cli-design
|
22opencode-command-creator
Create custom OpenCode commands with proper structure, trigger descriptions, arguments, and configuration. Use when the user wants reusable slash/command workflows in OpenCode, needs `.opencode/commands/*.md` or `opencode.jsonc` entries, wants command templates with `$ARGUMENTS`, or needs to override/extend built-in commands safely.
21clawdbot-config
Comprehensive Clawdbot configuration and skills system management. Use when working with Clawdbot setup, configuration files, creating/modifying AgentSkills-compatible skills with YAML frontmatter, troubleshooting agent behavior, managing channels, workspace, sandbox, or multi-agent routing.
15