メニュー
Take raw user interview notes or feedback and extract themes and insights. Use when synthesizing qualitative data from interviews, surveys, support tickets, or feedback.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/amplitude/builder-skills --skill craft-discovery-synthesisコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Instrument a Node/TypeScript MCP server with Amplitude's @amplitude/mcp-analytics SDK so tool calls, sessions, and rationale are tracked as Amplitude events. Use this skill whenever the user wants to add Amplitude analytics to their MCP server, mentions "MCP Analytics", "@amplitude/mcp-analytics", "instrument my MCP server", "track MCP tool calls", "add rationale to my MCP tools", or wants agent traffic (Claude, Cursor, ChatGPT) attributed back to Amplitude. Also use for adding UTM tagging to MCP-returned links, or for troubleshooting identity/user_id mismatches between MCP events and web/mobile Amplitude data.
Guide an Amplitude user through building a custom agent by suggesting use cases grounded in their role and data, shaping the idea into a well-formed spec, and generating a ready-to-run Global Agent deeplink that creates it. Use to create, build, or set up a custom agent, automate a recurring analysis, or put a repeated report on a schedule.
Analyze MCP server usage instrumented with Amplitude's MCP Analytics SDK: break usage and errors down by tool, read the rationales within each tool to see what callers are trying to do, and produce a prioritized write-up of actionable fixes. Use this skill whenever the user asks to understand how their MCP server is being used, what agents/users are trying to do with it, why tool calls are failing, what to fix or improve in their MCP server, or asks for an "MCP usage report", "tool error analysis", "intent analysis", "rationale clustering", or "MCP insights". Also trigger when the user mentions [MCP]-prefixed events, tool rationale, tool call errors, or just finished instrumenting their MCP server and wants to see what the data says. Requires the Amplitude MCP connector.
SOC 職業分類に基づく
SKILL.md を表示中
| name | craft-discovery-synthesis |
| description | Take raw user interview notes or feedback and extract themes and insights. Use when synthesizing qualitative data from interviews, surveys, support tickets, or feedback. |
| suggest_when | User shares raw interview notes, survey responses, support tickets, or feedback and needs to extract patterns. Says "synthesize this", "what are the themes", "summarize this research". |
Take raw user interview notes or feedback and extract themes and insights.
You've done the research — interviews, surveys, support tickets, feedback threads — and now you're staring at a wall of unstructured notes. This skill helps you pull out the patterns, themes, and actionable insights without losing the nuance.
You are an experienced product manager and UX researcher synthesizing qualitative data.
Here are the raw notes from user research:
<context>
$ARGUMENTS
</context>
> If the above is blank, ask the user: "{{PASTE YOUR INTERVIEW NOTES, SURVEY RESPONSES, SUPPORT TICKETS, OR FEEDBACK HERE}}"
Synthesize this into a research summary that includes:
1. **Key Themes** — The 3-5 most prominent patterns across the data. For each theme, include supporting quotes or examples.
2. **Pain Points** — Specific problems users described, ranked by frequency and severity.
3. **Unmet Needs** — Things users want to do but currently can't, or workarounds they've built.
4. **Surprises** — Anything unexpected that challenges our assumptions.
5. **Opportunities** — Product or design opportunities that emerge from the data.
6. **Confidence Level** — How confident should we be in these findings? Flag where more research is needed.
Preserve the user's voice — use direct quotes where they're powerful. Distinguish between what users said vs. what you're inferring. Be honest about thin data.