菜单
How to view, export, and analyze form responses. Use when the user asks about submitted data, wants to export responses, or needs response analytics.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
How to look up version-matched Agent Native framework docs in node_modules. Use before coding against @agent-native/core APIs or advanced features.
Use Content for repo-backed Markdown/MDX docs, blogs, resources, rich document editing, local components, shareable copies, and Content local-file workspaces. Prefer Content actions over raw filesystem writes when available.
All AI features in Clips — titles, summaries, chapters, tags, filler-word removal — delegate to the agent chat via sendToAgentChat except the narrow media pipeline path: transcription. Use when adding any AI-powered feature.
How Clips shares recordings — composes with the framework sharing skill and adds password, expiry, embed URLs, and view-counting. Use when wiring the share dialog, building embed links, adding a password, or debugging who can see a recording.
Cross-platform pattern for handling messaging integration webhooks (Slack, Telegram, WhatsApp, email, etc.) on serverless hosts. Use when adding a new integration adapter, debugging dropped messages, or wiring long-running agent work into a webhook handler.
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.
| name | form-responses |
| description | How to view, export, and analyze form responses. Use when the user asks about submitted data, wants to export responses, or needs response analytics. |
Use list-responses to see submissions for a specific form:
pnpm action list-responses --form <form-id> [--limit 50]
This shows each response with field labels and values, ordered by submission date (newest first).
For chart/table analytics, prefer response-insights:
# All recent accessible forms
pnpm action response-insights
# One form
pnpm action response-insights --formId <form-id> --days 30 --limit 300
response-insights returns an explicit first-party widget payload:
widget: "data-insights"chartSeries for submissions by daytable for recent response rowssummary with total, sampled, and truncation detailsNative chat renderers should use that contract for first-party tables/charts. MCP Apps/iframe rendering is only a fallback for external hosts.
For form setup/configuration previews, use preview-form:
pnpm action preview-form --formId <form-id>
It returns a native inline summary/table with the form fields, response count, status, visibility, and an "Open editor" action.
Use export-responses to export to CSV or JSON:
# CSV export (default)
pnpm action export-responses --form <form-id> --output data/export.csv
# JSON export
pnpm action export-responses --form <form-id> --output data/export.json --format json
The CSV includes headers derived from field labels. Array values (multiselect) are joined with semicolons.
Each response is stored in the responses SQL table:
| Column | Type | Description |
|---|---|---|
id | text | Unique response ID |
formId | text | Foreign key to the form |
data | text | JSON string of field ID -> value map |
submittedAt | text | ISO timestamp |
The data JSON maps field IDs to values:
{
"name": "Alice Smith",
"email": "alice@example.com",
"rating": 5,
"interests": ["design", "development"]
}
To analyze responses, the workflow is:
list-forms to find the form IDpreview-form --formId <id> when the question is about setup or fieldsresponse-insights --formId <id> for counts, daily submissions, and table datalist-responses --formId <id> only when exact row-level inspection is needed| User request | What to do |
|---|---|
| "@Form setup?" | preview-form --formId <id> and answer from the returned fields/settings |
| "How many responses?" | response-insights --formId <id> and report summary.responses |
| "Export to CSV" | export-responses --form <id> --output data/export.csv |
| "Submissions by day" | response-insights --formId <id> --days 30 |
| "Summarize feedback" | response-insights, then list-responses if more detail is needed |
| "Average rating" | list-responses, compute from rating fields and state the sampled row count |
| "Who submitted today?" | list-responses, filter by submittedAt |