Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
中文简介正在准备中。当前显示原文说明。
Triage feedback from docs, issues, Slack threads, or pasted notes into verified bugs, UX proposals, unclear questions, and skipped noise. Use when a user asks you to address product feedback or investigate a reported workflow.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use this skill when the user shares a feedback document, issue, thread, or pasted notes and asks you to address the feedback.
The default posture is judgment plus action: fix clear, verified bugs you agree with; propose UX changes with rationale; skip or flag low-signal, unclear, or out-of-scope items.
AGENTS.md before touching code.Read the feedback source.
| Source | Reader |
|---|---|
| Notion link | Notion connector or Notion skill |
| Google Docs/Drive link | Google Drive connector or Google Docs skill |
| Linear link | Linear connector if installed; otherwise ask for pasted content |
| GitHub issue or PR | GitHub connector or gh issue view / gh pr view |
| Slack thread | Slack connector |
| Public URL | Web browsing |
| Pasted text | Read directly |
Use web browsing only for public URLs. Auth-gated docs usually need their matching connector. For threads, read the parent and all replies; note when there are no replies, and inspect linked files or newer follow-ups when the source refers to them.
Check whether this defect has already been reported.
A feedback channel holds months of reports and nobody remembers all of them, so the same defect gets filed by different people weeks apart and every filing reads as new. One recorded case: the same Clips recording bug was filed almost word-for-word 29 days apart by the same reporter, and neither message mentions the other. Another defect was reported fifteen times by nine people across three months, was announced as fixed once in the middle, and was reported again two weeks later.
Search before fixing, going back at least three months: the source channel in the reporter's words and in your own, Sentry, and merged PR titles. Search the feature name, the error text, and the surface separately — repeat reports rarely share vocabulary.
Report the repeat explicitly, with dates and reporters. A defect on its third report is not a bug ticket, it is a missing check — and the missing check is the deliverable, not the patch.
Decompose and categorize every actionable item.
Build a compact checklist before changing code. For each item, record the symptom, expected behavior, evidence, and owning surface: UI, action/tool, data model, provider/runtime, or product policy.
For data, permissions, or resource-lifecycle feedback, verify the whole capability boundary before calling it UX.
Check Sentry when the feedback smells like an error.
builder-io unless the user specifies another.Fix only the clear bugs you agree with.
Treat UX feedback with product judgment.
Do not add visible UI as the default response. Address the underlying user problem first, then choose the smallest change that makes the current state, decision, action, or recovery path clearer.
DropdownMenu, Popover, Sheet,
Collapsible, tabs, or another contextual surface. Keep essential meaning,
labels, focus, hit targets, and recovery in the default path.When the user has corrected the same visual preference more than once, treat it as an acceptance criterion for the surface, not as a one-off copy edit. State the underlying invariant before coding, such as “the default state makes one next decision obvious and defers secondary detail,” then check the rendered result against it. A screenshot showing unrelated forms, repeated explanatory copy, documentation links, or competing controls in the default state fails the review. Subtract that competition instead of explaining the UI with more copy.
When proposing a UX change, write it as: what to change, why it helps, and the tradeoff. Keep each proposal short.
Verify changed behavior.
Keep the final report short:
## Repeat Reports
- [defect] - reported [N] times since [date] by [reporters]; [what now fails if it regresses]
## Bugs Fixed
- [feedback item] - [what changed, file:line]
## Bugs Flagged But Not Fixed
- [feedback item] - [why]
## UX Suggestions
- [feedback item] -> [proposed change]
## Skipped
- [feedback item] - [reason]
Only include sections that have content. The user can read the diff; do not write a second feedback document.
github:gh-address-comments for GitHub PR review threads.github:gh-fix-ci for failing GitHub checks.sentry:sentry for production error investigation.frontend-design for approved UI implementation work.qa for broader browser verification.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
中文简介正在准备中。当前显示原文说明。
Automate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.
中文简介正在准备中。当前显示原文说明。
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
中文简介正在准备中。当前显示原文说明。
Build integrated IS/BS/CF financial workbooks in Excel.
中文简介正在准备中。当前显示原文说明。
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTER_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability SKILL.md from the URLs below when needed.
中文简介正在准备中。当前显示原文说明。
Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.
中文简介正在准备中。当前显示原文说明。