/uipath-feedback

name: uipath-feedback
description: "UiPath bug reports and improvement suggestions via `uip feedback send`. Use for 'report issue', 'send feedback', 'file a bug', or the /uipath-feedback command. For investigating an error rather than reporting one→uipath-troubleshoot."
when_to_use: "User says 'this is broken', 'this isn't working', 'report a bug', 'send feedback', 'something is wrong', 'file an issue', 'this crashed', 'wrong result' about a UiPath product, CLI, or skill. Also fires on the /uipath-feedback slash command."
allowed-tools: Bash, Read, Write, Glob, Grep, AskUserQuestion
user-invocable: true

UiPath Feedback

Send structured bug reports or improvement suggestions to UiPath with auto-captured troubleshooting via `uip feedback send`.

> **Design principle: minimum friction.** The agent already knows what went wrong from the conversation. Don't re-ask what you already know. The only mandatory interaction is confirmation before sending.

Critical Rules

1. **Minimum user interaction.** If the conversation already contains enough context (error, what the user was doing, what went wrong), go straight to confirm and send. Only ask clarifying questions when you genuinely cannot determine what happened. 2. **Never send without explicit user confirmation.** Always show a preview and wait for "yes". 3. **Never include secrets, tokens, credentials, or customer data.** Sanitize all captured content before sending. 4. **Never include full conversation history.** Summarize relevant context in 2-3 sentences. Sample prompts (Step 2e) are a curated max-5 selection — not a transcript. 5. **Use `--output json`** on `uip feedback send` to parse the result programmatically. 6. **If `uip feedback send` fails**, save the report to `./feedback-report.md` so the user does not lose the gathered context.

Workflow

Step 1 -- Check prerequisites

uip --version 2>&1

| Result | Action | |---|---| | Version output | Proceed to Step 2 | | `uip: command not found` | Tell user to run the official installer: `curl -fsSL https://download.uipath.com/uipath-cli/install.sh \| bash` on macOS/Linux, or `irm https://download.uipath.com/uipath-cli/install.ps1 \| iex` in Windows PowerShell. Stop. | | Other error | Show the error. Stop. |

Step 2 -- Introspect and capture (silent -- no user interaction)

Gather all context automatically. Run these substeps silently.

2a. Detect the area

The **area** (which product) becomes the title tag and a Jira label for filtering. Identify it from the last `uip <verb>` the user ran in this conversation. If no `uip` command is identifiable, fall back to the working directory, then to conversation context. Map command/signal → area:

| Last command / signal | Area | |---|---| | `uip rpa …`, or `project.json` + `*.cs`/`*.xaml` | `RPA` | | `uip maestro flow …`, or `*.flow` file | `Flow` | | `uip maestro bpmn …`, or `*.bpmn` file | `BPMN` | | `uip maestro case …`, or `caseplan.case` / `caseplan.json` | `Case` | | `uip <agent…>`, or `pyproject.toml` with `uipath` / `agent.json` | `Agents` | | `uip codedapp …`, or `app.config.json` / `action-schema.json` | `CodedApps` | | `uip api-workflow …` | `ApiWorkflow` | | `uip df …` | `DataFabric` | | `uip solution …`, or `*.uipx` | `Solution` | | `uip tm …` (Test Manager) | `Test` | | `uip tasks …` | `Tasks` | | `uip admin …` | `Admin` | | `uip gov …` | `Governance` | | anything else (`uip login`, generic Orchestrator / Integration Service / platform) | `Platform` |

If ambiguous, infer from the conversation. Do NOT ask the user -- pick the best match.

**Optional CLI vs Skill marker.** Only when it is *clearly* one or the other, add a second tag so triagers can route the report:

• `CLI` -- a `uip` command crashed, returned wrong output, or lacked a verb/flag.
• `Skill` -- you followed this skill's instructions and they were wrong, misleading, or missing.

Omit it when the cause is mixed or unclear -- don't force a guess.

2b. Capture environment

uip --version 2>&1
uip login status --output json 2>&1
uip tools list 2>&1

From login status, extract only: `tenantName`, `organizationName`, `baseUrl`. Strip everything else.

From tools list, extract tool `name` and `version` from each row.

2c. Capture skill-specific troubleshooting

| Area | What to capture | Limits | |---|---|---| | **Flow** | `uip maestro flow validate <file> --output json`, `.flow` file content, directory listing | `.flow`: first 150 lines; directory: max 30 entries | | **RPA** (`.cs` or `.xaml`) | `project.json` dependencies, `uip rpa validate --output json`, list of workflow files (`.cs` and/or `.xaml`) | File list: max 20 files; `project.json`: dependencies section only; failing workflow: first 150 lines | | **Agents** | `pyproject.toml`, `bindings.json` (redact connection values), directory listing | `bindings.json`: redact all values; directory: max 30 entries | | **CodedApps** | `package.json` (name, version, dependencies only), `.uipath/` listing | `package.json`: name + version + dependencies only | | **Other** (Platform, Solution, Admin, …) | `uip login status --output json` output only | Strip tokens from output |

2d. Capture the failing command

Review the current conversation for the last CLI command that failed. If identifiable, capture:

• The full command
• Its stderr/stdout output (truncated to 100 lines)

If not identifiable, skip this section.

2e. Capture sample prompts

Pick 3-5 user prompts from the conversation that show what the user was trying to do. These give triagers what the retrospective cannot: the user's actual words.

Selection rules:

• Prefer prompts stating intent ("build a flow that…", "I need to…", "help me…") or describing failure ("this is broken", "wrong result").
• Keep wording **verbatim**. Paraphrasing loses signal. Sanitization Rules apply.
• Skip filler ("ok", "thanks", "try again").
• If fewer than 3 substantive prompts exist, include what you have. Do not pad.

-