Skip to content
Agentmart
Submit a tool

rqmd-feedback

Send user-driven improvement feedback about rqmd via the telemetry service.

Skill by ryeleo

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ryeleo-rqmd-feedback

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Send user-driven improvement feedback about rqmd via the telemetry service. Use to report friction, missing features, docs gaps, or workflow confusion to the rqmd developer with full telemetry context.

Use cases: documents, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/rqmd-feedback

What's inside

Skill name
rqmd-feedback
Description
Send user-driven improvement feedback about rqmd via the telemetry service. Use to report friction, missing features, docs gaps, or workflow confusion to the rqmd developer with full telemetry context.
License
MIT
Instructions
71 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Run structured user-driven feedback sessions for improving rqmd.

> **⚠️ Note:** This skill reports issues with **rqmd itself**. For your own project bugs, use `/bug` instead.

## When to use

Invoke when user explicitly asks to give feedback — not for autonomous agent friction (use `rqmd-telemetry` for that).

## Event type

All feedback uses `event_type="feedback"`, separating user-driven input from agent reports (`struggle`, `suggestion`, `error`).

## Payload schema

```json
{
  "session_id": "<uuid>",
  "event_type": "feedback",
  "severity": "low | medium | high | critical",
  "summary": "Concise one-line description",
  "detail": {
    "phase": "session_start | in_progress | session_close",
    "category": "ux_friction | missing_feature | docs_gap | workflow_confusion | performance | other",
    "description": "Plain-language description",
    "suggested_improvement": "What should change",
    "github_issue_url": "<optional>",
    "issue_skipped_reason": "<optional>"
  }
}
```

| Category | When to use |
|---|---|
| `ux_friction` | Workflow awkward or requires more effort than expected |
| `missing_feature` | Absent command, flag, or workflow |
| `docs_gap` | Documentation missing or out of sync |
| `workflow_confusion` | Guidance led in wrong direction |
| `performance` | Command noticeably slow |
| `doc_style_violation` | Agent produced prose that violated the sentence-per-line convention (hard-wrapping); always set `detail.violation="hard_wrap"` and `detail.model_id=<model identifier>` |
| `other` | Does not fit above |

| Severity | Meaning |
|---|---|
| `low` | Annoying but not blocking |
| `medium` | Regularly adds friction |
| `high` | Degrades core workflow |
| `critical` | Makes rqmd unusable |

## Submission workflow

1. **Session start:** Submit `session_start` event before asking anything
2. **Iterative refinement:** Submit `in_progress` events as payload evolves
3. **GitHub issue:** Offer `gh issue create --repo ryeleo/rqmd` for concrete bugs; set `issue_skipped_reason` if skipped
4. **Session close:** Submit final polished event with `phase: session_close`

```python
from rqmd.telemetry import send_event

send_event(
    event_type="feedback",
    severity="medium",
    summary="Description",
    session_id=session_id,  # reuse uuid across session

    detail={"phase": "in_progress", "category": "ux_friction", ...},
)
```

See `rqmd-telemetry` for endpoint resolution, authentication, and full field reference.

From ryeleo/rqmd-vscode, MIT.

More from ryeleo/rqmd-vscode

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 7, 2026 (5 months ago)
Last release
May 27, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ryeleo

Cite this page

rqmd-feedback skill. Agent Mart. https://agentmart.dev/skills/ryeleo-rqmd-feedback (last updated 2026-10-24)