clay-run/agent-plugins/clay-feedback
Claude Code and agent skill by clay-run/agent-plugins
- community
Checking that the SKILL.md file is still in the repository.
Clay feedback — send a bug report or product feedback to the Clay team via the `clay feedback` CLI.
Install
npx vskill@latest install clay-run/agent-plugins/clay-feedbackSKILL.md
Clay Feedback
Send feedback or a bug report to the Clay team using clay feedback. It reads the message from stdin and automatically attaches environment details.
The CLI does no confirmation of its own, so confirm with the user before sending.
Feedback is one-way: it lands in the Clay team's triage queue and nobody replies. When the user wants a human who responds — they explicitly ask for support, or the matter needs staff action (a disputed or duplicate charge, a refund, account recovery) — use clay support instead (see the clay skill's "Getting help and reporting problems"). Product feedback _about_ billing or plans (confusing UX, a feature request) is still feedback and belongs here.
Steps
- Determine type. The test is: did Clay fail, or behave differently from how it is documented or built to work? First occurrences count, and you do not need to know whether it worked before.
- Choose
bugfor: errors, crashes, timeouts or hangs; failures on valid input; wrong, empty, stale or duplicated output; output that contradicts the docs or--help; data lost or changed unexpectedly; documented features that do not work. - Choose
feedbackonly when Clay worked as designed and the user wants something different: feature requests, capabilities Clay does not claim to have, UX or naming suggestions, working-but-confusing flows, general ideas. - Tiebreaker: if the user saw an error or unexpected result while doing something Clay supports, use
bug; if it is still ambiguous, usebugwithout asking.
- Get feedback text. Use the argument if provided (e.g.
/clay-feedback would love CSV export from the enrichment table). Otherwise ask the user what feedback or bug report they'd like to send. For a bug, include the command that was run, the error output, and expected versus actual behavior in the message.
- Confirm. Use your ask-user tool (
AskUserQuestion;askUserinside the Clay app). List what the report will include, and offer "Send" / "Cancel":
> This report will include: > > - Type: {bug or feedback} > - Your feedback: {feedback text} > - Environment info (auto-collected) > > Send this feedback?
- If confirmed, send the message on stdin. The CLI reads the feedback from stdin. Do not pass it inline in the shell command (no heredoc, no
echo): the feedback is arbitrary user text, and a here-doc delimiter or quote appearing in it would truncate or mis-parse the message — or let pasted text run as shell. Instead, write the text to a temp file with your file-writing tool (which never goes through the shell), then redirect that file into the command. Always pass--type bugor--type feedbackfrom step 1.
- Write the feedback text verbatim to a temp file with an unpredictable name (a shared
fixed path lets other local sessions read or clobber it), e.g. /tmp/clay-feedback-<random>.txt.
- Then run:
``bash clay feedback --type <bug|feedback> < /tmp/clay-feedback-<random>.txt rm -f /tmp/clay-feedback-<random>.txt ``
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingclay/skills/clay-feedback/SKILL.md
Popularity
- Repository stars
- 141
- Repository forks
- 22
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/clay-run/agent-plugins/clay-feedback)