How do I install the Feedback skill?

Run npx skillmds add tinyfish-io/feedback in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Feedback safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Feedback?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Feedback free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Feedback?

tinyfish-io (@tinyfish-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Feedback by tinyfish-io — Agent Skill

Name: Feedback
Rating: 4.666666666666667 (3 reviews)
Author: tinyfish-io

Feedback

File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report. Creates a GitHub issue on tinyfish-io/tinyfish-cookbook with the user's approval; nothing is sent without an explicit preview.

tinyfish-io 6cbe607 2.4 KB Updated Sep 9, 2026

File contents

TinyFish Feedback

Collect the user's feedback, structure it, preview it, then file it. Nothing leaves the machine without the user seeing the exact text first.

Collect

Ask (briefly) for: what they were trying to do, what happened instead, and what they expected. For anything setup-, auth-, or connectivity-shaped, run npx -y @tiny-fish/cli@latest doctor and offer to attach its stdout JSON verbatim — it is schema-versioned and already redaction-safe (undeclared fields stripped on parse, messages authored rather than raw). Do not add fields, summarise it, or paste config contents alongside it. On exit 2 doctor produced no JSON — say so instead of attaching an empty report.

Structure

### What I was doing
…
### What happened
…
### Expected
…
### Environment
harness + version, CLI version (if known)
### Doctor report (optional)
`tinyfish doctor` stdout, verbatim

Preview gate

Show the complete issue body to the user and ask for an explicit yes before filing. Any edit they request happens before filing.

File

Preferred: write the body and the title to files, then gh issue create --repo tinyfish-io/tinyfish-cookbook --title "$(cat "$title_file")" --body-file "$body_file" (only if gh is installed and authenticated). Both values come from the user's free-form text (the body also carries doctor's JSON), so neither may reach the shell as literal text — including in a title=… assignment, where backticks or $(…) are evaluated just the same. cat's output is not re-parsed. Never build the command as a string or run it through eval.
Fallback: open a prefilled issue URL (https://github.com/tinyfish-io/tinyfish-cookbook/issues/new?title=…&body=…). Percent-encode both values — an unencoded # truncates the body and & splits it into junk parameters. URL length limits truncate long bodies anyway — if the body was truncated, tell the user and show the full text so they can paste the remainder.

This repo is public — remind the user of that in the preview if the report contains anything they typed free-form.

---name: feedbackdescription: File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report. Creates a GitHub issue on tinyfish-io/tinyfish-cookbook with the user's approval; nothing is sent without an explicit preview.--- # TinyFish Feedback Collect the user's feedback, structure it, preview it, then file it. Nothing leaves the machine without the user seeing the exact text first. ## Collect Ask (briefly) for: what they were trying to do, what happened instead, and what they expected. For anything setup-, auth-, or connectivity-shaped, run `npx -y @tiny-fish/cli@latest doctor` and offer to attach its stdout JSON verbatim — it is schema-versioned and already redaction-safe (undeclared fields stripped on parse, messages authored rather than raw). Do not add fields, summarise it, or paste config contents alongside it. On exit `2` doctor produced no JSON — say so instead of attaching an empty report. ## Structure ```markdown ### What I was doing … ### What happened … ### Expected … ### Environment harness + version, CLI version (if known) ### Doctor report (optional) `tinyfish doctor` stdout, verbatim ``` ## Preview gate Show the complete issue body to the user and ask for an explicit yes before filing. Any edit they request happens before filing. ## File - Preferred: write the body and the title to files, then `gh issue create --repo tinyfish-io/tinyfish-cookbook --title "$(cat "$title_file")" --body-file "$body_file"` (only if `gh` is installed and authenticated). Both values come from the user's free-form text (the body also carries doctor's JSON), so neither may reach the shell as literal text — including in a `title=…` assignment, where backticks or `$(…)` are evaluated just the same. `cat`'s output is not re-parsed. Never build the command as a string or run it through `eval`. - Fallback: open a prefilled issue URL (`https://github.com/tinyfish-io/tinyfish-cookbook/issues/new?title=…&body=…`). Percent-encode both values — an unencoded `#` truncates the body and `&` splits it into junk parameters. URL length limits truncate long bodies anyway — if the body was truncated, tell the user and show the full text so they can paste the remainder. This repo is public — remind the user of that in the preview if the report contains anything they typed free-form.

Frequently asked questions