Dogfood Exploratory QA
vercel-labs/agent-browser
Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue.
Turns a Cherry Studio support chat into a short, editable bug or feedback draft for the user to review, leaving diagnostics and final submission to the user.
SKILL.md written in Chinese; this summary is our English description.
Install Cherry Studio Feedback Draft
$ npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CherryHQ/cherry-studio cherry-studio-feedback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback .claude/skills/cherry-studio-feedback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cherry-studio-feedback" agent skill from https://github.com/CherryHQ/cherry-studio/tree/main/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback into .claude/skills/cherry-studio-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cherry-studio-feedback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/CherryHQ/cherry-studio/tree/main/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CherryHQ/cherry-studio cherry-studio-feedback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .agents/skills && cp -r skills-src/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback .agents/skills/cherry-studio-feedback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cherry-studio-feedback" agent skill from https://github.com/CherryHQ/cherry-studio/tree/main/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback into .agents/skills/cherry-studio-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cherry-studio-feedback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CherryHQ/cherry-studio cherry-studio-feedback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback .cursor/skills/cherry-studio-feedback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cherry-studio-feedback" agent skill from https://github.com/CherryHQ/cherry-studio/tree/main/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback into .cursor/skills/cherry-studio-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cherry-studio-feedback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/CherryHQ/cherry-studio.git --path resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CherryHQ/cherry-studio cherry-studio-feedback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback .gemini/skills/cherry-studio-feedback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cherry-studio-feedback" agent skill from https://github.com/CherryHQ/cherry-studio/tree/main/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback into .gemini/skills/cherry-studio-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cherry-studio-feedback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install CherryHQ/cherry-studio cherry-studio-feedbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .github/skills && cp -r skills-src/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback .github/skills/cherry-studio-feedback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cherry-studio-feedback" agent skill from https://github.com/CherryHQ/cherry-studio/tree/main/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback into .github/skills/cherry-studio-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cherry-studio-feedback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CherryHQ/cherry-studio cherry-studio-feedback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback .opencode/skills/cherry-studio-feedback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cherry-studio-feedback" agent skill from https://github.com/CherryHQ/cherry-studio/tree/main/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback into .opencode/skills/cherry-studio-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cherry-studio-feedback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cherry-studio-feedback- GitHub stars
- 52k
- Token cost
- ~248 tokens
- SKILL.md length
- 52 words
- Files
- 1
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Turns a Cherry Studio support chat into a short, editable bug or feedback draft for the user to review, leaving diagnostics and final submission to the user.
- Works in 5 steps: 复用对话中已知的实际结果、期望结果、复现步骤和影响，整理为一段简洁的问题描述。仅追… → 仅在用户批准且问题确实需要诊断信息时调用… → 仅在 Cherry Studio… → …
- A Cherry Studio user wants to report a bug or UI problem without naming GitHub
- SKILL.md covers 准备草稿, 用户拥有提交权, 禁止事项 and GitHub Issue
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill, written in Chinese for the Cherry Studio assistant, turns the current support conversation about a bug, a UI or UX problem or a feature idea into a short description the user can edit. It reuses what is already known about the actual result, the expected result, the reproduction steps and the impact, and asks a follow-up only when a missing detail would change the description.
When the user approves and diagnostics are really needed, it calls the assistant's diagnose tool, then, only in a live Cherry Studio session, a tool that prepares the draft report and tells the user to click the review button in the message. In channel or headless sessions, or if a tool fails, it does not retry; it points the user to the Submit Diagnostic Report entry under the Help or Settings feedback area to fill in the description by hand.
The user keeps every submission decision: opening the review dialog, choosing which diagnostic data to include, ticking the acknowledgment and submitting. The skill must not run `lark-cli`, build a feedback ZIP, open Feishu or other external forms, submit anything for the user, or claim that a dialog was opened or an upload happened. A request that explicitly names a GitHub Issue is handed to the separate `issue-reporter` skill.
When your agent uses it
- A Cherry Studio user wants to report a bug or UI problem without naming GitHub
- Turning a support conversation into a concise, editable problem description
- Sending a user to the right diagnostic report entry in a headless session
Example prompts
- “The chat window freezes when I paste a long prompt. I want to report this.”
- “Help me write up feedback about the settings page layout being confusing.”
- “I have a feature suggestion for the knowledge base. How do I submit it?”
Requirements
- A live Cherry Studio session, for the draft report tool
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 复用对话中已知的实际结果、期望结果、复现步骤和影响，整理为一段简洁的问题描述。仅追问会实质改变描述的缺失信息。
- 仅在用户批准且问题确实需要诊断信息时调用 mcpassistantdiagnose。用户拒绝、工具失败或不需要诊断时，仍使用现有内容继续准备草稿。
- 仅在 Cherry Studio 内有实时交互用户时，调用完全限定的草稿工具。渠道或其他 headless 会话不得调用，直接执行第 5 步
- 工具成功后，告诉用户点击消息内的“审阅诊断报告”按钮，在共享弹窗中检查并编辑描述。
- 渠道/headless 会话、工具不可用或失败时，不得循环重试模型或工具。让用户从 Cherry Studio 的帮助或设置打开“问题反馈”入口中的“提交诊断报告”，并手动填写问题描述。
What it can do on your machine
Read from SKILL.md and the folder at commit dd0767e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cherry Studio Feedback Draft loads about 248 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 52 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from CherryHQ/cherry-studio at commit dd0767e, republished under its AGPL-3.0 licence (© CherryHQ). 52 words, ~248 tokens.
Download SKILL.mdSave it as
.claude/skills/cherry-studio-feedback/SKILL.md (or your agent's skills folder).- name
- cherry-studio-feedback
- description
- Use when Cherry Studio 用户希望报告、提交或整理 BUG、UI/UX 问题或功能建议，但未明确要求创建 GitHub Issue。
Cherry Studio Feedback
将当前 Support 对话整理成简洁、用户可编辑的问题描述，再把草稿交给用户审阅。Support 只准备草稿；诊断选择、知晓确认和最终提交都由用户完成。
准备草稿
复用对话中已知的实际结果、期望结果、复现步骤和影响，整理为一段简洁的问题描述。仅追问会实质改变描述的缺失信息。
仅在用户批准且问题确实需要诊断信息时调用
mcp__assistant__diagnose。用户拒绝、工具失败或不需要诊断时，仍使用现有内容继续准备草稿。仅在 Cherry Studio 内有实时交互用户时，调用完全限定的草稿工具。渠道或其他 headless 会话不得调用，直接执行第 5 步：
text mcp__assistant__prepare_diagnostic_report({ description })工具成功后，告诉用户点击消息内的“审阅诊断报告”按钮，在共享弹窗中检查并编辑描述。
渠道/headless 会话、工具不可用或失败时，不得循环重试模型或工具。让用户从 Cherry Studio 的帮助或设置打开“问题反馈”入口中的“提交诊断报告”，并手动填写问题描述。
用户拥有提交权
prepare_diagnostic_report 只持久化并返回草稿结果：不会打开弹窗、勾选知晓确认或上传。必须由用户亲自：
- 点击“审阅诊断报告”。
- 选择要包含的诊断数据。
- 勾选知晓确认。
- 审阅后提交。
禁止事项
- 不得调用
lark-cli。 - 不得生成工作区反馈 ZIP。
- 不得直接打开飞书或其他外部表单。
- 不得代替用户勾选、上传或完成任何提交。
- 不得声称已打开弹窗、已上传或已提交。
GitHub Issue
用户明确要求创建 GitHub Issue 时，立即转交 issue-reporter，不再执行本流程。
© CherryHQ, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback of CherryHQ/cherry-studio.
Open the folder on GitHubat commit dd0767e
Compare with similar skills
Cherry Studio Feedback Draft next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cherry Studio Feedback Draft this skillCherryHQ/cherry-studio | 52k | — | ~248 | Automated safety check: Pass | AGPL-3.0 | |
| Dogfood Exploratory QAvercel-labs/agent-browser | 44k | 8 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| DeerFlow Smoke Testbytedance/deer-flow | 83k | — | ~2.5k | Automated safety check: Notes | MIT | |
| CodexBar Live QAsteipete/CodexBar | 22k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Diagnose Playwright Failure as Product Bugappsmithorg/appsmith | 41k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Acceptance Evidence for Deliverieslobehub/lobehub | 83k | — | ~9.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
DeerFlow Smoke Test
bytedance/deer-flow
Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.
CodexBar Live QA
steipete/CodexBar
Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.
Diagnose Playwright Failure as Product Bug
appsmithorg/appsmith
Investigates a stubbornly failing Playwright test as a possible product bug, using error output, screenshots, traces and server code, and writes a structured bug report.
Acceptance Evidence for Deliveries
lobehub/lobehub
Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.
Codex Plugin QA
code-yeongyu/oh-my-openagent
Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.
More from CherryHQ/cherry-studio
All 30 skills in this repoOffice File Transform
CherryHQ/cherry-studio
Derives new files from a selected part of a spreadsheet, Word document, PDF or slide deck, such as a cell range, paragraph, page or slide, without ever modifying the source file.
GitHub Issue Creator
CherryHQ/cherry-studio
Creates GitHub issues for the current repository by choosing the matching issue template and following its format, with a permission check for engineering tasks.
Cherry Studio PR Review
CherryHQ/cherry-studio
Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.
Cherry Studio Regression Tests
CherryHQ/cherry-studio
Runs Cherry Studio's critical-path regression suite as deterministic Playwright E2E tests through a GitHub workflow on macOS and Windows runners.
Antigravity CLI Runner
CherryHQ/cherry-studio
Runs the Antigravity CLI headlessly with the agy command to analyze a repository or carry out a coding task, then checks its JSON result and the diff.
Kimi Code Delegation
CherryHQ/cherry-studio
Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.
Related
Categories
Questions about Cherry Studio Feedback Draft
What does Cherry Studio Feedback Draft do?
Turns a Cherry Studio support chat into a short, editable bug or feedback draft for the user to review, leaving diagnostics and final submission to the user. This skill, written in Chinese for the Cherry Studio assistant, turns the current support conversation about a bug, a UI or UX problem or a feature idea into a short description the user can edit. It reuses what is already known about the actual result, the expected result, the reproduction steps and the impact, and asks a follow-up only when a missing detail would change the description.
When should I use Cherry Studio Feedback Draft?
Cherry Studio Feedback Draft fits situations like: A Cherry Studio user wants to report a bug or UI problem without naming GitHub; turning a support conversation into a concise, editable problem description; sending a user to the right diagnostic report entry in a headless session.
How do I install Cherry Studio Feedback Draft in Claude Code?
Run `npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a claude-code`. Or copy the skill folder (resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback in CherryHQ/cherry-studio) into .claude/skills/cherry-studio-feedback in your project. Claude Code loads it when a task matches its description.
How do I install Cherry Studio Feedback Draft in Codex?
Run `npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a codex`. Or copy the skill folder (resources/builtin-agents/cherry-assistant/.claude/skills/cherry-studio-feedback in CherryHQ/cherry-studio) into .agents/skills/cherry-studio-feedback in your project. Codex loads it when a task matches its description.
Can I use Cherry Studio Feedback Draft in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CherryHQ/cherry-studio --skill cherry-studio-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cherry-studio-feedback, .gemini/skills/cherry-studio-feedback, .github/skills/cherry-studio-feedback and .opencode/skills/cherry-studio-feedback in your project.
What does Cherry Studio Feedback Draft need to run?
SKILL.md names no scripts, command-line tools or credentials: Cherry Studio Feedback Draft is instructions for the agent only. Our summary lists: A live Cherry Studio session, for the draft report tool.
Does Cherry Studio Feedback Draft access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Cherry Studio Feedback Draft safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Cherry Studio Feedback Draft use?
Cherry Studio Feedback Draft is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cherry Studio Feedback Draft use?
About 248 tokens (SKILL.md is roughly 992 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Cherry Studio Feedback Draft?
Skills that share tags, products or a category with Cherry Studio Feedback Draft: Dogfood Exploratory QA (vercel-labs/agent-browser, 44k stars), DeerFlow Smoke Test (bytedance/deer-flow, 83k stars), CodexBar Live QA (steipete/CodexBar, 22k stars) and Diagnose Playwright Failure as Product Bug (appsmithorg/appsmith, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cherry Studio Feedback Draft?
CherryHQ (a GitHub organization) maintains it in CherryHQ/cherry-studio, which has 52,407 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 7, 2026.
Source: CherryHQ/cherry-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.