Repository
CherryHQ/cherry-studio agent skills
- skills
- 30
- GitHub stars
- 52k
GitHub description: “AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs”
- Stars
- 52,431 (5,044 forks)
- Licence
- AGPL-3.0
- Last push
- Oct 2026
- Created
- May 2024
- Homepage
- cherryai.com
- claude-code
- ai-agent
- skills
- codex
- vibe-coding
- deepseek
- hermes-agent
- agent-skills
- open-code-review
Install all skills
npx skills add CherryHQ/cherry-studioAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in CherryHQ/cherry-studio, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 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. | CherryHQ/ | 52k | — | ~4.7k | Automated safety check: Pass | AGPL-3.0 | today |
| 2 | Creates GitHub issues for the current repository by choosing the matching issue template and following its format, with a permission check for engineering tasks. | CherryHQ/ | 52k | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | today |
| 3 | Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream. | CherryHQ/ | 52k | 1 repo | ~504 | Automated safety check: Pass | AGPL-3.0 | today |
| 4 | 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. | CherryHQ/ | 52k | — | ~3.9k | Automated safety check: Pass | AGPL-3.0 | today |
| 5 | Runs Cherry Studio's critical-path regression suite as deterministic Playwright E2E tests through a GitHub workflow on macOS and Windows runners. | CherryHQ/ | 52k | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | today |
| 6 | 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. | CherryHQ/ | 52k | — | ~531 | Automated safety check: Pass | AGPL-3.0 | today |
| 7 | Creates or updates GitHub pull requests by reading the repository's PR template, filling every section and picking the right base branch under its release rules. | CherryHQ/ | 52k | — | ~1.8k | Automated safety check: Pass | AGPL-3.0 | today |
| 8 | Prepares a Cherry Studio release by resolving the version, collecting commits, writing bilingual release notes, updating version files and creating a release branch. | CherryHQ/ | 52k | — | ~4.3k | Automated safety check: Pass | AGPL-3.0 | today |
| 9 | Runs Claude Code non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Claude Code or… | CherryHQ/ | 52k | 1 repo | ~352 | Automated safety check: Pass | AGPL-3.0 | today |
| 10 | Develops, debugs and profiles Cherry Studio in a tracked Electron instance, reusing a verified running instance and capturing before and after evidence for each change. | CherryHQ/ | 52k | — | ~739 | Automated safety check: Pass | AGPL-3.0 | today |
| 11 | Delegates repository analysis or implementation to the Codex CLI in a single non-interactive run, with a read-only sandbox by default. | CherryHQ/ | 52k | 1 repo | ~363 | Automated safety check: Pass | AGPL-3.0 | today |
| 12 | Hands a bounded repository task to the DeepSeek Harness CLI (dsh) in headless mode, then checks the exit code and the diff before reporting back. | CherryHQ/ | 52k | 1 repo | ~359 | Automated safety check: Pass | AGPL-3.0 | today |
| 13 | Runs Gemini CLI once in headless JSON mode for repository analysis or coding work, keeping its approvals read-only unless you ask for changes. | CherryHQ/ | 52k | 1 repo | ~334 | Automated safety check: Pass | AGPL-3.0 | today |
| 14 | Runs GitHub Copilot CLI non-interactively on a repository task and reads its JSONL output, denying tools by default so nothing changes unless you ask. | CherryHQ/ | 52k | 1 repo | ~365 | Automated safety check: Pass | AGPL-3.0 | today |
| 15 | Sends a bounded task to MiniMax Code with mcode exec, passing the smart permission mode for analysis and never the full one. | CherryHQ/ | 52k | 1 repo | ~357 | Automated safety check: Pass | AGPL-3.0 | today |
| 16 | Runs the local OpenClaw main agent once with a JSON message and judges success from the returned payload, not only from the exit code. | CherryHQ/ | 52k | 1 repo | ~373 | Automated safety check: Pass | AGPL-3.0 | today |
| 17 | Runs OpenCode once with opencode run and reads its JSON event stream, leaving its default denial of permission prompts in place for analysis. | CherryHQ/ | 52k | 1 repo | ~343 | Automated safety check: Pass | AGPL-3.0 | today |
| 18 | Runs the Pi agent in sessionless JSON mode and limits it to read-only tools for analysis, since Pi has no approval prompt of its own. | CherryHQ/ | 52k | 1 repo | ~348 | Automated safety check: Pass | AGPL-3.0 | today |
| 19 | Runs the Qoder CN CLI statelessly with JSON output and accepts the result only when the is_error field says the task succeeded. | CherryHQ/ | 52k | 1 repo | ~369 | Automated safety check: Pass | AGPL-3.0 | today |
| 20 | Runs Qwen Code headlessly with JSON output for repository work, using restricted approvals and bounded turn limits, and never the --yolo flag. | CherryHQ/ | 52k | 1 repo | ~346 | Automated safety check: Pass | AGPL-3.0 | today |
| 21 | Runs Hermes Agent once for a bounded local task, with warnings about its automatic tool approval and advice to use a disposable copy for read-only work. | CherryHQ/ | 52k | — | ~390 | Automated safety check: Pass | AGPL-3.0 | today |
| 22 | 搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"，或当前能力不足需要先查找可复用方案的场景。 | CherryHQ/ | 52k | 1 repo | ~263 | Automated safety check: Pass | AGPL-3.0 | today |
| 23 | Answers questions about Cherry Studio's features, routes, shortcuts and providers from the installed build's manifest, and diagnoses runtime problems. | CherryHQ/ | 52k | — | ~494 | Automated safety check: Pass | AGPL-3.0 | today |
| 24 | Operates the visible browser pane of a Cherry Studio Agent session through live browser tools: navigation, snapshots, screenshots, forms and clicks, verifying outcomes. | CherryHQ/ | 52k | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | today |
| 25 | Tests a Cherry Studio pull request by checking it out, inspecting changes, driving the UI in an owned Electron instance and reporting, then restoring the branch. | CherryHQ/ | 52k | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | today |
| 26 | Routes an agent inside Cherry Studio to the right first-party tool or bundled runtime for local scripts, documents, memory, schedules, knowledge bases, MCP servers and more. | CherryHQ/ | 52k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | today |
| 27 | 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. | CherryHQ/ | 52k | — | ~248 | Automated safety check: Pass | AGPL-3.0 | today |
| 28 | Files Cherry Studio bug reports and feature requests as GitHub Issues after a duplicate check and your confirmation, or saves them locally when GitHub is not signed in. | CherryHQ/ | 52k | — | ~335 | Automated safety check: Pass | AGPL-3.0 | today |
| 29 | Searches for, installs and helps create agent skills in Cherry Studio when you ask or when a built-in skill falls short, then returns to the original task. | CherryHQ/ | 52k | — | ~534 | Automated safety check: Pass | AGPL-3.0 | today |
| 30 | 将成功解决的用户问题收录到 FAQ 知识库。问题解决后自动判断是否收录。也可以在用户说"收录到 FAQ"、"记录这个问题"、"add to FAQ"时手动触发。 | CherryHQ/ | 52k | — | ~154 | Automated safety check: Pass | AGPL-3.0 | today |
Questions, answered from the data.
What is the best skill in CherryHQ/cherry-studio?
Office File Transform from CherryHQ/cherry-studio ranks first of the 30 skills in CherryHQ/cherry-studio listed here, with the highest score: its repository has 52k GitHub stars, its SKILL.md loads about 4.7k tokens and it passes the automated safety check with no findings. Next come GitHub Issue Creator and Kimi Code Delegation.
Are the skills in CherryHQ/cherry-studio official?
None yet. All 30 skills in CherryHQ/cherry-studio listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from CherryHQ/cherry-studio?
Run npx skills add CherryHQ/cherry-studio in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.