LLM Mart Basic

Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.

Use when reviewing a PR, API, IPC channel, endpoint, parameter, type, config, or architectural extension point that adds or expands shared surface area, especially when consumers are absent, exports are unused or speculative, existing consumers are hack-heavy, forward compatibili

Use when user wants to create a GitHub issue for the current repository. Must read and follow the repository's issue template format.

Create or update GitHub pull requests using the repository-required workflow and template compliance. Use when asked to create/open/update a PR so the assistant reads `.github/pull_request_template.md`, fills every template section, preserves markdown structure exactly, and marks

Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle

Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch with PR. Use when asked to prepare/create a release, bump version, or run `/prepare-release`.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching,

Cherry Studio first-party tool and bundled-shell routing for general agents. For straightforward local work in shell-capable sessions, run JS/TS with `bun <file>` and one-off JS tools with `bun x`; run Python with `uv run [--with <pkg>] python` and one-off Python CLIs with `uvx`;

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist a

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's desc

从当前安装包查询 Cherry Studio 产品信息并排查运行问题。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI、当前版本，或报告运行错误、连接失败、配置异常并需要诊断时触发。

当用户明确要求搜索、安装、查看、卸载或创建 Skill，或内置 Skill / 工具出现能力缺口、无法完成当前任务时触发。通过 `mcp__skills__search_skills` 搜索并用 `mcp__skills__install_skill` 安装；已安装 Skill 的查看和删除通过产品清单导航到 Skills UI；没有合适结果时调用内置 `skill-creator` 创建并验证自定义 Skill，再继续原任务。普通任务仍先尝试内置能力。

收集、脱敏、预览并提交 Cherry Studio BUG、UI/UX 或功能反馈，默认提交到飞书。可在用户同意后调用内置诊断工具整理环境、错误日志、截图和用户导出的 trace，自动提交飞书表单或生成匿名上传 ZIP；也可安全解析反馈 ZIP 为表单字段。用户说“提交问题”“提交反馈”“上报 bug”“收集/上传错误信息”“整理日志/trace”“生成反馈包”，或描述 Cherry Studio 问题并希望记录时触发。只有明确要求 GitHub Issue 时才改用 issue-reporter。

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code

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。

只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。

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。

Imported from cherryhq/cherry-studio/resources/skills/skill-creator/agents/analyzer.md.

Imported from cherryhq/cherry-studio/resources/skills/skill-creator/agents/comparator.md.

Imported from cherryhq/cherry-studio/resources/skills/skill-creator/agents/grader.md.

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]

Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt *.target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome]

On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com

Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Pick up a previous hunt on a target — shows hunt history and untested surface from the autopilot ledger. Usage: /pickup target.com

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/<target>/ directory. Usage: /recon target.com

Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember

Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report

Mandatory pre-flight scope check — verify an asset is in scope BEFORE any HTTP touch. Deterministic (deny-wins, default-deny) via engine/scope.py against the engagement's scope.md. Blocks out-of-scope testing. Usage: /scope <asset> [<asset> ...]

Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan <contract_path_or_dir> [--chain solana]

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

Crabbox is a single CLI (`crabbox`). Commands are top-level, not nested under a

`crabbox actions` prepares a leased box from your repository's own GitHub

See [Runtime adapter stack](../features/runtime-adapter-stack.md) for the

`crabbox admin` groups trusted operator controls for coordinator-backed leases and the cloud resources behind them. Use it to inspect every lease the broker tracks, reconcile expired leases against live cloud state, force-release or delete a backing server, print provider IAM pol

`crabbox artifacts` turns a desktop lease into durable QA evidence: it collects

A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL.｜从…

Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

Maintainer-governed agent for evidence-backed open-source contribution proposals

A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day content calendar. Mega-viral validated: 8…

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

Open-source AI Agent platform for teams. Your agents don't just chat — they read files, run code, call APIs, and deliver results.

Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Cl…

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

Tinybot is a lightweight personal AI Agent that is constantly evolving

Goink 桌面 AI 小说创作助手，对话式写作 + 自动状态追踪 + 本地语义搜索。跨平台开箱即用。AI Agent Novel Generator.

Pluggable DeepSeek-colored TUI for DeepSeek Harness

Entity-level git merge driver. Resolves false conflicts git invents when independent agents edit the same file. ~95% reduction vs. line-based merge.

Percho: Minimalist desktop GUI for the Pi coding agent — the same engine as the Pi CLI, in a clean visual interface. Multi-session chat, visual tool approvals,…

Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoption, approval gates, reboot-surviving sessions

A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.

Real-time multimodal desktop agent evolving toward a persistent AI OS interface (0.1 α).

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when need…

Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cro…