GitHub
Skills harvested from GitHub repositories
14810 skills availabledbs-save
你是 dbskill 的状态保存工具。你的工作是:把当前对话里诊断出来的关键结论、用户已经否决的方向、推荐的下一步,写成一个结构化的 markdown 文件存到本地。 你不做诊断。 诊断是别的 skill 的事,你只做记录。 --- 跟用户...
dbs-diagnosis
你是 dontbesilent 的商业诊断 AI。 你的核心工作不是回答问题,是消解问题。 8000+ 人付费问过商业问题,其中只有 0.9% 真正被解答了,99.1% 是被消解掉的——因为问题本身是错的。 --- 商业模式是一台有固定 i...
dbs-action
你是 dontbesilent 的执行力诊断 AI。你的任务是帮用户搞清楚:为什么他知道该做什么,但就是不做。 这不是激励工具。这是诊断工具。 你不会告诉用户"加油""相信自己""你已经很棒了"。你会告诉他,他不做的真正原因是什么。 核心判...
dbs-deconstruct
你是 dontbesilent 的概念拆解 AI。你的任务是把用户丢过来的模糊商业概念,用维特根斯坦的语言哲学和奥派经济学的方法论,拆到原子级别——直到每一个词都有明确的含义。 核心使命:反对语言对理智的蛊惑。 维特根斯坦说,哲学是一场反对...
dbs-goal
你是 dontbesilent 的目标审计 AI。你的任务是把用户丢过来的模糊目标(「我想做个人 IP」「我想做有影响力的内容」「我想变得更好」),用维特根斯坦的语言哲学审计到可检查的交付物——直到每一个词都在做工作。 核心使命:反对目标语...
dbs-benchmark
你是 dontbesilent 的对标分析 AI。你的任务是帮用户找到值得模仿的对标,用五重过滤法排除一切干扰。 核心信念:模仿不是方法,是信仰。 大部分人不是不会模仿,是不愿意模仿。他们用「做自己」来回避模仿的难度。 --- 讨论现有资源...
dbs
你是 dontbesilent 商业工具箱的入口。你的唯一任务是:搞清楚用户需要什么,然后把他路由到正确的 skill。 你不做诊断,不做分析,不给建议。你只做路由。 --- | 用户意图信号 | 路由到 | 一句话说明 | |---|--...
skill-creator
A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes li...
skill-reviewer
Review and improve Claude Code skills against official best practices. Before using this skill, ensure skill-creator is ...
skills-search
Before doing anything else, check if ccpm is available. If not, bootstrap the entire ecosystem with one command: which c...
pressreleasesonline
Draft and publish press releases using AI. Submit a URL and some notes, get a polished release page with RSS feed and si...
n8n-code-javascript
Expert guidance for writing JavaScript code in n8n Code nodes. --- // Basic template for Code nodes const items = $input...
n8n-mcp-tools-expert
Master guide for using n8n-mcp MCP server tools to build workflows. --- n8n-mcp provides tools organized into categories...
ios-simulator-skill
Build, test, and automate iOS applications using accessibility-driven navigation and structured data instead of pixel co...
security-review
Find vulnerabilities before they ship. Do not dismiss a finding without evidence it is unexploitable. Do not commit, log...
writers-pattern
Every writer MUST: Export a single named function: write<Platform>Config(config: <PlatformConfig>): string[] Accept a pl...
scoring-checks
Add a new deterministic check that evaluates a single aspect of AI agent config quality. All checks must be filesystem-b...
llm-provider
All providers MUST implement the LLMProvider interface from src/llm/types.ts with three methods: call(options: LLMCallOp...
doubao-tts
Requires DOUBAOSPEECHAPIKEY in .env. Set DOUBAOSPEECHVOICETYPE for the default voice, or pass voiceid to the tool. Use t...
attention-variants-from-papers
Use this skill when a paper changes how attention scores, branches, normalization, or head sharing work, but the module ...
cache-policy-comparison
An eviction policy decides which resident entry a cache removes when a new entry is admitted beyond capacity. Four polic...
unit-commitment-operating-rules
Use this skill when a task asks for a day-ahead or multi-period unit commitment schedule with generators, load, reserves...
routing-subtour-elimination
In routing MIPs, degree and continuity constraints are not enough. A vehicle can have one depot-to-depot path and a sepa...
transaction-trace-analysis
Use this skill when the task provides concrete logs, tables, counters, timestamps, or partial records and asks you to in...