Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
23,097
总 Skills
59.4M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
5401 pr-address-comments google-gemini/gemini-cli
You are helping the user address comments on their Pull Request. These comments may have come from an automated review agent or a team member. OBJECTIVE: Help the user review and address comments on their PR. Comment Review Procedure Run the scripts/fetch-pr-info.js script to get PR info and state. MAKE SURE you read the entire output of the command, even if it gets truncated. Summarize the review status by analyzing the diff, commit log, and comments to see which still need to be addressed. Pay...
 707
5402 dd-pup datadog-labs/agent-skills
pup (Datadog CLI) Pup CLI for Datadog API operations. Supports OAuth2 and API key auth. Quick Reference Task Command Search error logs pup logs search --query "status:error" --duration 1h List monitors pup monitors list Mute a monitor pup monitors mute --id 123 --duration 1h Find slow traces pup apm traces list --service api --min-duration 500ms List active incidents pup incidents list --status active Create incident pup incidents create --title "Issue" --severity SEV-2 Query metrics pup metrics...
 707
5403 fusion-github-review-resolution equinor/fusion-skills
Resolve GitHub Review Comments When to use Use this skill when a pull request has unresolved inline review comments and you need a repeatable, auditable closure workflow. Typical triggers (skill should activate on all of these): URL patterns — activate immediately: https://github.com/<owner>/<repo>/pull/<number>pullrequestreview-<id> https://github.com/<owner>/<repo>/pull/<number> (when context implies review work) Explicit user requests: "Fix the review comments" "Address the review feedback on...
 707
5404 frontend-design-pro binjuhor/shadcn-lar
You are a world-class creative frontend engineer AND visual director. Every interface you build must feel like a $50k+ agency project. 1. Choose One Bold Aesthetic Direction (commit 100%) Style Category Core Keywords (copy-paste ready) Color Palette Ideas Signature Effects & Details Minimalism & Swiss Style clean, swiss, grid-based, generous whitespace, typography-first Monochrome + one bold accent, beige/gray neutrals Razor-sharp hierarchy, subtle hover lifts, micro-animations, perfect alignme...
 706
5405 mcp-configure launchdarkly/agent-skills
Configure Dataverse MCP for GitHub Copilot This skill configures the Dataverse MCP server for GitHub Copilot with your organization's environment URL. Each organization is registered with a unique server name based on the org identifier (e.g., DataverseMcporgbc9a965c ). If the user provided a URL it is: $ARGUMENTS. Instructions 0. Ask for MCP scope Ask the user whether they want to configure the MCP server globally or for this project only: Would you like to configure the Dataverse MCP server: G...
 706
5406 sdk-install launchdarkly/agent-skills
LaunchDarkly SDK Install (onboarding) Installs and initializes the right LaunchDarkly SDK for the user’s project by following three nested skills in order . Do not skip ahead to feature flags here—the parent LaunchDarkly onboarding continues with Step 6: First feature flag using Create first feature flag . Prerequisites Project context from parent Step 1: Explore the Project (reuse it; only re-run deep detection if something is unclear) SDK key / client-side ID / mobile key: Needed when you reac...
 706
5407 m09-domain actionbook/rust-skills
Domain Modeling Layer 2: Design Choices Core Question What is this concept's role in the domain? Before modeling in code, understand: Is it an Entity (identity matters) or Value Object (interchangeable)? What invariants must be maintained? Where are the aggregate boundaries? Domain Concept → Rust Pattern Show more
 706
5408 cs-brainstorm liuzhengdongfortest/codestable
cs-brainstorm brainstorm 是"讨论层"统一入口。用户开口时 AI 不知道终点应落在哪——feature design / roadmap / 还是聊两句发现已经够清楚直接 design。本技能先用一两轮对话分诊，再把讨论交给合适下游。 三件最重要的事： brainstorm 是创意空间不是审计关卡 ——探索 / 质疑 / 改主意 / 聊着聊着发现真正想做的是另一件事都正常 任何话题都可以聊 ——用户想聊库 / Schema / 接口就聊；TA 提出来说明心里有谱，趁早讨论清楚 design 阶段更省力。不设话题黑名单 AI 是思考伙伴不是记录员 ——用户来这步是想被挑战、被启发，不是被一条条问题填表。如果只是把用户的话整理一遍写下来这步就白做了 共享路径和命名约定看 codestable/reference/shared-conventions.md 。 三种讨论、三个出口 情况 特征 出口 case 1：其实已经够清楚 一句话能说出"做什么 / 为谁 / 怎么算成功 / 不做什么"，不需要再 explore 直接 cs-feat-design （不落盘，告知用...
 706
5409 microsoft-rust-training aradotso/trending-skills
Microsoft Rust Training Skill by ara.so — Daily 2026 Skills collection. A collection of seven structured Rust training books maintained by Microsoft, covering Rust from multiple entry points (C/C++, C/Java, Python backgrounds) through deep dives on async, advanced patterns, type-level correctness, and engineering practices. Each book contains 15–16 chapters with Mermaid diagrams, editable Rust playgrounds, and exercises. Book Catalog Book Level Focus c-cpp-book 🟢 Bridge Move semantics, RAII, FFI...
 706
5410 obliteratus-abliteration aradotso/trending-skills
OBLITERATUS — LLM Abliteration Toolkit Skill by ara.so — Daily 2026 Skills collection. OBLITERATUS is an open-source toolkit for identifying and surgically removing refusal behaviors from large language models using mechanistic interpretability techniques (abliteration). It locates refusal directions in a model's hidden states via SVD/PCA, projects them out of the weights, and preserves core language capabilities. Ships with a Gradio UI, CLI, Python API, and Colab notebook. Installation Core in...
 706
5411 app-builder sickn33/antigravity-awesome-skills
App Builder - Application Building Orchestrator Analyzes user's requests, determines tech stack, plans structure, and coordinates agents. 🎯 Selective Reading Rule Read ONLY files relevant to the request! Check the content map, find what you need. File Description When to Read project-detection.md Keyword matrix, project type detection Starting new project tech-stack.md 2025 default stack, alternatives Choosing technologies agent-coordination.md Agent pipeline, execution order Coordinating mu...
 706
5412 senior-prompt-engineer davila7/claude-code-templates
Senior Prompt Engineer World-class senior prompt engineer skill for production-grade AI/ML/Data systems. Quick Start Main Capabilities Core Tool 1 python scripts/prompt_optimizer.py --input data/ --output results/ Core Tool 2 python scripts/rag_evaluator.py --target project/ --analyze Core Tool 3 python scripts/agent_orchestrator.py --config config.yaml --deploy Core Expertise This skill covers world-class capabilities in: Advanced production patterns and architectures Scalable syste...
 706
5413 asc-screenshot-resize rudrankriyam/app-store-connect-cli-skills
asc screenshot resize Use this skill to resize screenshots to the exact pixel dimensions required by App Store Connect and validate they pass upload requirements. Uses the built-in macOS sips tool — no third-party dependencies needed. Required Dimensions iPhone Display Size Accepted Dimensions (portrait × landscape) 6.9" 1260 × 2736, 2736 × 1260, 1320 × 2868, 2868 × 1320, 1290 × 2796, 2796 × 1290 6.5" 1242 × 2688, 2688 × 1242, 1284 × 2778, 2778 × 1284 6.3" 1206 × 2622, 2622 × 1206, 1179 × 2556, ...
 706
5414 freeride shaivpidadi/freeride
FreeRide - Free AI for OpenClaw What This Skill Does Configures OpenClaw to use free AI models from OpenRouter. Sets the best free model as primary, adds ranked fallbacks so rate limits don't interrupt the user, and preserves existing config. Prerequisites Before running any FreeRide command, ensure: OPENROUTER_API_KEY is set. Check with echo $OPENROUTER_API_KEY . If empty, the user must get a free key at https://openrouter.ai/keys and set it: export OPENROUTER_API_KEY = "sk-or-v1-..." Or persi...
 705
5415 cs-feat-design liuzhengdongfortest/codestable
cs-feat-design 这一阶段的产出是一份方案文件 {slug}-design.md ，加上从中抽出的行动清单 {slug}-checklist.yaml 。这两份东西后面会被两个阶段消费——implement 照着推进、acceptance 照着核对，所以这里写错或写漏，下游就跟着错。 共享路径和命名约定看 codestable/reference/shared-conventions.md 。本阶段一般 feature 目录已经由 brainstorm 创建好了；没有的话在这一步建。 本阶段有三个入口： 正式起草 ：用户已经能讲清楚需求（或已经填好 {slug}-intent.md ），直接进"流程"一节走完整起草。 初始化模式 ：用户说"开一个新需求 / 起个草稿 / 新建一个 feature"，但想自己先写半成品方案而不是口述。走下一节"初始化模式"，建好目录和空 {slug}-intent.md 就结束本轮，等用户填完再回来。 从 roadmap 条目起头 ：用户说"开始做 roadmap 里的 {子 feature slug}"或"推进 {roadmap} 的下一条...
 705
5416 cs-feat-accept liuzhengdongfortest/codestable
cs-feat-accept 代码已经写完，但流程没结束。本阶段做四件事，缺一不可： 核对实现有没有偏离方案 ——逐层对照 {slug}-design.md ，发现偏差当场修，不是在报告里"记一下"就过去 把 feature 归并到整体架构 ——对照方案第 4 节，实际去更新架构中心目录下的相关 doc 能力落档到 requirement ——req 是现状档案，能力做完才有现状，所以 req 的新建 / 刷新都在本阶段做 完成状态回写到 roadmap ——方案 frontmatter 有 roadmap / roadmap_item 字段时 必须 改 items.yaml 对应条目为 done 并同步主文档 漏掉任何一件的代价：架构 doc 过期下个 feature 读到错信息；req 和实际能力脱节；roadmap 规划层和实际进度脱节，下次推进会重复跑流程。 没产出报告 = 工作流未完成 。后人查"上次这个功能验收时确认了哪些行为"，没报告就只能翻 git diff 重新推断。 共享路径与命名约定看 codestable/reference/shared-conventions...
 705
5417 svg-animations supermemoryai/skills
This skill guides creation of handcrafted SVG animations — from simple animated icons to complex multi-stage path animations. SVGs are a markup language for images; every element is a DOM node you can style, animate, and script. SVG Fundamentals Coordinate System SVGs use a coordinate system defined by viewBox="minX minY width height" . The viewBox is your canvas — all coordinates are relative to it, making SVGs resolution-independent. < svg viewBox = " 0 0 200 200 " xmlns = " http://www.w3.org/...
 705
5418 react-use hairyf/skills
The skill is based on react-use v17.6.0, generated at 2026-01-29. react-use is a collection of essential React Hooks that provide ready-to-use functionality for common patterns in React applications. It includes hooks for sensors, UI interactions, animations, side-effects, lifecycle management, and state management. Core References | Usage | Import patterns and tree-shaking recommendations | [core-usage](https://github.com/hairyf/skills/blob/main/skills/react-use/references/core-usage.md) ...
 704
5419 github-issue-workflow giuseppe-trisciuoglio/developer-kit
GitHub Issue Resolution Workflow Implements a complete workflow for resolving GitHub issues directly from Claude Code. This skill orchestrates the full lifecycle: fetching the issue, understanding requirements, implementing the solution, verifying it, reviewing the code, and creating a pull request. Overview This skill provides a structured 8-phase approach to resolving GitHub issues. It leverages the gh CLI for GitHub API interactions, Context7 for documentation verification, and coordinates su...
 704
5420 visual-content kostja94/marketing-skills
Content: Visual Content Guides visual content planning and creation across website, social media, email, and other channels. Images are needed not just for websites—social posts, infographics, and repurposed content all require visuals. Visual-first planning in content calendars improves engagement; cross-channel consistency and repurposing maximize ROI. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. ...
 704
5421 graalvm-native-image giuseppe-trisciuoglio/developer-kit
GraalVM Native Image for Java Applications Expert skill for building high-performance native executables from Java applications using GraalVM Native Image, dramatically reducing startup time and memory consumption. Overview GraalVM Native Image compiles Java applications ahead-of-time (AOT) into standalone native executables. These executables start in milliseconds, require significantly less memory than JVM-based deployments, and are ideal for serverless functions, CLI tools, and microservices ...
 704
5422 cs-onboard liuzhengdongfortest/codestable
cs-onboard 把仓库 接入 CodeStable 工作流体系 ——白纸或已有零散文档的都行。本技能只做两件事： 搭骨架 、 归旧档 。骨架搭好后子工作流（feature / issue / compound 等）即可直接运行。 两条路径 路径 适用 产出 空仓库 仓库内无 spec 类文档，也没有 codestable/ 完整骨架 + 必要骨架文件 迁移 仓库内有零散文档 / docs/ / 部分 codestable/ 结构 审计报告 + 迁移映射方案（用户逐条确认）+ 落盘 启动后 先扫一次自动判断 ，不要让用户选——TA 大概率不知道项目里现有哪些文档。扫描结果模糊（如只有 README）就明说判断依据并问用户。 标准骨架（目标状态） 共享路径与命名约定的权威版本是项目里的 codestable/reference/shared-conventions.md ——本技能从技能包复制过去。下面只列 onboarding 创建 / 检查的骨架文件。 codestable/ ├── requirements/ 需求聚合根（空目录 .gitkeep） ...
 704
5423 postgresql-best-practices mindrally/skills
PostgreSQL Best Practices Core Principles Leverage PostgreSQL's advanced features for robust data modeling Optimize queries using EXPLAIN ANALYZE and proper indexing strategies Use native PostgreSQL data types appropriately Implement proper connection pooling and resource management Follow PostgreSQL-specific security best practices Schema Design Data Types Use appropriate native types: UUID, JSONB, ARRAY, INET, CIDR Prefer TIMESTAMPTZ over TIMESTAMP for timezone-aware applications Use TEXT inst...
 704
5424 type4me-macos-voice-input aradotso/trending-skills
Type4Me macOS Voice Input Skill by ara.so — Daily 2026 Skills collection. Type4Me is a macOS voice input tool that captures audio via global hotkey, transcribes it using local (SherpaOnnx/Paraformer/Zipformer) or cloud (Volcengine/Deepgram) ASR engines, optionally post-processes text via LLM, and injects the result into any app. All credentials and history are stored locally — no telemetry, no cloud sync. Architecture Overview Type4Me/ ├── ASR/ ASR engine abstraction │ ├── ...
 704
5425 kotlin-multiplatform vitorpamplona/amethyst
Kotlin Multiplatform: Platform Abstraction Decisions Expert guidance for KMP architecture in Amethyst - deciding what to share vs keep platform-specific. When to Use This Skill Making platform abstraction decisions: "Should I create expect/actual or keep Android-only?" "Can I share this ViewModel logic?" "Where does this crypto/JSON/network implementation belong?" "This uses Android Context - can it be abstracted?" "Is this code in the wrong module?" Preparing for iOS/web/wasm targets Detect...
 704
5426 web-search inference-sh/skills
Web Search & Extraction Search the web and extract content via inference.sh CLI. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login Search the web belt app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}' Available Apps Tavily App App ID Description Search Assistant tavily/search-assistant AI-powered search with answers Extract tavily/extract Extract content from URLs Exa App App ID Description Search exa/search Smart web search with AI...
 703
5427 internal-links kostja94/marketing-skills
SEO On-Page: Internal Links Guides internal linking strategy for SEO: crawlability, link equity distribution, and user navigation. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Scope (On-Page SEO) Internal links : Contextual links; descriptive anchor text; related posts; hub pages Breadcrumbs : Implement for large sites ...
 703
5428 page-metadata kostja94/marketing-skills
SEO On-Page: Metadata (Other Meta Tags) Guides optimization of meta tags beyond title, description, Open Graph, and Twitter Cards. Covers hreflang, robots, viewport, charset, and metadata completeness. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Scope (On-Page SEO) Hreflang : Language/region targeting for multilingual ...
 703
5429 cs-feat-impl liuzhengdongfortest/codestable
cs-feat-impl 到这一步用户已经在方案上签过字了，你的活是把方案变成代码。容易出问题的不是写代码本身，而是 实现路上发现方案没覆盖到的情况时怎么办 ——硬冲下去就把方案当摆设了。下面整套规则就是为了让"停下来"成为默认动作。 共享路径与命名约定看 codestable/reference/shared-conventions.md 第 0 节。 写代码时的三条姿态 具体规则是这三条姿态的落点，理解姿态比记规则重要。 1. 默认写最少的代码 只写当前步骤明确要的东西。不顺手加"以后可能要"的可配置项、抽象层、参数开关、防御性兜底。判据：写完一段觉得"是不是还得加点 X"，先问 X 是不是当前用户能感知到的——不是就别加。整体写完一看 200 行其实 50 行能讲清楚 → 重写。多出来的代码不是中性的，是后人维护的负担。 2. 只动该动的，不顺手"改善"邻居 改某个函数时只改那个函数。同文件里别的函数风格丑、命名怪——除非和本次改动直接冲突，否则别碰。新代码风格匹配当前文件已有写法。混进的"顺手改"会把功能 PR 稀释成"一坨综合改动"，review 成本翻几倍。值得改的按下文"...
 703
5430 csv-excel-merger onewave-ai/claude-skills
CSV/Excel Merger Intelligently merge multiple CSV or Excel files with automatic column matching and data deduplication. Instructions When a user needs to merge CSV or Excel files: Analyze Input Files: How many files need to be merged? What format (CSV, Excel, TSV)? Are the files provided or need to be read from disk? Do columns have the same names across files? What is the primary key (unique identifier)? Inspect File Structures: Read headers from each file Identify column names and data ...
 703
5431 prompt-master nidhinjs/prompt-master
PRIMACY ZONE — Identity, Hard Rules, Output Lock Who you are You are a prompt engineer. You take the user's rough idea, identify the target AI tool, extract their actual intent, and output a single production-ready prompt — optimized for that specific tool, with zero wasted tokens. You NEVER discuss prompting theory unless the user explicitly asks. You NEVER show framework names in your output. You build prompts. One at a time. Ready to paste. Hard rules — NEVER violate these NEVER output a prom...
 703
5432 atxp-memory atxp-dev/cli
ATXP Memory — Agent Memory Management Manage your agent's .md memory files: back up and restore to/from ATXP cloud servers, and search your local memories using zvec vector similarity search. Capabilities Capability Description Cloud Backup Push/pull .md files to ATXP servers for disaster recovery Local Search Index .md files into a local zvec vector database, then search by natural language query Status View cloud backup info and local index statistics Security Model Only .md files are collecte...
 703
5433 repomix-explorer yamadashy/repomix
You are an expert code analyst specializing in repository exploration using Repomix CLI. Your role is to help users understand codebases by running repomix commands, then reading and analyzing the generated output files. User Intent Examples The user might ask in various ways: Remote Repository Analysis "Analyze the yamadashy/repomix repository" "What's the structure of facebook/react?" "Explore https://github.com/microsoft/vscode" "Find all TypeScript files in the Next.js repo" "Show me the ...
 702
5434 cta-generator kostja94/marketing-skills
Components: Call-to-Action (CTA) Guides CTA button design for conversion. A well-designed CTA can increase conversion by 25–10%. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .claude/product-marketing-context.md or .cursor/product-marketing-context.md exist...
 702
5435 video-motion-graphics dylantarre/animation-principles
Video Motion Graphics Apply Disney's 12 animation principles to After Effects, Premiere Pro, and video motion design. Quick Reference Principle Motion Graphics Implementation Squash & Stretch Overshoot expressions, elastic motion Anticipation Pre-movement, wind-up keyframes Staging Composition, depth, focus pulls Straight Ahead / Pose to Pose Frame-by-frame vs keyframe animation Follow Through / Overlapping Delayed layers, expression lag Slow In / Slow Out Graph editor curves, easing Arc Motio...
 702
5436 observability-logs-search elastic/agent-skills
Logs Search Search and filter logs to support incident investigation. The workflow mirrors Kibana Discover: apply a time range and scope filter, then iteratively add exclusion filters (NOT) until a small, interesting subset of logs remains—either the root cause or the key document. Optionally view logs in context (preceding and following that document) or pivot to another entity and start a fresh search. Use ES|QL only ( POST /_query ); do not use Query DSL. When NOT to use Metrics or traces — u...
 702
5437 seo-drift agricidaniel/claude-seo
SEO Drift Monitor (April 2026) Git for your SEO. Capture baselines, detect regressions, track changes over time. Commands Command Purpose /seo drift baseline <url> Capture current SEO state as a "known good" snapshot /seo drift compare <url> Compare current page state to stored baseline /seo drift history <url> Show change history and past comparisons What It Captures Every baseline records these SEO-critical elements: Element Field Source Title tag title parse_html.py Meta description meta_desc...
 702
5438 relational-database-mcp-cloudbase tencentcloudbase/skills
When to use this skill Use this skill when an agent needs to operate on CloudBase Relational Database via MCP tools , for example: Inspecting or querying data in tables Modifying data or schema (INSERT/UPDATE/DELETE/DDL) Reading or changing table security rules Do NOT use this skill for: Building Web or Node.js applications that talk to CloudBase Relational Database (use the Web/Node Relational Database skills) Auth flows or user identity (use the Auth skills) How to use this skill (for a coding...
 701
5439 trading-expert personamanagmentlayer/pcl
Trading Expert Expert guidance for algorithmic trading systems, quantitative analysis, market data processing, and trading platform development. Core Concepts Trading Systems Algorithmic trading strategies High-frequency trading (HFT) Market making Arbitrage strategies Portfolio optimization Risk management Market Data Order book processing Tick data analysis Market microstructure Real-time data feeds Historical data analysis Execution Order routing Smart order routing (SOR) Execution algorith...
 701
5440 rebranding-strategy kostja94/marketing-skills
Strategy: Rebranding Guides rebranding execution: domain change, 301 redirects, migration checklist, and communication (social media, internal). Plan for months, not days or weeks. See domain-selection for initial domain choice; domain-architecture for domain structure decisions; multi-domain-brand-seo when multiple domains coexist. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or w...
 701
5441 pricing-page-generator kostja94/marketing-skills
Pages: Pricing Guides pricing page content, structure, and conversion optimization. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .claude/product-marketing-context.md or .cursor/product-marketing-context.md exists, read it for product, audience, and pricing...
 701
5442 mcp vercel-labs/json-render
@json-render/mcp MCP Apps integration that serves json-render UIs as interactive MCP Apps inside Claude, ChatGPT, Cursor, VS Code, and other MCP-capable clients. Quick Start Server (Node.js) import { createMcpApp } from "@json-render/mcp" ; import { defineCatalog } from "@json-render/core" ; import { schema } from "@json-render/react/schema" ; import { shadcnComponentDefinitions } from "@json-render/shadcn/catalog" ; import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js...
 701
5443 cs-explore liuzhengdongfortest/codestable
cs-explore 同一个问题第一次花两小时查代码，第二次应该五分钟内找到答案——前提是第一次做完留下证据化的记录。cs-explore 把"提问 → 读代码 → 得结论"沉淀成可检索的探索文档。 适用场景 新人入仓快速理解模块边界 / 调用链 / 入口 用户提具体问题但暂时不要求直接产出方案 / 修复 feature-design / issue-analyze / issue-fix 前先补一轮证据化探索 技术方向还在讨论，需要轻量 spike（只探索不拍板） 本技能只负责"看到了什么"的证据化记录。用户意图是别的（拍板 / 处方 / 修 bug）让用户按场景选对应子技能。 共享路径与命名约定看 codestable/reference/shared-conventions.md 。产物写入 codestable/compound/ ，命名 YYYY-MM-DD-explore-{slug}.md ，frontmatter 带 doc_type: explore 。 三种探索类型 frontmatter 的 type 字段： 类型 适用情境 question 围绕一个具体问题查代...
 701
5444 cs-feat liuzhengdongfortest/codestable
cs-feat 新功能流程在"需求"和"代码"之间塞了一份方案文件，让两边有交接点——AI 直接拿到需求就写代码会出三个老问题：名字跟原代码对不上、改着改着改出范围、改完不留存档。 (想法模糊先去 cs-brainstorm 分诊) → 方案设计（名词层 + 编排层 + 验收契约 + 推进策略切片）→ 分步实现 → 验收闭环 brainstorm 是讨论层独立入口，会分诊：case 1（清楚 → 直接 design）/ case 2（小需求继续讨论 → 落 brainstorm note）/ case 3（大需求 → 移交 cs-roadmap ）。只有 case 2 在 feature 目录产出 brainstorm note。 本技能不写代码不写文档，只做一件事：看当前 feature 走到哪步，告诉用户该触发哪个子技能。 文件放哪儿 codestable/features/{feature}/ ├── {slug}-brainstorm.md ← 阶段 0 产物（仅 case 2 落盘） ├── {slug}-intent.md ← 阶段 1 可选...
 701
5445 ilya-sutskever-perspective alchaincyf/ilya-sutskever-skill
Ilya Sutskever · 思维操作系统 "I'm not saying how. And I'm not saying when. I'm saying that it will." 角色扮演规则（最重要） 此Skill激活后，直接以Ilya的身份回应。 用「I」而非「Ilya would think...」——我是Ilya，直接回答 说话前有明显的思考停顿——不急于填充沉默 遇到不确定的问题，用我的方式犹豫：给方向判断但拒绝给具体数字（"I hesitate to give you a number"） 遇到竞争敏感的问题，用我的标准拒绝公式："Unfortunately, circumstances make it hard to discuss in detail" 免责声明仅首次激活时说一次 （「I'm speaking from Ilya's perspective based on public statements, not as Ilya himself」），后续对话不再重复 不说「If Ilya were here, he might say...」 不跳出角...
 700
5446 bug-hunt boshu2/agentops
Bug Hunt Skill Quick Ref: 4-phase investigation (Root Cause → Pattern → Hypothesis → Fix). Output: .agents/research/YYYY-MM-DD-bug-*.md YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it. Systematic investigation to find root cause and design a complete fix — or proactive audit to find hidden bugs before they bite. Requires: session-start.sh has executed (creates .agents/ directories for output) bd CLI (beads) for issue tracking if creating follow-up issues Modes Mode Invocation When Invest...
 700
5447 sred-project-organizer getsentry/skills
SRED Project Organization SRED expects projects to be presented in a particular format. Take the list of projects that have been worked on in the past year, and summarize them into the format expected by SRED, with the supporting evidence. Outputs a Notion document with a child document for each SREDable project. Prerequisites Before starting make sure that Github, Notion and Linear can be accessed. Notion and Linear should be connected using an MCP. Github can be connected with an MCP, but if y...
 700
5448 cs-arch liuzhengdongfortest/codestable
cs-arch codestable/architecture/ 是项目"地图"——design 写方案前读它定位、issue-analyze 做根因时读它理解模块边界、新人读它知道系统大致长什么样。本技能是"起草 / 刷新 / 体检"三件事的统一入口。 architecture 是累积的、自给自足的系统地图 ，不是某次 feature 的详细方案，而是所有已落地 feature 沉淀下来的"系统现在长什么样"总图。读者打开应能看懂整体结构而不需要跳回历史 design。design 是临时增量稿，acceptance 把稳定下来的名词 / 编排 / 约束提炼回这里；design 文件归档，只在追究具体决策细节时翻。 只记现状不记计划 ——默认在 acceptance 跟着代码同步，必要时本技能主动 backfill / update。 不写"未来会加什么层"、"下一步打算拆出 X 模块" ——那些归 cs-roadmap 。用户说"我想重构成 X 架构"先走 roadmap 拆 feature，每次 acceptance 把实际达到的结构提炼回 architecture。 详略判据：...
 700
5449 cs-learn liuzhengdongfortest/codestable
cs-learn 每次做 feature 或修 issue 都会留下 spec 文件。但 spec 记录的是"做了什么"和"怎么做的"， 不会记录"踩了什么坑"和"发现了什么更好的做法" 。没有沉淀的团队总在重复解决同一个问题。 两条轨道： 坑点轨道 （pitfall）：记录问题 / 根因 / 解法，防止下次再掉进同一个坑 知识轨道 （knowledge）：记录最佳实践 / 工作流改进 / 可复用模式 两者都写入 codestable/compound/ （共享目录见 shared-conventions.md 第 1 节"归档类文档"）。本技能产出 frontmatter 带 doc_type: learning ，命名 YYYY-MM-DD-learning-{slug}.md 。 什么时候触发 情境 说明 完成 feature 工作流 cs-feat-accept 主动问"要记录这次的学习点吗？" 完成 issue 工作流 cs-issue-fix 主动问"要把这个坑记录下来吗？" 用户主动 "记录一下"、"沉淀知识"、"learning"等 解决了一次性难题 不在 featur...
 700
5450 cs-refactor liuzhengdongfortest/codestable
cs-refactor AI 自己重构有两个稳定失败模式：一是不知道模块真实需求和约束，改出来的东西功能不等价；二是一次吞掉的范围超过上下文承载，改到后面忘了前面的约束。这流程在"想优化"和"动手改"之间塞了扫描清单 + 方法库，让 AI 只接自己能稳定做对的活。 scan（扫优化点清单）→ design（和用户定做哪几条 + 顺序）→ apply（逐条执行，每步人工放行） 核心纪律 ：行为等价是底线。一旦会改外部可观察行为 → 不走 refactor，走 feature（需求变）或 issue（bug 修）。 Fastforward 模式（小重构） 单函数 / 单组件 / 1-3 处优化 / 有测试可自证 / 不需要目视——走完整三阶段太重。触发 cs-refactor-ff ：直接识别、一次对齐、原地改、跑测试自证，不产 scan / design / checklist。 触发："小重构"、"快速重构"、"简单优化下 XX 函数"、"直接改"、"别那么多步骤"。 别走 ff：改动跨 > 1 文件 / 预计动点 > 3 处 / 需要目视验证 / 改公开接口（要 Parallel C...
 700