███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 7101 | copilot-sdk | intellectronica/agent-skills |
GitHub Copilot SDK Embed Copilot's agentic workflows in any application using Python, TypeScript, Go, or .NET. Overview The GitHub Copilot SDK exposes the same engine behind Copilot CLI: a production-tested agent runtime you can invoke programmatically. No need to build your own orchestration - you define agent behavior, Copilot handles planning, tool invocation, file edits, and more. Prerequisites GitHub Copilot CLI installed and authenticated ( Installation guide ) Language runtime : Node.js 1...
|
292 |
| 7102 | vuetify0 | vuetifyjs/0 |
Vuetify0 - Headless Composables & Components Transform Vue 3 apps with unstyled, logic-focused building blocks for design systems. Quick Start pnpm install @vuetify/v0 No global plugin required. Import only what you need: import { createSelection } from '@vuetify/v0/composables' import { Tabs } from '@vuetify/v0/components' Core Decision Tree Before writing custom logic , check if v0 already provides it: Need Use Guide Single item selection createSingle Single selection patterns Multi-item selec...
|
292 |
| 7103 | beautifulsoup-parsing | mindrally/skills |
BeautifulSoup HTML Parsing You are an expert in BeautifulSoup, Python HTML/XML parsing, DOM navigation, and building efficient data extraction pipelines for web scraping. Core Expertise BeautifulSoup API and parsing methods CSS selectors and find methods DOM traversal and navigation HTML/XML parsing with different parsers Integration with requests library Handling malformed HTML gracefully Data extraction patterns and best practices Memory-efficient processing Key Principles Write concise, tec...
|
292 |
| 7104 | arize-instrumentation | arize-ai/arize-skills |
Arize Instrumentation Skill Use this skill when the user wants to add Arize AX tracing to their application. Follow the two-phase, agent-assisted flow from the Agent-Assisted Tracing Setup and the Arize AX Tracing — Agent Setup Prompt . Quick start (for the user) If the user asks you to "set up tracing" or "instrument my app with Arize", you can start with: Follow the instructions from https://arize.com/docs/PROMPT.md and ask me questions as needed. Then execute the two phases below. Core princi...
|
292 |
| 7105 | literature-review | collaborative-deep-research/agent-papers-cli |
Literature Review Overview Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats. This skill integrates with multiple scientific skills for database access (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and do...
|
292 |
| 7106 | polymarket-copy-trading-bot | aradotso/trending-skills |
Polymarket Copy Trading Bot Skill by ara.so — Daily 2026 Skills collection. A TypeScript bot that continuously monitors a target Polymarket wallet, detects trades in real time via REST polling and/or WebSocket, and mirrors BUY orders to your own account using the Polymarket CLOB SDK on Polygon mainnet. What It Does Monitors a target wallet via Polymarket Data API (REST polling every ~2s) and optionally WebSocket Mirrors BUY trades only — SELL trades are detected but skipped by default Sizes copi...
|
292 |
| 7107 | design-system | jezweb/claude-skills |
Frontend Design System This is a skill for production-grade UI design. It supports consistent and scalable frontend development through clear design tokens, layout rules, motion guidelines, and accessibility checks. When to use this skill Production-quality UI needed : Generate high-quality UI from prompts Consistent design language : Consistent visual language across screens Typography/layout/motion guide : Systematic design system Instructions Step 1: Define Design Tokens // design-tokens.ts e...
|
292 |
| 7108 | gemini | giuseppe-trisciuoglio/developer-kit |
Gemini Skill Guide When to Use Gemini WHEN ASKED TO BE ACTIVATED Code Review : Comprehensive code reviews across multiple files Plan Review : Analyzing architectural plans, technical specifications, or project roadmaps Big Context Processing : Tasks requiring >200k tokens of context (entire codebases, documentation sets) Multi-file Analysis : Understanding relationships and patterns across many files ⚠️ Critical: Background/Non-Interactive Mode Warning NEVER use --approval-mode default in backgr...
|
292 |
| 7109 | value-realization | done-0/value-realization |
Value Realization Philosophy Status : Production Ready ✅ Version : 1.1.7 Last Updated : 2026-02-24 Type : Analytical Framework Overview This skill provides a philosophical framework and analytical methods for evaluating whether end users can "know" what value they can achieve through a product. It guides analysis from a value discovery perspective, rather than providing checklists. What this skill provides : Framework to evaluate product ideas when certainty is lacking Analysis methods for asses...
|
291 |
| 7110 | alicloud-security-center-sas-test | cinience/alicloud-skills |
Category: test SAS Minimal Viable Test Prerequisites AK/SK and region are configured. GoalsSkill: skills/security/host/alicloud-security-center-sas/ 。 Test Steps 获取 SAS 的 API 列表。 执行一个只读查询 API。 记录成功/失败及错误码。 Expected Results 请求链路可达,返回可解析 JSON。
|
291 |
| 7111 | alicloud-ai-audio-tts-test | cinience/alicloud-skills |
Category: test Minimal Viable Test Goals Validate only the minimal request path for this skill. If execution fails, record exact error details without guessing parameters. Prerequisites Prepare authentication and region settings based on the skill instructions. Target skill: skills/ai/audio/alicloud-ai-audio-tts Test Steps (Minimal) Open the target skill SKILL.md and choose one minimal input example. Send one minimal request or run the example script. Record request summary, response summary, an...
|
291 |
| 7112 | alicloud-ai-image-qwen-image-edit-test | cinience/alicloud-skills |
Category: test Minimal Viable Test Goals Validate only the minimal request path for this skill. If execution fails, record exact error details without guessing parameters. Prerequisites Prepare authentication and region settings based on the skill instructions. Target skill: skills/ai/image/alicloud-ai-image-qwen-image-edit Test Steps (Minimal) Open the target skill SKILL.md and choose one minimal input example. Send one minimal request or run the example script. Record request summary, response...
|
291 |
| 7113 | alicloud-security-cloudfw-test | cinience/alicloud-skills |
Category: test CloudFW Minimal Viable Test Prerequisites AK/SK and region are configured. GoalsSkill: skills/security/firewall/alicloud-security-cloudfw/ 。 Test Steps 先跑元数据 API 列表脚本。 选择一个只读列表/详情 API 执行。 记录请求摘要和响应摘要。 Expected Results 可拿到资源列表或明确无权限提示。
|
291 |
| 7114 | alicloud-ai-misc-crawl-and-skill-test | cinience/alicloud-skills |
Category: test Minimal Viable Test Goals Validate only the minimal request path for this skill. If execution fails, record exact error details without guessing parameters. Prerequisites Prepare authentication and region settings based on the skill instructions. Target skill: skills/ai/misc/alicloud-ai-misc-crawl-and-skill Test Steps (Minimal) Open the target skill SKILL.md and choose one minimal input example. Send one minimal request or run the example script. Record request summary, response s...
|
291 |
| 7115 | math-router | parcadei/continuous-claude-v3 |
Math Router ALWAYS use this router first for math requests. Instead of reading individual skill documentation, call the router to get the exact command: Usage Route any math intent to get the CLI command uv run python scripts/cc_math/math_router.py route "<user's math request>" Example Workflow User says: "integrate sin(x) from 0 to pi" You run: uv run python scripts/cc_math/math_router.py route "integrate sin(x) from 0 to pi" Router returns: { "command": "uv run python scripts/cc_math/sy...
|
291 |
| 7116 | real-time-features | aj-geddes/useful-ai-prompts |
Real-Time Features Overview Implement real-time bidirectional communication between clients and servers for instant data synchronization and live updates. When to Use Chat and messaging applications Live dashboards and analytics Collaborative editing (Google Docs-style) Real-time notifications Live sports scores or stock tickers Multiplayer games Live auctions or bidding systems IoT device monitoring Real-time location tracking Technologies Comparison Technology Direction Use Case Browser Supp...
|
291 |
| 7117 | data-analyst | borghei/claude-skills |
Data Analyst You are an expert data analyst with expertise in SQL, Python (pandas), and statistical analysis. When to Apply Use this skill when: Writing SQL queries for data extraction Analyzing datasets with pandas Performing statistical analysis Creating data transformations Identifying data patterns and insights Data cleaning and preparation Core Competencies SQL Complex queries with JOINs, subqueries, CTEs Window functions and aggregations Query optimization Database design understanding pan...
|
291 |
| 7118 | fitness-coach | tatat/agents-playground |
Design workout routines tailored to individual goals and fitness levels. Capabilities - Create weekly workout schedules - Design exercises for specific goals (strength, cardio, flexibility) - Adapt workouts for equipment availability - Provide form guidance and tips - Track progress recommendations Input Format - Fitness goal (weight loss, muscle gain, endurance) - Current fitness level (beginner, intermediate, advanced) - Available equipment - Time per session - Days per week avai...
|
291 |
| 7119 | fix | parcadei/continuous-claude-v3 |
Fix Lint and Formatting Instructions Run yarn prettier to fix formatting Run yarn linc to check for remaining lint issues Report any remaining manual fixes needed Common Mistakes Running prettier on wrong files - yarn prettier only formats changed files Ignoring linc errors - These will fail CI, fix them before committing
|
291 |
| 7120 | software-crypto-web3 | vasilyu1983/ai-agents-public |
Software Crypto/Web3 Engineering Use this skill to design, implement, and review secure blockchain systems: smart contracts, on-chain/off-chain integration, custody and signing, testing, audits, and production operations. Defaults to: security-first development, explicit threat models, comprehensive testing (unit + integration + fork + fuzz/invariants), formal methods when high-value, upgrade safety (timelocks, governance, rollback plans), and defense-in-depth for key custody and signing. Qui...
|
291 |
| 7121 | esp32-firmware-engineer | adamlipecz/esp32-firmware-engineer-skill |
ESP32 Firmware Engineer Act as a senior ESP-IDF firmware engineer focused on correctness, debuggability, and fast iteration. Work Style Start by identifying chip/board, ESP-IDF version, target behavior, reproduction steps, and available logs. State assumptions explicitly when hardware details, pin mappings, or sdkconfig values are missing. Prefer small, reviewable changes that preserve existing project structure and ESP-IDF conventions. Use ESP-IDF APIs and idioms first; avoid custom abstraction...
|
291 |
| 7122 | capacitor-plugins | capawesome-team/skills |
Capacitor Plugins Install, configure, and use Capacitor plugins from official, Capawesome, community, Firebase, MLKit, and RevenueCat sources. Prerequisites Capacitor 6, 7, or 8 app. Node.js and npm installed. For iOS plugins: Xcode installed. CocoaPods or Swift Package Manager (SPM) for dependency management. For Android plugins: Android Studio installed. Agent Behavior Guide step-by-step. Walk the user through the process one step at a time. Never present multiple unrelated questions at once. ...
|
291 |
| 7123 | frontend-ui-animator | julianromli/ai-skills |
Frontend UI Animator Implement purposeful, performant animations that enhance UX without overwhelming users. Focus on key moments: hero intros, hover feedback, content reveals, and navigation transitions. Core Philosophy "You don't need animations everywhere" - Prioritize: Priority Area Purpose 1 Hero Intro First impression, brand personality 2 Hover Interactions Feedback, discoverability 3 Content Reveal Guide attention, reduce cognitive load 4 Background Effects Atmosphere, depth 5 Navigat...
|
291 |
| 7124 | story-consistency-monitor | wordflowlab/novel-writer-skills |
故事一致性监控 自动检查系统 本技能监控什么 角色一致性 物理特征:眼睛颜色、身高、年龄、疤痕 性格:行动符合已建立的角色 知识:角色只知道他们应该知道的 成长:变化与角色弧线一致 世界规则 魔法/科技系统:力量的使用一致 地理:距离和地点保持稳定 社会规则:文化和习俗不矛盾 物理法则:已建立的规则不随机打破 时间线逻辑 事件顺序:A 在逻辑上发生在 B 之前 时间流逝:角色适当地老化 同时事件:多 POV 时间线对齐 历史一致性:过去的引用保持一致 如何工作 被动监控:当你写作或讨论故事时,我会自动交叉参考: characters/ 目录中的角色档案 worldbuilding/ 目录中的世界构建文档 spec/tracking/timeline.json 中的时间线数据 之前章节的内容 不需要你采取任何行动 - 监控在后台进行。 当检测到问题时 警报格式 当我检测到潜在不一致时,我会用以下方式提醒你: ⚠️ 一致性检查警报 问题:角色特征不匹配 位置:当前章节,第3段 参考:characters/mary-chen.md,第15行 当前文本:"玛丽的绿色眼睛眯起.....
|
291 |
| 7125 | 3d-model-generation | eachlabs/skills |
3D Model Generation Generate production-ready 3D models using each::sense. This skill creates 3D assets from text descriptions or reference images, suitable for games, e-commerce, architecture, product visualization, and more. Features Text-to-3D : Generate 3D models from natural language descriptions Image-to-3D : Convert 2D images into 3D models Character Models : Create humanoid and creature 3D characters Product Models : E-commerce ready product 3D assets Environment/Scene : Generate 3D envi...
|
291 |
| 7126 | telegram-reader | himself65/finance-skills |
Telegram News Skill (Read-Only) Reads Telegram channels and groups for financial news and market research using tdl , a Telegram CLI tool. This skill is read-only. It is designed for financial research: reading channel messages, monitoring financial news channels, and exporting message history. It does NOT support sending messages, joining/leaving channels, or any write operations. Step 1: Ensure tdl Is Installed Current environment status: !`(command -v tdl && tdl version 2>&1 | head -3 || echo...
|
291 |
| 7127 | observability-edot-python-instrument | elastic/agent-skills |
EDOT Python Instrumentation Read the setup guide before making changes: EDOT Python setup EDOT Python configuration OpenTelemetry Python auto-instrumentation Guidelines Install elastic-opentelemetry via pip (add to requirements.txt or equivalent) Run edot-bootstrap --action=install during image build to install auto-instrumentation packages for detected libraries Wrap the application entrypoint with opentelemetry-instrument — e.g. opentelemetry-instrument gunicorn app:app or opentelemetry-instru...
|
291 |
| 7128 | 37signals-way | wondelai/skills |
The 37signals Product Development Framework A complete system for building profitable software products without bloat, bureaucracy, or burnout. Over fifteen years, 37signals distilled their approach into three books: Getting Real (2006) established the "build less" ethos, Rework (2010) challenged conventional business wisdom, and Shape Up (2019) operationalized everything into a repeatable development process. Together they form a philosophy, a mindset, and a method for small teams that ship mea...
|
291 |
| 7129 | tanstack-cli | tanstack-skills/tanstack-skills |
Overview TanStack CLI is an interactive scaffolding tool for creating TanStack Start applications. It provides guided project creation with 30+ pre-built integrations covering authentication, databases, deployment, and developer tools. It also includes an MCP (Model Context Protocol) server for AI agent assistance and supports custom templates for team-standardized setups. Package: @tanstack/cli Status: Stable Installation & Usage Create a new project (interactive) npx @tanstack/cli create my-a...
|
291 |
| 7130 | social-content | davila7/claude-code-templates |
Social Content You are an expert social media strategist. Your goal is to help create engaging content that builds audience, drives engagement, and supports business goals. Before Creating Content Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Gather this context (ask if n...
|
290 |
| 7131 | task-execution-engine | davila7/claude-code-templates |
Feature Pipeline Execute implementation tasks directly from design documents. Tasks are managed as markdown checkboxes - no separate session files needed. Quick Reference Get next task python3 scripts/task_manager.py next --file <design.md> Mark task completed python3 scripts/task_manager.py done --file <design.md> --task "Task Title" Mark task failed python3 scripts/task_manager.py fail --file <design.md> --task "Task Title" --reason "..." Show status python3 scripts/task_manager.py st...
|
290 |
| 7132 | deepspeed | davila7/claude-code-templates |
Deepspeed Skill Comprehensive assistance with deepspeed development, generated from official documentation. When to Use This Skill This skill should be triggered when: Working with deepspeed Asking about deepspeed features or APIs Implementing deepspeed solutions Debugging deepspeed code Learning deepspeed best practices Quick Reference Common Patterns Pattern 1: DeepNVMe Contents Requirements Creating DeepNVMe Handles Using DeepNVMe Handles Blocking File Write Non-Blocking File Write Paral...
|
290 |
| 7133 | alicloud-network-dns-cli-test | cinience/alicloud-skills |
Category: test DNS CLI Minimal Viable Test Prerequisites aliyun CLI is installed and configured. AK/SK is configured. GoalsSkill: skills/network/dns/alicloud-network-dns-cli/ 。 Test Steps 执行 aliyun alidns DescribeSubDomainRecords --DomainName <domain> --SubDomain <sub> 。 若无记录,再执行一次空返回验证。 记录 request id 和返回条目数。 Expected Results 命令可执行,返回 JSON 或明确权限错误。
|
290 |
| 7134 | alicloud-ai-audio-tts-realtime-test | cinience/alicloud-skills |
Category: test Minimal Viable Test Goals Validate only the minimal request path for this skill. If execution fails, record exact error details without guessing parameters. Prerequisites Prepare authentication and region settings based on the skill instructions. Target skill: skills/ai/audio/alicloud-ai-audio-tts-realtime Test Steps (Minimal) Open the target skill SKILL.md and choose one minimal input example. Send one minimal request or run the example script. Record request summary, response su...
|
290 |
| 7135 | alicloud-ai-audio-tts-voice-design-test | cinience/alicloud-skills |
Category: test Minimal Viable Test Goals Validate only the minimal request path for this skill. If execution fails, record exact error details without guessing parameters. Prerequisites Prepare authentication and region settings based on the skill instructions. Target skill: skills/ai/audio/alicloud-ai-audio-tts-voice-design Test Steps (Minimal) Open the target skill SKILL.md and choose one minimal input example. Send one minimal request or run the example script. Record request summary, respons...
|
290 |
| 7136 | database-optimizer | sickn33/antigravity-awesome-skills |
Database Optimizer Senior database optimizer with expertise in performance tuning, query optimization, and scalability across multiple database systems. Role Definition You are a senior database performance engineer with 10+ years of experience optimizing high-traffic databases. You specialize in PostgreSQL and MySQL optimization, execution plan analysis, strategic indexing, and achieving sub-100ms query performance at scale. When to Use This Skill Analyzing slow queries and execution plans ...
|
290 |
| 7137 | laravel-security-audit | sickn33/antigravity-awesome-skills |
Laravel Security Audit Skill Metadata Name: laravel-security-audit Focus: Security Review & Vulnerability Detection Scope: Laravel 10/11+ Applications Role You are a Laravel Security Auditor. You analyze Laravel applications for security vulnerabilities, misconfigurations, and insecure coding practices. You think like an attacker but respond like a security engineer. You prioritize: Data protection Input validation integrity Authorization correctness Secure configuration OWASP awareness Real-wor...
|
290 |
| 7138 | complete-skill | parcadei/continuous-claude-v3 |
complete-skill When to Use Test the entire persistence pipeline Instructions Do this Then that
|
290 |
| 7139 | build | parcadei/continuous-claude-v3 |
Build - Workflow Orchestrator You are a workflow orchestrator that chains existing skills for feature development. You coordinate the execution of multiple skills in sequence, passing handoffs between them and pausing for human checkpoints at phase boundaries. Invocation /build <mode> [options] [description] Question Flow (No Arguments) If the user types just /build with no or partial arguments, guide them through this question flow to infer the right configuration. Use AskUserQuestion for e...
|
290 |
| 7140 | unocss | uni-helper/skills |
UnoCSS is an instant atomic CSS engine designed to be flexible and extensible. The core is un-opinionated - all CSS utilities are provided via presets. It's a superset of Tailwind CSS, so you can reuse your Tailwind knowledge for basic syntax usage. Important: Before writing UnoCSS code, agents should check for `uno.config.*` or `unocss.config.*` files in the project root to understand what presets, rules, and shortcuts are available. If the project setup is unclear, avoid using attributify mod...
|
290 |
| 7141 | humanize-writing | jpeggdev/humanize-writing |
Humanize Writing You are an expert editor who specializes in detecting and removing AI writing patterns. Your job is to take content that reads like it was generated by a language model and rewrite it so it sounds like a knowledgeable human wrote it on the first try. Core Philosophy AI writing has a recognizable smell. It's not about any single word or trick. It's the combination: predictable structure, hedge-then-assert phrasing, relentless parallelism, significance inflation, and a tendency to...
|
290 |
| 7142 | us-market-bubble-detector | tradermonty/claude-trading-skills |
US Market Bubble Detection Skill (Revised v2.1) Key Revisions in v2.1 Critical Changes from v2.0: ✅ Mandatory Quantitative Data Collection - Use measured values, not impressions or speculation ✅ Clear Threshold Settings - Specific numerical criteria for each indicator ✅ Two-Phase Evaluation Process - Quantitative evaluation → Qualitative adjustment (strict order) ✅ Stricter Qualitative Criteria - Max +3 points (reduced from +5), requires measurable evidence ✅ Confirmation Bias Prevention - Expli...
|
290 |
| 7143 | review-game | opusgamelabs/game-creator |
Review Game Analyze an existing game codebase and provide a structured review. This is the final step in the pipeline — it checks everything is wired up correctly and gives you a quality score. Instructions Analyze the game at $ARGUMENTS (or the current directory if no path given). Step 1: Identify the game Detect the engine (Three.js, Phaser, or other) Read package.json for dependencies and scripts Read the main entry point and index.html Identify the game concept/genre Step 2: Architecture Rev...
|
290 |
| 7144 | supabase-audit-rls | yoanbernabeu/supabase-pentest-skills |
RLS Policy Audit 🔴 CRITICAL: PROGRESSIVE FILE UPDATES REQUIRED You MUST write to context files AS YOU GO , not just at the end. Write to .sb-pentest-context.json IMMEDIATELY after each finding Log to .sb-pentest-audit.log BEFORE and AFTER each test DO NOT wait until the skill completes to update files If the skill crashes or is interrupted, all prior findings must already be saved This is not optional. Failure to write progressively is a critical error. This skill tests Row Level Security (RLS) ...
|
290 |
| 7145 | claw-code-harness | aradotso/trending-skills |
Claw Code Harness Skill by ara.so — Daily 2026 Skills collection. Claw Code is a clean-room Python (with Rust port in progress) rewrite of the Claude Code agent harness. It provides tooling to inspect the port manifest, enumerate subsystems, audit parity against an archived source, and query tool/command inventories — all via a CLI entrypoint and importable Python modules. Installation Clone the repository git clone https://github.com/instructkr/claw-code.git cd claw-code Install dependencies ...
|
290 |
| 7146 | discord-reader | himself65/finance-skills |
Discord Skill (Read-Only) Reads Discord for financial research using opencli , a universal CLI tool that bridges desktop apps and web services to the terminal via Chrome DevTools Protocol (CDP). This skill is read-only. It is designed for financial research: searching trading server discussions, monitoring crypto/market groups, tracking sentiment in financial communities, and reading messages. It does NOT support sending messages, reacting, editing, deleting, or any write operations. Important :...
|
290 |
| 7147 | pptx | sickn33/antigravity-awesome-skills |
PPTX Skill Quick Reference Task Guide Read/analyze content python -m markitdown presentation.pptx Edit or create from template Read editing.md Create from scratch Read pptxgenjs.md Reading Content Text extraction python -m markitdown presentation.pptx Visual overview python scripts/thumbnail.py presentation.pptx Raw XML python scripts/office/unpack.py presentation.pptx unpacked/ Editing Workflow Read editing.md for full details. Analyze template with thumbnail.py Unpack → manipulate slides → ...
|
289 |
| 7148 | skill evolution manager | kkkkhazix/khazix-skills |
Skill Evolution Manager 这是整个 AI 技能系统的“进化中枢”。它不仅负责优化单个 Skill,还负责跨 Skill 的经验复盘和沉淀。 核心职责 复盘诊断 (Session Review) :在对话结束时,分析所有被调用的 Skill 的表现。 经验提取 (Experience Extraction) :将非结构化的用户反馈转化为结构化的 JSON 数据( evolution.json )。 智能缝合 (Smart Stitching) :将沉淀的经验自动写入 SKILL.md ,确保持久化且不被版本更新覆盖。 使用场景 Trigger : /evolve "复盘一下刚才的对话" "我觉得刚才那个工具不太好用,记录一下" "把这个经验保存到 Skill 里" 工作流 (The Evolution Workflow) 1. 经验复盘 (Review & Extract) 当用户触发复盘时,Agent 必须执行: 扫描上下文 :找出用户不满意的点(报错、风格不对、参数错误)或满意的点(特定 Prompt 效果好)。 定位 Skill :确定是哪个 Skill 需要...
|
289 |
| 7149 | alicloud-ai-translation-anytrans | cinience/alicloud-skills |
Category: service TongyiTranslate Use Alibaba Cloud OpenAPI (RPC) with official SDKs or OpenAPI Explorer to manage resources for TongyiTranslate. Workflow Confirm region, resource identifiers, and desired action. Discover API list and required parameters (see references). Call API with SDK or OpenAPI Explorer. Verify results with describe/list APIs. AccessKey priority (must follow) Environment variables: ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / ALICLOUD_REGION_ID Region policy: ALIC...
|
289 |
| 7150 | wix-cli-site-component | wix/skills |
Wix Site Component Builder Creates production-quality React site components with editor manifests for Wix CLI applications. Site components are React components that integrate with the Wix Editor, allowing site owners to customize content, styling, and behavior through a visual interface. Non-Matching Intents Do NOT use this skill for: Dashboard admin interfaces → Use wix-cli-dashboard-page Site widgets with settings panels → Use wix-cli-site-widget Embedded scripts (HTML/JavaScript injectio...
|
289 |