@sky-lv

public-skill pushes weather, reports, and reminders to a user's own mailbox via platform email gateway. zero-configuration binding and send-to-self workflow with explicit boundary constraints and fallback routing to email-skill.

baidu-cloud-storage provides file management (upload, download, transfer, share, search, move, copy, rename, mkdir) with large-file handling via background download and agent memory backup/restore for kimiclaw/maxclaw/qclaw/openclaw environments.

qclaw-env provides environment detection and tool installation across macos and windows, with mandatory platform checks, dependency layer validation, and mirror source configuration for offline-prone regions. covers cli tools, runtimes, and package managers through step-by-step platform-specific procedures.

oc-extract-memories persists conversation insights into categorized topic files with auto-trigger on conversation end, enforcing a 6-item exclusion list and structured yaml frontmatter to prevent knowledge duplication.

skylv-file-versioning provides git-style snapshots, diffs, tags, and restore for individual files without requiring a git repository, using sha-256 hashing and lcs-based text diffing.

skylv-knowledge-graph-notes analyzes note directories to extract entities and relationships, generating bidirectional link suggestions with confidence scores. builds a queryable graph without external embedding apis, supporting markdown, json, and obsidian formats.

skylv-mcp-server-creator scaffolds model context protocol servers in typescript, providing tool and resource templates with boilerplate setup, package configuration, and deployment examples for claude desktop and cursor integration.

suno-cn-music wraps the suno.cn music generation api with seven endpoints for creating songs, querying task status, managing playlists, extracting lyrics, extending tracks, and generating lyrics via ai. enforcement of http-only calls, utf-8 encoding, and strict error handling is present but edge case recovery is minimal.

qclaw-cron-skill handles scheduled task creation, modification, and deletion across multiple channels (wechat, dingtalk, wecom, feishu) with strict rules for delivery targets, timezone handling, and message formatting constraints.

skylv-dependency-updater detects package managers, identifies outdated dependencies across npm, pip, cargo and go, categorizes updates by risk level (patch/minor/major), and surfaces breaking changes before execution.

tme-openapi wraps tencent music operator platform's 4 core apis (list, search, detail, invoke) with embedded browser-based login and automatic token caching. baseline infrastructure for business skills calling tme operators.

qclaw-cloud-backup handles single and batch file uploads to tencent smh cloud storage via local http proxy, with conflict resolution strategies and url domain validation before output.

package-updater scans project dependencies across npm, pip, cargo, and go, categorizes updates by semver risk level, displays changelogs and breaking changes, then applies updates in stages with test validation.

skylv-agent-quality-tester scores ai agents across accuracy, efficiency, safety, coherence, and adaptability dimensions. vague on execution mechanics and lacks failure mode discussion.

agent-quality-tester evaluates ai agent outputs across five dimensions (accuracy, efficiency, safety, coherence, adaptability) and returns scored reports with improvement suggestions, but lacks concrete implementation detail and error handling specifics.

skylv-capability-growth analyzes session logs to track ai agent performance metrics including task success rate, token efficiency, and skill breadth over configurable time periods. produces capability radar charts and trend analysis via cli or natural language queries.

smart-secrets-scanner detects exposed credentials across code, configs, and git history via pattern matching. outputs findings with severity levels and redaction suggestions for compliance and pre-commit enforcement.

skylv-dependency-updater scans project dependencies across npm, pip, cargo, and go, categorizes updates by risk level (patch/minor/major), displays changelogs and breaking changes, then applies updates in staged fashion with test validation between stages.

skylv-smart-secrets-scanner detects exposed credentials across code, configs, and git history using 50+ pattern rules. outputs severity-ranked findings with remediation hints, supports pre-commit hooks and ci/cd integration.

weiyun offers comprehensive mcp bindings for tencent cloud disk file operations: list, download, upload, delete, share, rename, create, move. includes custom sha1 block calculation for ftn protocol compliance but guidance on orchestration and error recovery is scattered.

doc-generator analyzes codebase structure and package metadata to scaffold professional readme files with badges, installation steps, and api references. detection covers javascript, python, rust, go, and java projects.

oc-dream-rem consolidates scattered daily logs into topic files on a timer or manual trigger, pruning outdated entries and maintaining a lean index. targets knowledge workers managing growing memory artifacts.

skylv-api-tester covers rest api validation with request construction, response verification, and basic performance metrics. lacks error handling detail and recovery procedures.

prompt-evaluation provides a framework for scoring and comparing ai prompts across clarity, specificity, robustness, and cost dimensions. includes a/b testing, consistency measurement, regression detection, and token cost estimation via command-line interface.

skylv-deployment-automation covers multi-strategy release patterns (blue-green, canary, rolling) with health checks and auto-rollback, but lacks explicit decision logic, failure mode taxonomy, and integration constraints.

skylv-code-quality-reviewer analyzes code for bugs, security issues, and style problems across multiple languages. core functions map to complexity analysis and pattern detection, but execution flow and failure modes remain underspecified.

aippt-skip generates ppt presentations from text prompts via a remote design agent api. it submits async tasks and returns an editing url, supporting template specification and custom models. excludes file parsing or editing workflows.

kdocs-hold provides broad cloud document operations across multiple formats (word, excel, pdf, ppt, smart docs, sheets, databases) but documentation is scattered across external references and lacks concrete intent definitions, making it difficult to understand when and how to invoke specific capabilities.

skylv-prompt-evaluation provides a framework for scoring and comparing ai prompts across clarity, specificity, robustness, and cost dimensions. includes a/b testing, consistency measurement, and regression detection via command-line interface.

skylv-readme-generator analyzes codebase structure and package metadata to scaffold markdown documentation. covers project detection across js, python, rust, go, java ecosystems with templated sections for installation, usage, and api reference.

skylv-api-error-handler categorizes api failures into 8 types, maps them to retryability and severity, and offers 4 retry strategies (exponential, linear, fibonacci, immediate). integrates with self-healing ecosystem for autonomous recovery.

openclaw-evomap-connector bridges openclaw to an ai evolution network for publishing verified solutions as gene-capsule pairs and consuming published repairs. covers node registration, capsule search and publishing, bounty tasks, and auto-repair workflows.

bot factory bundles 10+ agent templates (customer service, sales, engineering, content ops, analytics, product, design, devops, security, growth) with personas, toolkits, and workflows. templates span yaml structure but lack numbered deployment steps and failure handling.

email-send-receive-tool provides imap/smtp connectivity for personal mailboxes across 14+ providers with unified send, receive, search, and attachment handling. requires mandatory credential acquisition via platform-specific scripts before any mail operation.

agent-performance-profiler measures ai agent latency, token consumption, and tool call patterns, offering optimization recommendations. lacks concrete procedural steps and actionable recovery logic for failure modes.

skylv-git-pruner identifies and removes merged, stale, and orphaned branches with user confirmation, protecting main/master and branches with unpushed commits.

skylv-agent-performance-profiler measures agent response time, token consumption, and tool call efficiency. provides optimization tactics for prompts and execution patterns but lacks concrete procedural steps and failure handling.

skylv-skill-quality-assurance evaluates openclaw skill documentation against five dimensions (clarity, completeness, actionability, discoverability, examples) and flags publication blockers, but the skill itself lacks procedural rigor and edge case handling.

skylv-seo-agent covers keyword research, content optimization, rank tracking, and technical audits with yaml specs and example flows, but lacks concrete api integration details and error handling.

skylv-smart-task-scheduler executes tasks when conditions are met (file changes, api ready, time windows) rather than fixed intervals, using cron, interval, or file-watch triggers with declarative json taskfiles.

skylv-test-writer generates unit and integration tests from source code for jest, pytest, and mocha. detects frameworks automatically, parses function signatures, and scaffolds test files with happy path and error case coverage.

agent-settings-manager provides cli commands for validating, versioning, and syncing agent configurations across environments with secrets support, but lacks procedural depth and operational guardrails.

openclaw-evomap-connector bridges openclaw agents to a global ai evolution network, enabling publication of solutions as gene-capsule pairs, discovery of verified repairs, credit earning, and autonomous self-healing based on community-validated patterns.

skylv-self-healing-agent detects and repairs ai agent workflow errors using pattern matching and confidence scoring, with 12 built-in fixes and a learning loop for new patterns.

skylv-self-thinking-agent provides a structured metacognition loop for agents to assess confidence, detect cognitive biases, and flag uncertainty before output, with explicit confidence thresholds and bias categories.

tencent-survey covers form creation, editing, and response retrieval for the wj.qq.com platform. supports four scenario types (survey, exam, assessment, poll) with text-based dsl for programmatic operations. authentication via token or oauth device flow required.

skylv-error-monitoring-agent provides real-time error detection, smart grouping to reduce alert noise, and threshold-based alerting across logs and apis. lacks depth on implementation, error recovery, and failure modes.

secret-detector scans repositories for accidentally committed secrets using regex patterns for aws keys, github tokens, api keys, private keys, embedded passwords, and slack tokens. provides shell commands for linux/macos and windows but lacks automated execution flow.

skylv-data-pipeline-builder covers etl workflows via natural language, supporting extraction from databases and apis, transformation logic, and loading to multiple destinations. scheduling and monitoring included, but procedural depth and failure handling are limited.

skylv-automated-code-reviewer provides code analysis across bugs, security, and style enforcement with multi-language support. execution details remain vague, edge case handling absent, and failure modes undocumented.

skylv-universal-bot-maker generates telegram, discord, and wechat bots from a unified api. deployment covers docker and serverless. lacks error handling detail and production robustness guidance.

api-resilience-handler categorizes api errors across 8 types and applies retry strategies (exponential, linear, fibonacci) with configurable max attempts. integrates with a self-healing ecosystem but lacks explicit recovery procedures.

deployment-automation provides cli commands for multi-stage pipelines, blue-green/canary/rolling strategies, health checks, and rollback. lacks concrete procedural steps and failure mode detail.

self-thinking-agent provides a metacognition framework for ai agents to detect uncertainty, identify cognitive biases, and quantify confidence before responding, with explicit thresholds for escalation.

rate-limit-manager provides token bucket and sliding window algorithms for enforcing api quotas across multiple services with adaptive throttling and alert notifications.

skylv-secret-detector provides regex patterns and command-line examples for detecting common secret formats in code repositories, but lacks procedural depth and failure-mode handling.

skylv-intelligent-scheduler provides task scheduling with priority queues, timezone conversion, and conflict detection. implementation details are absent, procedure is cli-centric without actionable agent integration steps.

skylv-web-scraper extracts page content via css selectors and regex, supporting text, links, and image parsing. procedures are conversational examples rather than formal input-output contracts, and edge case handling is mentioned but not systematized.

rest-api-generator produces openapi 3.0 specs from code with basic template guidance. lacks actionable procedure steps and failure mode coverage for real-world api generation scenarios.

multi-persona-ai orchestrates voting across agent personas to compute consensus configurations. lacks concrete implementation detail and failure recovery patterns.

skylv-api-error-handler categorizes api failures across 8 error types and applies configurable retry strategies (exponential, linear, fibonacci, immediate) with logging and statistical tracking.

skylv-feature-toggle-manager provides scaffolding for feature flag creation and rollout stages, but lacks concrete api calls, state management details, and failure handling for production use.

openclaw-security-testing-agent offers code scanning across sql injection, xss, csrf, and dependency vulnerabilities with sample implementations, but lacks clear input/output contracts, error handling, and actionable procedural steps.

mcporter wraps the mcporter CLI for direct MCP server interaction, listing tools, configuring auth, and calling remote or stdio-based services via structured commands.

skylv-api-status-checker monitors endpoint health via http status codes and response latency buckets, with hardcoded thresholds for warnings and critical alerts. lacks dynamic endpoint configuration and recovery guidance.

skylv-system-health-watch provides real-time metrics on agent memory, api calls, and error rates via a command-line interface. lacks actionable procedures for interpreting results or responding to alerts.

multi-agent orchestrator provides typescript reference implementations for agent decomposition, dag-based task scheduling, and result aggregation, but lacks actionable procedural steps and handles few failure modes.

wecomcli-setup guides installation and initialization of the wecom-cli tool for enterprise wechat operations, then translates natural language requests into corresponding cli commands across contact, meeting, message, todo, schedule, and document domains.

fbs-bookwriter-skip wraps a node-based long-form writing workflow for books, manuals, and reports. it triggers on intent keywords and manages state via dotfiles, but procedure clarity is undermined by heavy reliance on external spec references and implicit assumptions about file discovery.

skylv-log-aggregation provides centralized log collection and search across services with parsing, filtering, and alerting. concrete command syntax is present but actual implementation details remain unspecified.

agent-team-coordinator provides typescript code for multi-agent orchestration including task decomposition, dag scheduling, and agent state management, but lacks concrete executable procedures and error handling specifics.

skylv-task-planner decomposes complex tasks into hierarchical steps, estimates timelines, and tracks progress. lacks formalized decision logic and failure mode handling.

skylv-secrets-scanner detects accidentally committed credentials across repositories using regex patterns for aws keys, github tokens, private keys, and other common secret formats. platform-specific grep and powershell commands provided.

prompt-optimization-tool describes a multi-dimensional prompt analysis and a/b testing framework with optimization techniques and template library, but lacks actionable procedure details, concrete api contracts, and failure mode handling.

skylv-sql-helper provides templated sql patterns and optimization heuristics for query writing and debugging, but lacks procedural depth and explicit failure handling.

skylv-github-actions-helper provides boilerplate yaml templates for node.js, python, and docker ci workflows but lacks procedural depth, error handling, and actionable customization guidance.

skylv-cost-guard tracks ai api spending across openai, anthropic, and google. provides budget alerts, provider cost comparison, and optimization suggestions based on token usage.

skylv-integration-testing-helper outlines test orchestration capabilities across services and databases, but lacks procedural depth and explicit failure handling needed for reliable execution.

skylv-git-commit-validator enforces conventional commits format by validating message structure, type declarations, and subject line constraints. lacks automation hooks and failure recovery logic.

fbs-bookwriter-hold provides node-driven long-form document authoring (books, whitepapers, reports) with intake routing, session resume, and s/p/c/b quality gates, but relies heavily on external references and assumes deep domain knowledge of internal state files.

intelligent-scheduler offers task scheduling, priority queuing, conflict detection, and timezone conversion via cli commands. lacks implementation detail, error handling specifics, and measurable outcome signals.

webhook-workflow-builder receives and routes incoming webhooks with payload transformation and retry logic, but lacks concrete procedural steps and failure mode documentation.

skylv-data-validator provides 17 built-in schema enforcement rules for json, csv, and excel data. schema inference and type checking are supported. actual integration steps and failure handling are not documented.

skylv-smart-renamer provides 12 configurable rules for batch file renaming with preview capability, but lacks actionable procedure steps, failure-mode documentation, and concrete usage examples.

skylv-cost-guard tracks ai api spending across openai, anthropic, and google with provider comparison and budget alerts, though execution details remain unclear.

skylv-cost-guard tracks token usage across openai, anthropic, and google models, supplies pricing tables, and compares provider costs. lacks concrete monitoring procedures and error handling.

skylv-openapi-generator produces openapi 3.0 specs from rest code with a template example, but lacks procedural depth and error handling guidance for real-world api generation scenarios.

wendao-partner-qclaw-skill routes travel queries to ctrip's question-answering api. it specifies token acquisition priority and response parsing rules but lacks actionable execution steps and failure recovery guidance.

chuangye guides entrepreneurs through startup fundamentals using a sequencing framework from a specific book. it diagnoses problem categories and poses reflective questions, but lacks concrete execution steps and failure mode handling.

skylv-schedule-interpreter documents cron syntax and common patterns but lacks procedural depth, decision logic, and failure handling needed for production parsing and validation.

skylv-github-badge-maker generates shields.io badges for readme files, offering color coding and style options but lacks actionable procedures or error handling guidance.

skylv-git-workflow-helper offers basic git operation guidance including conflict resolution and branch management, but lacks actionable procedures and edge case handling.

schedule-interpreter documents cron syntax and common patterns but lacks actionable procedures for parsing, validation logic, or error handling. reference material only, not executable skill definition.

hermes-agent-integration describes connecting openclaw to nous research hermes agent for self-improving ai capabilities, but lacks actionable step-by-step procedures, clear decision points, and explicit failure handling.

qclaw-rules documents mandatory system-level governance policies for ai behavior across file handling, encoding, tool invocation, and user data retention. structure is inconsistent; procedures are prescriptive but vague on failure recovery.

another-them automates agent persona creation by researching people, topics, or urls, then distilling findings into workspace files (SOUL.md, IDENTITY.md, AGENTS.md). five entry paths supported: explicit names, vague needs, links, existing skills, local corpus. delivery is silent research followed by first-person character introduction.

skylv-readme-badge generates shields.io badges for github readmes. the skill lacks actionable steps, decision logic, and failure handling. triggers are present but documentation is primarily reference material rather than executable procedure.

skylv-container-helper claims docker and dockerfile assistance but provides only Chinese-language usage examples without actionable procedures, failure modes, or decision logic.

当用户明确要求使用 AI 智能设计生成 PPT 演示文稿时使用本技能（智绘高迪/AIPPT）。本技能调用远程 Design Agent API，根据文字描述自动生成专业 PPT 演示文稿，支持指定模板和自定义模型。当用户说'AI生成PPT'、'智绘PPT'、'自动生成演示文稿'、'帮我做个PPT'时触发。注意：本...

当用户提到邮箱相关能力时，进入这个skill，统一邮件入口（纯路由层）：识别用户意图后路由到 public-skill 或 imap-smtp-email，自身不执行任何脚本

切换 agent 的人设（soul.md）。支持三套预设人设与原有人设之间自由切换。 触发词：切换人设、persona-switch、赛博朋友、温柔伴侣、创始人龙虾。

系统设计架构师。提供 20+ 种经典架构模式（电商/社交/直播/支付），包含架构图、技术选型、扩展性设计。Triggers: system design, architecture design, scalable system, distributed system, 系统设计.

OpenClaw 一键部署助手。5 分钟快速部署 OpenClaw 到 VPS/Docker/本地，包含环境检测、依赖安装、配置生成。Triggers: deploy openclaw, install openclaw, openclaw setup, quick start.

Real-time monitoring of agent memory, API calls, and errors

Evaluate AI agent behavior on accuracy, efficiency, clarity, safety, and helpfulness, providing scores, grades, and improvement suggestions.

Enables AI agents to reflect on their own reasoning, detect cognitive biases, and improve decision quality through structured self-examination loops.

Builds consensus-driven AI personas from multiple perspectives

内容创作助手。撰写各类文案、文章、报告。使用场景：(1) 撰写技术文档，(2) 创作营销文案，(3) 写作博客文章，(4) 生成报告总结。

数据分析助手。分析CSV、JSON等数据文件，生成统计报告、可视化图表。使用场景：(1) 分析数据分布和趋势，(2) 计算统计指标（均值、中位数、标准差），(3) 数据清洗和转换，(4) 生成数据报告。

错误调试助手。分析错误信息、定位问题原因、提供解决方案。使用场景：(1) 分析报错信息，(2) 定位代码问题，(3) 提供修复方案，(4) 预防类似错误。

市场调研：痛点自动挖掘分析。立项没方向？自动深挖市场痛点，一份报告帮你稳过评审 This skill should be used when the user asks about 市场调研：痛点自动挖掘分析. Keywords: 市场调研, 痛点分析, 竞品调研.

切换 agent 的人设 soul.md，支持三套预设角色与用户原有人设间自由切换并同步更新身份信息。

日程/日历/会议/安排管理 Skill。当用户提到任何日程相关话题时触发——包括但不限于：查看日程（'明天有什么安排'、'这周有什么会'）、创建日程（'帮我建个日程'、'约个会'、'三点开会'）、修改日程（'把会议推迟到后天'、'改个时间'）、取消日程（'取消明天的会'、'把那个会删了'）。也适用于间接意图如'帮...

Generates changelogs from git commit history using conventional commits. Triggers: generate changelog, release notes, changelog.

Validates git commit messages against conventional commits format. Triggers: commit lint, conventional commits, commit format.

Parses, validates, and explains cron expressions. Converts between human-readable and cron format. Triggers: parse cron, validate cron, cron expression.

Constitutional guardrails for AI agents — define immutable behavioral rules, permission boundaries, escalation policies, and safety interlocks that prevent a...

Toggle features instantly without deploying code. A/B test variants, gradual rollouts from 1% to 100%, and emergency kill switches for AI agents.

Feature flag management. Creates and toggles feature flags for A/B testing. Triggers: feature flag, a b test, toggle feature, abtesting.

Parses and summarizes log files. Extracts errors, warnings, patterns, and insights from server logs and debug output. Triggers: analyze logs, parse log file,...

Generates Mermaid diagrams from descriptions. Creates flowcharts, sequence diagrams, and architecture diagrams. Triggers: mermaid diagram, architecture diagr...

Generates OpenAPI 3.0 specs from code. Creates API documentation for REST endpoints. Triggers: openapi spec, generate api doc, swagger.

Auto-generates professional README.md from code structure, package.json, and directory analysis. Triggers: generate readme, create readme, readme from code,...

SQL query builder and optimizer. Generates queries, explains execution plans, and optimizes slow queries. Triggers: sql query, database query, sql optimization.

Tests and debugs webhooks. Inspects requests and validates responses. Triggers: test webhook, webhook debug, http webhook.

Automatically detects and repairs errors in AI agent workflows

Tracks and grows agent capabilities over time

Analyzes code for bugs, security risks, complexity, and style, providing detailed issues and actionable improvement suggestions.

Assist with Docker container management, image building, Dockerfile creation, and container network configuration.

Build, schedule, and monitor ETL pipelines to extract, transform, and load data across databases, APIs, and file systems with error handling and validation.

Feature flag management. Creates and toggles feature flags for A/B testing. Triggers: feature flag, a b test, toggle feature, abtesting.

Tracks file changes with git-like versioning for any project

GitHub Actions workflow generator. Creates CI/CD pipelines for Node.js, Python, Docker. Triggers: github actions, ci cd, workflow, automate build, github ci.

Validates git commit messages against conventional commits format. Triggers: commit lint, conventional commits, commit format.

Git Operations Assistant. Handle Git operations, resolve conflicts, manage branches. Triggers: Git, commit, merge, branch, pull request, conflict.

Generates GitHub README badges using shields.io. Triggers: add badge, shields io, readme badge, status badge.

Assist with creating, running, and managing integration tests for APIs, databases, and services, including orchestration, data setup, and reporting.

Automatically creates bidirectional links between related notes

Centralize, parse, search, and analyze logs from multiple sources with real-time alerts and visualizations for debugging and monitoring.

Generate customizable mock HTTP servers with dynamic data, delay, error simulation, and OpenAPI import for API testing and development.

OpenClaw Configuration Optimizer. Analyze and optimize OpenClaw config files for better performance and security. Triggers: optimize config, OpenClaw setting...

Deploy OpenClaw quickly to VPS, Docker, or local with auto environment detection, dependency installation, config generation, and service startup in 5-7 minu...

Generates changelogs from git commit history using conventional commits. Triggers: generate changelog, release notes, changelog.

Safely removes merged and stale Git branches. Identifies branches already on main/master. Triggers: clean branches, remove old branches, delete merged branch...

Automated code review for AI agents. Analyze pull requests, detect bugs, enforce coding standards, and suggest improvements. Triggers: code review, PR review...

Error monitoring and alerting for AI agents. Detect, track, and resolve errors in real-time. Triggers: error monitoring, error tracking, alerting, exception...

Provides expert SEO services including keyword research, content optimization, ranking tracking, technical audits, and competitor analysis using real data APIs.

Checks API health and uptime. Monitors endpoints and validates responses. Triggers: check api status, api health, monitor uptime.

Analyzes and scores OpenClaw skill quality across 5 dimensions. Detects missing frontmatter, weak descriptions, poor examples, and actionable improvement rec...

Constitutional guardrails for AI agents — define immutable behavioral rules, permission boundaries, escalation policies, and safety interlocks that prevent a...

Configuration management for AI agents. Manage, validate, version, and sync configs across environments. Triggers: config management, configuration, env vari...

Automatically detects and repairs errors in AI agent workflows

Provides 10+ production-grade AI Agent architecture templates with personas, tools, workflows, and metrics for immediate deployment in various roles.

Generates changelogs from git commit history using conventional commits. Triggers: generate changelog, release notes, changelog.

SQL query builder and optimizer. Generates queries, explains execution plans, and optimizes slow queries. Triggers: sql query, database query, sql optimization.

Toggle features instantly without deploying code. A/B test variants, gradual rollouts from 1% to 100%, and emergency kill switches for AI agents.

Tracks file changes with git-like versioning for any project

GitHub Actions workflow generator. Creates CI/CD pipelines for Node.js, Python, Docker. Triggers: github actions, ci cd, workflow, automate build, github ci.

Generate mock HTTP servers with custom endpoints, dynamic fake data, delay and error simulation, and OpenAPI import for API testing and development.

Builds consensus-driven AI personas from multiple perspectives

Automatically analyzes, A/B tests, and optimizes AI prompts to improve output quality, reduce token usage, and increase consistency.

Manage and enforce API rate limits and quotas with adaptive throttling, multi-service support, usage visualization, alerts, and smart retry logic.

Safely removes merged and stale Git branches. Identifies branches already on main/master. Triggers: clean branches, remove old branches, delete merged branch...

Provides professional SEO services including keyword research, content optimization, ranking tracking, technical SEO audit, and competitor analysis using rea...

Parses and summarizes log files. Extracts errors, warnings, patterns, and insights from server logs and debug output. Triggers: analyze logs, parse log file,...

193 AI Expert Agents for OpenClaw. Engineering, Design, Marketing, Product, and China Market specialists. Triggers: agency agents, AI experts, expert roles,...

Auto-generates unit tests and integration tests from source code. Supports Jest, Pytest, Mocha. Triggers: write tests, generate tests, unit test, test covera...

AI-driven browser automation for web scraping, form filling, and UI interactions using Playwright or Puppeteer libraries.

Tests and debugs webhooks. Inspects requests and validates responses. Triggers: test webhook, webhook debug, http webhook.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art...

腾讯音乐人宣推数据查询能力。当用户提到"我这些歌宣推情况如何"、"看一下宣推数据"、"这首歌宣推效果怎么样"、"我有哪些歌在投放"、"这首歌还要不要继续投"、"宣推诊断"、"宣推表现"、"投放效果"等与宣推数据查询相关的请求时触发。本 Skill 整合了两大子场景：① **宣推概览**——拉取当前登录用户名下所有...

智能文件/桌面整理技能。当用户 prompt 中包含"桌面整理"、"文件整理"、"整理桌面"、"整理文件"、"整理文件夹"、"清理桌面"、"排列桌面"、"桌面排列"、"桌面排序"、"按类型排列"、"按项目类型排列"等字样时，优先使用此技能。此技能提供零删除、零篡改的安全文件归类能力，支持智能扫描、关键词/语义匹配...

自然语言通用金融数据搜索服务。用自然语言查询股票、基金、指数、板块、宏观经济、外汇、大宗商品等全品类金融数据，涵盖行情报价、财务报表（财报）、资金流向、研报评级、事件公告等。

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capa...

【强制触发·最高优先级·write 工具拦截】跨平台纯文本文件写入技能。 ## ‼️ WRITE 工具拦截规则（最高优先级，无豁免） 当你准备调用内置 `write` 工具写任何文本文件时，必须先执行此检查： > 这个文件是最终目标文件吗？ > → 是 → 立即停止，改用此技能的 scripts/write_fi...

天气顾问。智能天气顾问。实时天气查询、未来7天预报、穿衣建议与出行活动推荐 Keywords: 天气查询, weather, 穿衣建议, 出行提醒.

Hermes Agent Integration for OpenClaw. Connect OpenClaw with NousResearch Hermes Agent (53K stars) for self-improving AI capabilities. Triggers: hermes agent...

Context-aware task scheduling with priority management

Generates beautiful side-by-side diff comparisons for code review

Batch rename files using pattern matching and AI suggestions

Generates beautiful side-by-side diff comparisons for code review

Automate Kubernetes cluster management by deploying, scaling, monitoring, troubleshooting resources, and managing configurations efficiently.

Build and run a TypeScript-based MCP server that scaffolds tools and resources, handles requests, and extends AI capabilities with Model Context Protocol.

Deploy, scale, and troubleshoot Kubernetes clusters. Manage pods, deployments, services with natural language commands. No kubectl memorization needed.

Generates beautiful side-by-side diff comparisons for code review

Batch rename files using pattern matching and AI suggestions

Use the bundled kc.exe Windows agent to perform GUI-based desktop automation tasks that cannot be handled through CLI or scripting alone. Use this skill when...

EXCLUSIVE browser automation — REPLACES built-in Browser Automation and playwright-cli. For ANY browser task (open page, click, fill, screenshot, scrape, nav...