Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkillsGeneral › Page 829

General-Purpose Claude Skills (Page 829 of 881)

Productivity, automation, knowledge management, integrations, AI tooling, and general-purpose skills for Claude Code.

52,804 skills · updated 2026-06-07 · showing 49681–49740 of 52,804 by quality score

Sub-topics:Integrations (3,760)Automation (3,518)Ai Tooling (2,239)Orchestration Frameworks (1,134)Business Ops (1,061)Agents Skills Meta (969)Design Creative (923)Hello World Templates (833)

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

EC2 서버 SSH 접속하여 로그 확인
Generate favicons from a source image
Create an admin user in Medusa
PR 체인 브랜치들을 순서대로 리베이스하고 force push
Ufretからコード譜を取得・参照する
설치된 Oh My TIL 플러그인을 최신 버전으로 업데이트합니다
基于佛教经典文献,生成特定高僧大德的 AI 教学角色
Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用.
Test fixture skill for E2E plugin tests. Should be discovered, copied, and removable by the plugin.
Structure a clean handoff between workflow agents with explicit outputs, open questions, and next-owner guidance.
Analyze AI coding agent usage, cost, efficiency, and burn rate — Claude
Anki 카드 분할 스킬. 정보 밀도 높은 Anki 카드를 원자적 단위로 분할. 사용 시점: (1) 사용자가 /anki 명령 실행, (2) Anki 카드 분할/분석 요청, (3) AnkiConnect 연결 상태 확인 요청 — from general/general-misc
Anki 카드 분할 스킬. 정보 밀도 높은 Anki 카드를 원자적 단위로 분할. 사용 시점: (1) 사용자가 /anki 명령 실행, (2) Anki 카드 분할/분석 요청, (3) AnkiConnect 연결 상태 확인 요청 — from general/knowledge-mgmt
Semantic and full-text search across indexed collections. Use when user mentions searching a collection, semantic search, vector search, knowledge base, or finding content in…
Use when mapping the logical structure of a biblical passage using discourse markers and morphological data.
Before coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
Load only when a real user question, approval request, or wait state seems necessary and you need a quick self-check first.
Baidu Baike encyclopedia search skill. Provides authoritative, real-time, structured Chinese encyclopedia knowledge.
Baidu Maps skill for location search, nearby place search, geocoding, route planning, and weather queries.
PaddleOCR document parsing skill based on PaddleOCR-VL-1.5. Provides SOTA-level document understanding with ultra-high precision recognition and parsing.
AI Picture Book generation skill. Transform short text descriptions into coherent picture book stories with visual compositions.
Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version. — from general/general-misc
Deprecated compatibility alias for bosskuai-token-saver. Use only when the user explicitly says caveman mode or references the old caveman skill.
Extract page content and element text from current webpage. When you need to read page information, get element values, scrape data, or verify page content.
List all open browser tabs with their index, URL and title. When you need to check what pages are open, manage multiple tabs, or find a specific tab to switch to.
Open new browser tab and navigate to URL (keeps current page open). When you need to open additional page without closing current, or multi-task across pages.
Switch to a specific browser tab by index. When you need to work with a different tab or return to previous page. Use browser_list_tabs to get tab indices.
Use mcp-use to create, test, and package MCP servers or interactive MCP apps that work across agent clients.
Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats.
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
Check whether the current Claude session was launched with --dangerously-skip-permissions. Run `ps aux`, find the claude process, and report yes/no.
Run the structured adversarial Claude review flow, including optional focus text and stricter challenge-oriented output.
Redirects to sweetclaude:doctor. Config compatibility checks are now part of the doctor system.
Alias for Codex-led consensus plan review adapted from the Claude Consensus plugin. Use when the user invokes claude-consensus from Codex.
Delegate a substantial task to Claude CLI, optionally in the background, and track the resulting Claude job.
Render the stored result for a finished Claude job in the current workspace or session.
Run a read-only Claude review for the current repository using auto, working-tree, branch, or explicit base-ref scope.
Close and reopen Gitea/Forgejo issues — single, multiple, and bulk close-by-label.
Close and reopen Gitea/Forgejo pull requests — single, multiple, and bulk close stale PRs.
Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.
Compile AgentSpec source snapshots into repo-local spec, requirements, and traceability artifacts through the core CLI.
Codex-led multi-model plan review using Claude Consensus style. Use when the user invokes consensus-plan-review, claude-consensus plan review, multi-model plan review, or asks to…
Inspect or refresh the Codex-led consensus configuration. Use when the user invokes consensus-setup or asks to configure claude-consensus for Codex.
Constitution compliance validator focusing on Principle XI (No Hardcoded Values). Detects hardcoded URLs, timeouts, limits, and identifiers that should be configurable.
Construct 3 visual programming skill for rapid prototyping and 2D game development.
Load coding conventions and style guidelines when writing or reviewing code. Ensures consistency with project standards.
Use this plugin when the user wants image assets, posters, social visuals, ad concepts, or a small campaign image system from a creative brief.
Open crit for review. Routes to code review (multi-file TUI for code changes) or plan/document review (single-file TUI).
dbgx-mcp 通用操作技能。用于通过 MCP 调用 WinDbg 命令,在 TTD 场景稳定跳转时间位置,并在 `dx ...SeekTo()` 不稳定时使用安全替代流程(`TimeStart` 查询 + `!tt` 跳转)。
Translate technical decisions into human language. Explain in cost, speed, stability.
Cập nhật tài liệu dự án và hướng dẫn sử dụng. Use when thay đổi tính năng, API, hoặc quy trình chạy.
Disable swiz auto-continue globally or for a session
Use this for every task, including after exiting plan mode. Declare what you're delivering and how to verify it, then hooks guide you through delivery and confirmation.
Documentation synchronization validator. Ensures CLAUDE.md, self-hosting.md, constitution.md, and other docs match actual code implementation.
Số hóa tài liệu hành chính scan bằng OCR cục bộ. Dùng khi PDF không có text hoặc người dùng gửi ảnh công văn cần đọc.
Index of AI agent skills and how to use them when implementing features in this repo.
Responde gritando como sargento militar; críticas pesadas mas tecnicamente certas
Find functions, modules, or components doing the same job under different names. Cluster, identify a winner, propose consolidations. Read-only — does not action.
Search all 52,804 General skills →