В каталоге 182 820 навыков в 14 категориях.
Product Manager Skills Pack - Full lifecycle support from demand to delivery 让一个产品经理拥有一个产品团队的能力 Use when: Starting a new...
Use when: 用户要求检查 super-pm 更新、升级完整 Git 安装或回退 Do NOT use when: 正在执行普通 PM 任务、仅需安装健康检查或用户没有要求升级
Complete Product Owner / Product Manager capability — a wiki-style knowledge map of product practice in active software...
Super QA canonical workflow for functional bug-bash, evidence capture, and fix-ready issue filing. Crawls routes from `d...
Super Ralph Wiggum - autonomous iteration loops with templates, PRD support, progress tracking, and browser testing. Thi...
Run a mixture-of-agents style deep research workflow — decompose a question, fan out parallel searches, cross-verify cla...
Reviewer lane of the super-board pipeline and standalone PR/branch readiness review — forms its own hypotheses before re...
Use when user requests code review with multiple perspectives, wants parallel review from different models, or uses trig...
Maximum visual excellence for any UI platform. Use when building user interfaces, styling components, or polishing visua...
搜索您的编码记忆。当用户询问过去的工作、以前的会话、某些内容是如何实现的、他们之前做过什么，或者想要召回以前会话中的信息时使用。
The bulletproof ship for structural work. Run the full drift audit, fix the broken and stale findings, then ship the com...
Apply the combined rigor + delegation framework for complex tasks. Two operating modes: (1) **Rigor mode** — use the GPT...
Only to be triggered by explicit super-swarm-spark commands.
Complete UI/UX design capability — a wiki-style knowledge map of design theory (UX laws, Nielsen heuristics, usability,...
Set up Superagent Context Guardrails at coding-agent tool boundaries, configure and safely use the remote MCP server, an...
Train and use SuperBPE tokenizers for 20-33% token reduction across any project. Covers training, optimization, validati...
Use when executing implementation plans phase-by-phase with strict enforcement of quality gates, tests, and Definition o...
Automate Superchat tasks via Rube MCP (Composio). Always search tools first for current schemas.
Configure and operate the Claude Code harness for large codebases. Builds CLAUDE.md hierarchies, scoped test/lint comman...
SuperClaude 增强层 Skill，为其他 Skills 提供 SuperClaude 能力增强。 支持前置分析、后置审查、智能建议等增强模式。
Provides flag definitions and usage rules when double-dash flags (--flag-name) detected in user prompt - describes execu...
Codex compatibility layer for SuperClaude /sc:* commands with vibe-adapted routing.
Provides software engineering principles and decision frameworks when architectural guidance keywords detected (SOLID, p...
Expert SuperClaude prompt engineering assistant that analyzes user needs and crafts optimal prompts using the full Super...
Behavioral rules when development keywords detected (implement, build, fix, test, commit) - covers workflow patterns, qu...
SuperCLI capability router — discover and execute CLI commands through namespace.resource.action interface
Diagnoses which capabilities are ready or blocked, sets up the keys, then sets up the brand from its website. Use when t...
Measure line, branch and MC/DC coverage of a project's existing tests with the supercov CLI, then write small, focused t...
Measures test coverage and code quality in a repository with the supercov CLI, and turns what it finds into small, focus...
Scans a repository's source for security vulnerabilities with the supercov CLI, pointing to the line of each finding and...
Use when the user wants to start tracking a local custom instruction file (like .agy/ANTIGRAVITY.md or .github/copilot-i...
Use when the user wants to set up, check, repair, or report the SuperCtx state for this repository. Consolidated command...
Superdesign is a design agent, where it specialised in frontend UI/UX design; Use this skill before you implement any UI...
Expert frontend design guidelines for creating beautiful, modern UIs. Use when building landing pages, dashboards, or an...
Superdesign is a design agent specialized in frontend UI/UX design. Use this skill before implementing any UI that requi...
Design or redesign frontend UI on the Superdesign canvas. Use whenever the user wants to design a page, feature, flow, o...
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models...
Guides users through superdev setup, /superdev-mode, and picking the skill, playbook, or principle for a task. Type /sup...
superdev's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified...
Configure a repository for SuperDev with its issue tracker, triage labels, Wayfinder setup, domain docs, per-role models...
Superdisco MoAI fork management - track customizations, sync upstream updates while preserving your changes
Metacognitive oversight. Invoke with "$superego" to evaluate, "$superego init" to set up, "$superego remove" to uninstal...
Provides specialized functionality for writing and managing Super Factory Manager (SFM) scripts for Minecraft, including...
Make well-calibrated probability estimates using superforecasting methodology. Use when user asks about probability, lik...
Route objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation thr...
Meta-orchestrator — dispatches to the right skill for the task. Use before any non-trivial work.
AI-native software development lifecycle that replaces traditional SDLC. Triggers on "plan and build", "break this into...
Run a superRA task tree autonomously through dispatched implementer and reviewer seats. Requires superRA:using-superra....
Integrate code-complete superRA work. Requires superRA:using-superra. Use for result protection, base sync, codebase-fit...
Use when a user wants to start trading with Superior Trade and does not have everything set up yet — getting an API key,...
Use when an agent needs to register a Superior Trade account, verify an email OTP, configure x-api-key authentication, o...
Use only after explicit Codex `$superloopy:superloopy-backend` or Claude Code `/superloopy:superloopy-backend` invocatio...
Use when the user asks for Superloopy clone or asks to clone, rebuild, reverse-engineer, replicate, or copy a website or...
Use when diagnosing Superloopy doctor, install, wrapper, plugin cache, hook bootstrap, bundled agents, marketplace, Code...
Use only after explicit Codex `$superloopy:superloopy-frontend` or Claude Code `/superloopy:superloopy-frontend` invocat...
Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-bac...
Use only after explicit Codex `$superloopy:superloopy-research` or Claude Code `/superloopy:superloopy-research` invocat...
Use when the user asks to create, convert, style, animate, export, share, or deploy HTML slide decks, presentations, pit...
Official SuperMemory adapter for the trading lab. Bearer SUPERMEMORY_API_KEY, POST /v3/documents, POST /v4/search, singu...
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applicat...
Every SuperOps PSA+RMM entity in your terminal, plus a local SQLite mirror that answers cross-entity questions the web U...
Use when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with paralleli...
Proactively plan or update superRA work. Requires superRA:using-superra. Use when starting or changing work, creating/re...
Identify your core leadership strengths and reframe your perceived weaknesses using story-driven analysis. Use this when...
Use when creating Zustand stores — MANDATORY. Do NOT create stores without this skill. All stores must use the required...
MANDATORY for creating Zustand stores. This skill is required when users request state management, creating stores, or m...
Comprehensive skill framework from obra/superpowers for AI-assisted development workflows, covering planning, implementa...
Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers...
Use when asked to "autoplan", "run the review pipeline", "full review", "review my plan", "check everything", "multi-rev...
Bootstrap skill - Loads Superpowers SDLC workflow into every session
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying...
Use before writing any code, scaffolding, or taking implementation action — explore intent, requirements, and design thr...
Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures. Take...
OpenAI Codex CLI wrapper — three modes. Review: independent diff review with pass/fail gate. Challenge: adversarial mode...
Getting Skills Together to Learn from the Best
Dispatch to the right problem-solving technique based on how you're stuck
Use when asked to "run a security audit", "security review", "check for vulnerabilities", "OWASP review", "threat model"...
Design audit tool that crawls a live site, screenshots every page, runs a 10-category checklist (including AI slop detec...
Use when multiple independent problems exist and sequential investigation would waste time — dispatch one specialized ag...
Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUT...
Software development methodology workflow assistant (Superpowers). Trigger when users mention "brainstorming", "requirem...
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when executing a written implementation plan in the current session — load the plan, execute tasks in sequence with...
统一开发编排器：将 Superpowers 方法论框架与 AI 代码工厂深度整合， 创建统一的开发工作流，结合 TDD 纪律、SoT 合规和自动化代码生成。
Use when all tasks in a plan are complete — run the full ship pipeline from code to merged PR: detect base branch, verif...
Use when the user wants maximum safety — "guard mode", "full safety", "lock it down", "protect this", "maximum safety",...
Lab environment for Claude superpowers
Experimental Claude Code skills extending capabilities with new techniques for interactive CLI tools, tmux automation, a...
Use when asked to "land and deploy", "merge and ship", "deploy this PR", "merge to production", "ship to prod", or after...
Use when the user wants to explore a product idea, validate a concept, get clarity on what to build, or get unstuck on a...
Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", "is this ambitious enough", "CEO re...
Designer's eye plan review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to g...
Engineering plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, perf...
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, scree...