83,201 skills sorted by stars.
[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absol...
To maintain the integrity of audit logs, we must ensure that agents use their real identities in worklogs, rather than blindly cop...
Setting up a new repo still requires manual folder creation and tool wrapper
2026-01-16 16:07 [agent=codex] [model=unknown] Created item
We want a local-first backlog system so the demo can show planning before coding
2026-01-06 12:00 [agent=codex-cli] Create/init backlog scaffold, default config, and optionally write agent guide files (AGENTS.md...
Standardizing commit messages is critical for traceability and automation in multi-agent/multi-developer projects.
/esper:build is the primary implementation skill but has no recovery path when a session is interrupted mid-implementation. A espe...
The current workflow requires manual intervention between each plan: run /esper:build, then /esper:commit, then /esper:ship, then...
Currently the esper workflow has two commit-related commands:
Use when you need to generate a checklist document with Java system prompts, following the embedded template exactly and producing...
Use when you need to generate a checklist document with embedded agents inventory, following the embedded template exactly and pro...
Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination int...
esper currently has no skill for reviewing code before shipping. The /esper:ship skill pushes and opens a PR, but there is no stru...
Plan files, phase files, and fix documents are the backbone of the esper workflow — they define what gets built and how. Currently...
The current esper workflow goes straight from idea to plan (/esper:plan or /esper:fix). There is no structured way to investigate...
Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infras...
专门用于在项目初期或重大功能迭代时进行技术栈选择与方案评估。支持根据 PRD 自动生成 2-3 套对比方案，涵盖前端、后端、数据库及中间件，并提供优劣势分析（性能、SEO、开发成本、可维护性）和最终选型建议。
专用于在 GitHub 上搜索现有的开源库、工具、MCP Server 或最佳实践代码。当你想在开始开发前查找是否有“现成的轮子”或参考案例时使用。
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior....
[01] META. Сканирует доступные skills, создает план выполнения и идет шаг за шагом с подтверждением каждого этапа. Triggers on com...
> 도메인: devian-upm-samples
- SceneSingleton\<T\> - Scene-Placed / Persistent (자동 생성 없음)
The skill is script-heavy and evolving fast. When Python dependencies are missing, agents currently discover failures late (mid-co...
Guides the creation of agile epics with comprehensive definition including business value, success criteria, and breakdown into us...
Guides the creation of detailed agile feature documentation from an existing epic. Use when the user wants to split an epic into f...
Guides the creation of agile user stories and Gherkin feature files. Use when the user wants to create a user story, write accepta...
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use whe...
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web...
UI/UX 设计智能库与推荐专家。包含 67 种风格、96 种配色方案、57 种字体搭配、99 条 UX 指南，支持跨技术栈的设计系统生成。
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "...
[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Resear...
Generate API documentation from code. Use when the user wants to document APIs, create API reference, generate endpoint documentat...
Facilitates conversational discovery to create Architectural Decision Records (ADRs) for CLI development. Use when the user wants...
Use when creating a plan using Plan model and enhancing structured design plans in Cursor Plan mode for Java implementations. Use...
Need a consistent conflict-resolution policy for duplicate IDs/UIDs across agents and tooling.
Current guidance allows tasks to proliferate without clear Epic/UserStory boundaries. We need explicit criteria in SKILL.md.
Facilitates conversational discovery to create Architectural Decision Records (ADRs) for REST API development. Use when the user w...
Use when you need the GitHub CLI (`gh`) to verify installation, list issues (all or by milestone) as markdown tables, fetch issue...
Use when you need the Jira CLI (`jira`) to verify installation, configure Jira Cloud access, list issues (all or by JQL) as markdo...
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tai...
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing,...
专注于构建高性能、可扩展且架构清晰的 Flutter 应用。涵盖整洁架构、高级状态管理和深度性能优化。
Capture learnings, patterns, or workflows from the current conversation into a new or existing skill. Use when the user wants to s...
Analyze financial data, calculate financial ratios, and generate analysis reports. Use when the user asks about revenue, costs, pr...
На втором этапе необходимо добиться систематичности в
ParentSSOT: skills/devian-core/03-ssot/SKILL.md