Prompts
Prompt engineering and templates
code-review-claude-skills
by Jamie-BitFlight
Loaded automatically when reviewing Claude skills or agent definitions — covers SKILL.md structure, frontmatter validity, token budget, description quality, and agent contract compliance.
code-review-llm
by Jamie-BitFlight
Use when reviewing AI/ML code or LLM integration — activates on prompt templates, model selection logic, token budget concerns, or evaluation harness code. Enforces prompt hygiene, model tier matching, context window management, token economics, structured output validation, temperature settings, retry logic, streaming error handling, and PII/safety rules.
angular-directives
by analogjs
Create custom directives in Angular v20+ for DOM manipulation and behavior extension. Use for attribute directives that modify element behavior/appearance, structural directives for portals/overlays, and host directives for composition. Triggers on creating reusable DOM behaviors, extending element functionality, or composing behaviors across components. Note - use native @if/@for/@switch for control flow, not custom structural directives.
mob-programming
by gzhanlei
组建 Pair/Mob Programming 团队进行代码开发。根据用户需求智能选择团队配置： - Pair 模式（2人）：Cunningham（测试）+ Thompson（实现），内部遵循 TDD 规范 - Pair 审查模式（2人）：Jobs（Navigator）+ Thompson（Driver），内部遵循 SOLID 原则 - Pair 覆盖率模式（2人）：Cunningham（Navigator）+ Thompson（Driver），提升测试覆盖率 - Mob 三人模式（3人）：Cunningham + Jobs + Thompson，完整双重审查流程 触发场景： - "pair programming" / "结对编程" / "结对" → 询问选择 Pair 模式 - "mob programming" / "团队编程" → 启动三人模式 - "代码审查" / "帮我重构" → Pair 审查模式 - "提升测试覆盖率" / "测试覆盖率" → Pair 覆盖率模式（Navigator + Driver） - 提到 "Cunningham/Jobs/Thompson" → 按指定角色启动
design-trends-2026
by guia-matthieu
"Apply 2026's top graphic design trends to any creative brief. Based on Kittl × Savee's 2026 Design Trends Report (10 trends + 2 honorable mentions), backed by Adobe, Figma, and Pinterest data. Use when: Designing a brand identity — pick the right aesthetic for your audience; Creating social media assets — use trending visual languages that perform; Briefing a designer or AI image tool — give precise style direction with vocabulary and references; Refreshing a visual identity — know what's rising vs saturating; Building mood boards — combine trends intentionally with data-backed rationale."
podcast-production
by guia-matthieu
"Master Ira Glass's narrative storytelling methodology from This American Life to create podcasts that captivate listeners through the power of story. Use when: Creating a branded podcast or audio content series; Structuring episodes for maximum listener engagement; Transforming raw interviews into compelling narratives; Building thought leadership through audio storytelling; Planning podcast content that keeps audiences coming back"
skill-writer
by metalagman
Use this skill to design, document, and structure AI agent skills for Gemini, Claude, and Codex. It provides architectural rules, directory standards, and writing best practices.
docker-sandbox
by joelhooks
Create, manage, and execute agent tools (claude, codex) inside Docker sandboxes for isolated code execution. Use when running agent loops, spawning tool subprocesses, or any task requiring process isolation. Triggers on "sandbox", "isolated execution", "docker sandbox", "safe agent execution", or when working on agent loop infrastructure.
preencher-formulario
by dspinillo
EXPERIMENTAL. Preenche no navegador o formulário de candidatura de uma vaga do Radar a partir da folha de respostas, pelo Claude in Chrome, e para antes do envio.
claude-hooks-configuration
by laurigates
Set up Claude Code lifecycle hooks and event handlers in settings.json. Use when you want to trigger a script on session start, run a hook before or after tool calls (PreToolUse/PostToolUse), configure hook timeouts to prevent cancellation errors, or debug hooks that aren't firing correctly.
ai-ready
by viktor-silakov
Analyzes repositories for AI agent development efficiency. Scores 8 aspects (documentation, architecture, testing, type safety, agent instructions, file structure, context optimization, security) with ASCII dashboards. Use when evaluating AI-readiness, preparing codebases for Claude Code, or improving repository structure for AI-assisted development.
blueprint-promote
by laurigates
"Move generated artifact to custom layer to preserve modifications"
blueprint-generate-rules
by laurigates
"Generate project-specific rules from PRDs. Supports path-specific rules with paths frontmatter and brace expansion."
meta-assimilate
by laurigates
Analyze and assimilate project-specific Claude configurations
blueprint-init
by laurigates
"Initialize Blueprint Development structure in current project"
blueprint-status
by laurigates
"Show blueprint version, configuration, and check for available upgrades"
blueprint-upgrade
by laurigates
"Upgrade blueprint structure to the latest format version"
blueprint-claude-md
by laurigates
"Generate or update CLAUDE.md from project context and blueprint artifacts. Supports @import syntax, CLAUDE.local.md, and auto memory delineation."
prd
by leodearden
"Author and decompose PRDs under implementation-chain-completeness gates that prevent incomplete/ill-formed work from reaching the orchestrator. ALWAYS use this skill for: /prd commands, authoring a new PRD, decomposing a committed PRD into tasks, queueing tasks from a PRD into the orchestrator. Triggers on requests like 'let's write a PRD for X', 'draft a PRD', 'decompose this PRD', 'queue tasks from <prd>.md', or any mention of starting/finishing PRD-shaped work. Walks G1 (consumer named), G2 (user-observable leaf signal), G3 (assumed-substrate verified), G4 (cross-PRD seam ownership), G5 (design-first when stakes are high), G6 (premise validity), and the meta-gate 'would this PRD produce a complete/coherent/cohesive/good design under decompose-and-queue without further oversight?' before saving or queueing. Adapts to the current project via an optional overlay at .claude/skills/prd/project.md. This is NOT for: editing existing PRDs without re-running gates, running tasks (use /orchestrate), reviewing landed code (use /review), unblocking tasks (use /unblock)."
continuous-learning-v2
by JochenYang
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
jochen-skill-creator
by JochenYang
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 capabilities with specialized knowledge, workflows, or tool integrations.
ux-flow-designer
by ThomasPraun
"Design and document app user flows, screens, and use cases using Mermaid diagrams and HTML wireframes. Use when creating user flow diagrams (flowcharts, state diagrams, sequence diagrams), screen wireframes (HTML), use case documentation, screen maps, or when the user mentions 'flows', 'wireframes', 'user journey', 'screen map', 'navigation flow', 'use cases', 'app flow', 'screen layout', 'flujos', 'pantallas', 'casos de uso'. Bridges Product (PRD) and Visual Design phases. Outputs serve as input for ui-ux-pro-max. Optional Figma export when user explicitly requests it."
b2c-isml
by SalesforceCommerceCloud
Work with ISML templates in B2C Commerce. Use when writing storefront templates, using isprint/isset/isloop tags, understanding ISML expressions (${...}), or creating custom template modules. Covers tag syntax, expression language, and template includes.
migrate-to-skills
by kasperjunge
Convert legacy subagents, slash commands, and rules to the unified Agent Skills format. Use when migrating agent resources, consolidating legacy directories, or standardizing across Claude Code, Cursor, Copilot, Codex, and Open Code.