模板
项目与代码模板
stock-analyzer
AltenLi
全球股票综合分析工具。支持A股、港股、美股等东方财富覆盖的所有市场。根据用户输入的股票名称或代码，从东方财富网获取股票信息，进行基本面、新闻面、资金面三维分析，给出投资建议、买入价位和卖出价位。触发关键词：分析股票、股票推荐、股票买卖点、股票研究、A股分析、港股分析、美股分析、中概股、恒生指数、纳斯达克、标普500、道琼斯、腾讯、阿里巴巴、苹果AAPL、特斯拉TSLA、英伟达NVDA、美光MU等。
typo3-powermail
dirnbauer
Expert guidance on TYPO3 Powermail 13+ form extension. Creating forms, custom finishers, validators, spam protection, ViewHelpers, PSR-14 events, TypoScript configuration, email templates, backend modules, and extension development. Use when working with powermail forms, mail handling, form validation, or extending powermail functionality.
programmatic-seo
dirnbauer
When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," or "building many pages for SEO." For auditing existing SEO issues, see seo-audit.
email-writing
guia-matthieu
"Master email marketing from subject lines to sequences. Templates for welcome emails, nurture campaigns, sales emails, and newsletters that get opened, read, and clicked. Use when: Writing email subject lines that get opens; Creating welcome email sequences; Building nurture and sales sequences; Writing newsletters that engage; Re-engagement and win-back campaigns"
report-generator
guia-matthieu
"Generate PDF/HTML reports from templates and data. Use when: creating client reports; generating weekly summaries; producing marketing performance reports; automating recurring reports"
delegate-to-ollama
IsmaelMartinez
Use this skill to offload non-reasoning text work to locally-installed Ollama models via ollama run, keeping content on-device and freeing the main-agent context window. Saves API tokens too, though context protection and privacy are the headline values, not cost. MUST use whenever the user asks to summarise a log/diff/file/PR/issue, draft a commit message/changelog/release note, triage or classify many items, extract structured fields from free text, skim many files for a one-liner, rewrite or reformat prose, anonymise or redact text, convert between markup formats (YAML↔JSON, markdown→HTML), generate regex from description, or stub docstrings. MUST also use when the user mentions running locally, on-device, offline, saving tokens, privacy, Ollama, or a local model. MUST also use after the user sets durable auto-delegate intent ("delegate where it fits", "auto-delegate", "route to ollama as appropriate"), defaulting to delegating any subsequent matching task without re-confirming. Do NOT use for code correctness review, architectural decisions, debugging or tracing errors, implementing features, or any task whose output triggers a destructive or shared-state action without review. Do NOT use for open-ended "find anything interesting / suggest improvements" prompts that ask the model to surface things not in the input — those invite fabrication.
_template
tao3k
Template skill for creating new capabilities - demonstrates Trinity Architecture v4.0 with scripts/commands.py pattern.
Quality Gates Enforcement
hivellm
CLI tool to standardize AI-generated projects with templates, rules enforcement, and automation
ai-coding-ok
Mark7766
USE THIS SKILL FIRST on any coding task (feat, fix, bug, refactor, plan, design, brainstorm, code review, implement, add feature, write tests, 新功能, 修复, 重构) when the project contains .github/agent/memory/ or AGENTS.md. Loads three-tier project memory (project-memory, decisions-log, task-history) and AGENTS.md BEFORE writing code, then updates task-history (always), decisions-log (on architecture changes) and project-memory (on fact changes) AFTER finishing — the PDCA guardrail that prevents "AI fixed bug X and broke feature Y" across iterations. Also handles INSTALL when the user asks to "install ai-coding-ok", "set up project memory", "initialize AI guardrails", or the project has no .github/agent/memory/ yet — copy templates and customize placeholders. Also handles UPGRADE when the user says "upgrade ai-coding-ok", "update ai-coding-ok", "升级 ai-coding-ok", or "更新 ai-coding-ok" — diff project files against latest templates and apply framework-level changes while preserving project customizations.
rulebook_task_update
hivellm
CLI tool to standardize AI-generated projects with templates, rules enforcement, and automation
rulebook_skill_search
hivellm
CLI tool to standardize AI-generated projects with templates, rules enforcement, and automation
crawl4ai
tao3k
Use when crawling web pages, extracting markdown content, or scraping website data with intelligent chunking and skeleton planning. Use when the user provides a URL or link to fetch or crawl.
Git Workflow Standards
hivellm
CLI tool to standardize AI-generated projects with templates, rules enforcement, and automation
rulebook_task_archive
hivellm
CLI tool to standardize AI-generated projects with templates, rules enforcement, and automation
Rulebook Task Management
hivellm
CLI tool to standardize AI-generated projects with templates, rules enforcement, and automation
Base Template Generator (Gold Tier)
DNYoussef
Context Cascade - Nested Plugin Architecture for Claude Code Official Claude Code Plugin Version 3.1.0 Last updated: 2026-01-09 (see docs/COMPONENT-COUNTS.json for source counts) Context-saving nested architecture: Playbooks -> Skills -> Agents -> Commands. Load only what you need, saving 90%+ context space.
brand-messaging-architecture
manojbajaj95
Provides brand messaging architecture, value proposition, and brand pillar development frameworks including Peep Laja's Message Layers, Osterwalder's Value Proposition Canvas, Geoffrey Moore positioning template, April Dunford's Five Components, StoryBrand SB7, Andy Raskin's Strategic Narrative, the Messaging House, and MECLABS quality tests. Auto-activates during messaging framework development, value proposition creation, and brand pillar definition. Use when discussing messaging architecture, value proposition, brand pillars, message layers, messaging house, messaging hierarchy, elevator pitch, Peep Laja, Geoffrey Moore, April Dunford, StoryBrand, Andy Raskin, or MECLABS.
bd-email
manojbajaj95
Craft Business Development emails for RYLLC fractional CTO consultancy. Handles warm reconnects, job posting outreach, rejection follow-ups, VC intros, and custom BD scenarios. Uses established templates and project voice.
design-documentation
jasonkneen
Transform approved requirements into comprehensive technical designs. Define system architecture, component interactions, data models, and interfaces to create a blueprint for implementation.
cold-outreach-generator
manojbajaj95
Generate cold email templates, LinkedIn messages, follow-up sequences, and value propositions tailored to specific industries that actually get responses and book discovery calls.
dev-planner
cat9999aaa
🚀 超级开发规划师 —— 对话式需求收集 + Agent 团队并行开发 + MCP 工具全程调用。 触发时机：用户说"帮我开发"、"我想做一个项目/网站/APP/系统/工具/脚本/Bot"、"plan模式"、 "对话式开发"、"生成开发文档"、"我有个想法想实现"，或任何描述了软件/工具/系统需求的请求。 即使需求模糊如"我想做个东西"也要触发。核心能力：(1) 引导小白用户通过选项对话完善需求， (2) 生成企业级超详细开发文档，(3) 编排 Agent 团队+MCP 工具并行开发，(4) 全程文档驱动、节点测试、自动提交。
new-feature
camalus
Create a complete feature artifact scaffold — PRD slice, technical spec, and task breakdown. Use when starting work on any new feature, user story, or capability. Triggers on phrases like 'new feature', 'create a PRD for', 'start work on', 'scaffold a feature'.
clearshot
udayanwalvekar
"Structured screenshot analysis for UI implementation and critique. Analyzes every UI screenshot with a 5×5 spatial grid, full element inventory, and design system extraction — facts and taste together, every time. Escalates to full implementation blueprint when building. Trigger on any digital interface image file (png, jpg, gif, webp — websites, apps, dashboards, mockups, wireframes) or commands like 'analyse this screenshot,' 'rebuild this,' 'match this design,' 'clone this.' Skip for non-UI images (photos, memes, charts) unless the user explicitly wants to build a UI from them. Does NOT trigger on HTML source code, CSS, SVGs, or any code pasted as text."
robotframework-testcase-builder
manykarim
Generate Robot Framework test cases from structured requirements or scenarios. Use when asked to create test cases, apply tags/setup/teardown/templates, or produce keyword-driven tests.