Prompts
Prompt engineering and templates
gepetto
by softaworks
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
daily-meeting-update
by softaworks
"Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update."
agent-md-refactor
by softaworks
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
plugin-forge
by softaworks
Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.
creating-skills
by fvadicamo
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context injection and subagent execution.
monitoring-observability
by yonatangross
Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse LLM tracing, and drift detection. Use when adding logging, metrics, distributed tracing, LLM cost tracking, or quality drift monitoring.
architecture-decision-record
by yonatangross
Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Use when writing ADRs, recording decisions, or evaluating options.
multimodal-llm
by yonatangross
Vision, audio, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, or building multimodal AI pipelines.
errors
by yonatangross
Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.
product-frameworks
by yonatangross
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.
llm-integration
by yonatangross
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
configure
by yonatangross
"Configures OrchestKit settings. Use when customizing MCP servers, plugin options, or preferences."
videocut-clip-oral
by zrt-ai-lab
口播视频转录和口误识别。生成审查稿和删除任务清单。触发词：剪口播、处理视频、识别口误
videocut-self-update
by zrt-ai-lab
自更新 skills。记录用户反馈，更新方法论和规则。触发词：更新规则、记录反馈、改进skill
videocut-clip
by zrt-ai-lab
执行视频剪辑。根据确认的删除任务执行FFmpeg剪辑，循环直到零口误，生成字幕。触发词：执行剪辑、开始剪、确认剪辑
videocut-subtitle
by zrt-ai-lab
字幕生成与烧录。转录→词典纠错→审核→烧录。触发词：加字幕、生成字幕、字幕
nav-diagnose
by alekspetrov
Detect quality drops in AI output and prompt re-anchoring. Auto-triggers after repeated corrections, context confusion, or when user says "something seems off", "you're not getting this".
frontend-component
by alekspetrov
Create React/Vue component with TypeScript, tests, and styles. Auto-invoke when user says "create component", "add component", "new component", or "build component".
nav-upgrade
by alekspetrov
Automates Navigator plugin updates. Detects current version, updates plugin, verifies installation, updates project CLAUDE.md, and validates new features. Auto-invoke when user mentions upgrading Navigator or getting new features.
picocom
by BrownFineSecurity
Use picocom to interact with IoT device UART consoles for pentesting operations including device enumeration, vulnerability discovery, bootloader manipulation, and gaining root shells. Use when the user needs to interact with embedded devices, IoT hardware, or serial consoles.
telnetshell
by BrownFineSecurity
Use telnet to interact with IoT device shells for pentesting operations including device enumeration, vulnerability discovery, credential testing, and post-exploitation. Use when the user needs to interact with network-accessible shells, IoT devices, or telnet services.
agentic-development
by alinaqi
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)
iterative-development
by alinaqi
Ralph Wiggum loops - self-referential TDD iteration until tests pass
llm-patterns
by alinaqi
AI-first application patterns, LLM testing, prompt management