Skills directory · page 52

Plan-feature workflow phase 04 stub — orchestration phase planning (mock, Phase 3.3+ dogfood 时换真 gsd spawn)

Read a plan document, decompose it into steps, classify each step, and emit the ready-to-paste ECC slash command for that step, carrying the step identifier and scope in the command's own documented argument form. Generative only — never invokes commands itself and never claims to control what a command runs internally. Steps whose command cannot carry plan scope fail closed instead of being emitted. Use when the user has a multi-step plan and wants the right command for each step without picking it by hand.

Build the phase plan with GSD /gsd-plan-phase, then persist it to task_plan.md and progress.md.

Optional: produce the GSD threat-model contract before plan-phase when the change touches auth or secrets.

Optional: produce the GSD design contract before plan-phase when the phase requires a spec.

Optional: produce the GSD UI design contract before plan-phase when the change touches the UI.

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks. Use when setting up write-time formatting, linting, or auto-fix hooks on file edits.

Enforce code quality at writing time with Plankton: hooks automatically format, lint, and apply Claude-powered fixes on every file edit.

Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "start a research project", or when a task requires more than 5 tool calls and needs structured phase tracking to stay focused and avoid goal drift.

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Prosjekt-uavhengige Playwright E2E-regler: detekter prosjektets egne konvensjoner, rolle-baserte locators, auto-waiting, test-isolasjon, mocking og soft assertions. Use when: skriver eller endrer Playwright E2E-tester i et hvilket som helst prosjekt. Do NOT use for: enhetstester (Vitest/Jest), manuell testing, backend-tester.

Plan and build comprehensive Playwright E2E test suites with Page Object Model, authentication state persistence, custom fixtures, visual regression, and CI integration. Uses interview-driven planning to clarify critical user flows, auth strategy, test data approach, and parallelization before writing any tests.

Generate a Playwright test based on a scenario using Playwright MCP

Scaffold, write, debug, and enhance enterprise-grade Playwright E2E tests in Java using Page Object Model, JUnit 5, Allure reporting, and parallel execution.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly Express) and fine-grained customization (graph objects). Outputs interactive HTML or static images (PNG, PDF, SVG).

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.

Router for project-management skills: sprints, portfolio health, Jira, Confluence, stakeholder comms, plus a delivery loop. Use whenever a delivery request is unclear about which PM skill fits, or the user asks to run a delivery loop or pull Jira data into one.

Transform podcast episodes into compelling, SEO-optimized blog posts in a conversational voice. Creates narrative-driven explainers (~1,000 words) that weave guest expertise with real-world storytelling.

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

Complete workflow for producing podcast episodes from raw transcript to publishable YouTube and social media assets. Four-checkpoint system for strategic decision-making plus final polished assets.

Fast DataFrame library (Apache Arrow). Select, filter, group_by, joins, lazy evaluation, CSV/Parquet I/O, expression API, for high-performance data analysis workflows.

Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding explained in plain English. One-shot report, changes nothing. Use for "audit this codebase", "review the whole repo", "find bloat", "what can I delete", /ponytail-audit.

Use when creating or fixing a popup, modal, exit-intent, slide-in or banner meant to convert. Sets trigger, frequency, offer and copy rules that avoid hurting the page.

When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," or "overlay." For forms outside of popups, see form-cro. For general page conversion optimization, see page-cro.

Perform Porter's Five Forces analysis — competitive rivalry, supplier power, buyer power, threat of substitutes, and threat of new entrants. Use when analyzing industry dynamics, assessing competitive forces, or evaluating market attractiveness.

Transform resume bullets into detailed portfolio case studies with context, action, and outcome. Use when the user mentions portfolio, case study, project write-up, or expanding a resume bullet into a longer narrative.

Brainstorm product positioning ideas differentiated from competitors. Identifies top competitors and generates positioning statements with rationale. Use when developing product positioning, differentiating from competitors, or crafting brand positioning strategy.

Use for /c-level-agents:post-mortem, or when a decision hits its 90-day review or kill criteria. Scores it against the original assumptions and dissent.

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

Patrones de base de datos PostgreSQL para optimización de consultas, diseño de esquemas, indexación y seguridad. Basado en las buenas prácticas de Supabase.

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Quick reference for common patterns, index types, data types, and anti-pattern detection. Based on Supabase best practices.

쿼리 최적화, 스키마 설계, 인덱싱, 보안을 위한 PostgreSQL 데이터베이스 패턴. Supabase 모범 사례 기반.

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

Sorgu optimizasyonu, şema tasarımı, indeksleme ve güvenlik için PostgreSQL veritabanı kalıpları. Supabase en iyi uygulamalarına dayanır.

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices. Use when designing PostgreSQL schemas, indexes, or RLS policies, or when a query is too slow.

Comprehensive PostgreSQL-specific table design reference covering data types, indexing, constraints, performance patterns, and advanced features

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features