Skills directory · page 22

Compatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

Render clean blueprint-style SVG diagrams from JSON specs. Use when users ask to draw, sketch, or diagram a request flow, neural net, transformer block, system architecture, state machine, data pipeline, or any node-and-edge technical visual they want as an SVG for docs, READMEs, posts, or slides.

Draws architecture and flow diagrams as code — Mermaid, C4, sequence, ER, and state diagrams that stay in version control and do not go stale. Use this whenever the user asks for a diagram, wants to visualise an architecture or flow, mentions Mermaid or C4, or is explaining a system that would be clearer drawn. For the prose around the diagram, use markdown-docs; for charts of quantitative data, use the dataviz guidance.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions.

Scaffold a directions lab that shows shipped UI (Today) beside 2-3 design directions, with surface tabs, theme and animation toggles and the V1 MVP hover motion, registered in design-proposals Storybook. Use for a directions page or lab, or to explore design directions next to production.

Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding.

Send structured tables and reports into Discord within its real limits: Components V2 payloads, monospace aligned tables, and the attachment fallback. Use when a plain Discord message would show raw pipes or truncate. Discord only — other platforms have their own rich-message systems.

Decide which clarification layers a piece of work needs, then run them in parallel — strategic, phase, and subtask are judged independently. Use it at the start of new work to settle scope before planning.

Optional: clarify a phase's gray areas with GSD and persist the outcome to findings.md, when a phase has two or more open implementation decisions, an unclear cross-phase contract, or a scope of more than a day.

Run the gstack strategic governance gates before starting a new feature, milestone, or product direction. Use it when the commercial scope or user value of the work is still unclear.

Optional: explore implementation options for a subtask with superpowers brainstorming, when the design has several viable approaches, touches a core algorithm or API contract, or is expensive to get wrong.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when independent tasks benefit from parallel work without shared state or sequential dependencies

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

The studio's Distribution Lead. Owns stage 7 for the studio-director, covering platform-correct exports, vertical and square versions, cut-downs and repurposed posts, a posting schedule, a publish checklist, the first-48-hours follow-up, and a lessons report that feeds the next video. Delivers a Distribution Handoff. Picks and runs reframe-social, yt-shorts, youtube-clip-extractor, social-content-creation, text-content, x-article-converter, x-posting, email-writing, yt-comment and yt-retention. Use when the director reaches export/publishing, or when the user asks to export for each platform, make shorts/reels from a video, repurpose, plan when to post, publish, or check how a video did, or says "صدّرلي الفيديو", "اعمل منه ريلز", "انشره", "امتى أنزّله", "الفيديو جاب كام".

Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding background jobs, scheduled tasks, or async processing to a Django app.

DjangoおよびCeleryを使用した非同期タスク処理。タスクキューイング、ワーカー管理、エラー処理、スケジューリング。Redis/RabbitMQ ブローカー統合。

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django applications.

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

Patrones de arquitectura Django, diseño de API REST con DRF, buenas prácticas de ORM, caché, señales, middleware y aplicaciones Django de nivel producción.

DRF ile Django mimari desenleri, REST API tasarımı, ORM en iyi uygulamaları, caching, signal'ler, middleware ve production-grade Django uygulamaları.

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps. Use when building or reviewing Django apps, DRF APIs, ORM queries, or caching.

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment.

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations. Use when reviewing Django authentication, authorization, input handling, or deployment settings.

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.

Django testing strategies covering pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.

Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs. Use when writing Django or DRF tests with pytest-django, or driving a Django feature test-first.

Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

Run the full Django verification loop — environment check, mypy/ruff/black linting, migration safety, pytest with coverage targets, pip-audit and bandit security scans, settings and logging review, and diff review — producing a phased pass/fail report before release or PR. Use when preparing a Django pull request, validating migrations or coverage, or running pre-deploy readiness checks.

Multi-agent orchestration using dmux, a tmux pane manager for AI agents. Parallel-agent workflow patterns across Claude Code, Codex, OpenCode, and other tools. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

複数のAIエージェントとタスク集約ワークフローを調整します。複数のワーカーで作業を分配し、エラーを処理し、結果をマージ。

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Two related workflows for a locally-cloned codebase, in one skill. Documentation mode produces a single, comprehensive, verifiable architecture document primarily by reading files on disk (local-first) — use it whenever the user wants to understand, map, document, research, or onboard onto a codebase ("research this repo", "write up the architecture", "do an architecture deep dive", "document how this codebase works", "map the system design", "create an onboarding doc"). Modernization mode generates a phased plan to modernize, migrate, upgrade, or rewrite a legacy system ("modernize this", "plan the migration", "how would we rewrite this", "how do we get off this legacy stack"); if no architecture document exists yet it first runs Documentation mode, then continues straight through to the plan. It assumes the legacy stack may be dead, runs a time-boxed feasibility spike, and picks the highest achievable rung on a safety ladder instead of demanding a fully-green legacy CI gate up front.

Free lite skill — drafts one friendly (level-1) client document-request email for a single tax client from a short brief plus the practice profile. A strict subset of client-doc-chaser (no batch, no escalation levels 2/3), carrying the pack's full guard. Use to try the kit before buying, or as the directory-published funnel skill. Triggers - "client document request email", "chase a client's documents", "free document request writer", "doc-chaser-lite".

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.