⌘ K
Newest skills
455 skills
codex-huge-context
Codex 1M context: direct OpenAI Responses API inference, safe Astra/Sol/Terra/Luna input headroom, Keychain delivery, and Mac fleet rollout.
workflow-run
Run a workflow — drive an MCP workflow lifecycle (execute/pause/resume/cancel) or invoke + resume a native .claude/workflows/*.js orchestration via the Workflow tool
winui-session-report
Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.
x-posting-license
Turn any X (Twitter) profile into a 10.3s animated "POSTING LICENSE" card video — a fake driver's license in X's branding: the card slides in over an animated dot-matrix ground, license text types on letter-by-letter, follower / following / post counters tick up, a diagonal glimmer sweeps as the card tilts in 3D, it flips to a fine-print back with a signature write-on, then crouches and leaps out of frame. Trigger on: "X driver's license", "posting license", "make an X license for @handle", "license card video". The whole composition is a finished template — the agent only supplies profile dat
build-zoom-virtual-agent
Reference skill for Zoom Virtual Agent. Use after routing to a virtual-agent workflow when implementing web embeds, Android or iOS wrapper integrations, knowledge-base sync, lifecycle handling, or troubleshooting.
lora-qlora-recipes
Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training configuration, choosing rank/alpha/target modules, or deciding between LoRA, QLoRA, and full fine-tuning.
codex-first
Claude Code work routing: delegate implementation, fixing, exploratory subagents, rebasing, and PR merging/landing to GPT-6 Astra through Codex CLI while the parent specifies, decides, reviews, and verifies. Apply the native-Claude model gate. Codex-backed autoreview is always allowed and preferred.
workflow-create
Author a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration script (agent/parallel/pipeline fan-out)
waza
**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison. DO NOT USE FOR: improving skill frontmatter (use waza dev), creating new skills from scratch (use skill-creator), token counting or budget checks (use waza tokens). INVOKES: Copilot SDK executor, mock engine, code/regex validators. FOR SINGLE OPERATIONS: use waz
duo
Composite any two HTML screens into a locked photo plate of hands holding an open foldable phone — a 1448×1086 still with two blank 495×849 / 498×849 screen slots (left and right) — to make side-by-side meme and comparison videos: TikTok vs Reels, ChatGPT vs Claude, "me vs my friend", before/after, two apps racing. Trigger on: "foldable phone meme", "put X on the left screen and Y on the right", "two-screen comparison video", "the dual-screen phone meme", or any request that names two apps/feeds/chats to show at once. The plate, geometry, and camera are finished — the agent only authors what p
setup-zoom-mcp
Decide when Zoom MCP is the right fit and produce a safe setup plan for Claude. Use when planning AI workflows over Zoom data, deciding between MCP and REST, or defining a hybrid MCP architecture.
finetuning-method-selection
Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.
devtools
Drop-in inspector panel for any json-render app. Use when the user wants to debug a generative UI, inspect the spec tree, edit state at runtime, see dispatched actions, follow stream patches live, browse a catalog, or pick DOM elements to find their spec keys. Triggers include "add devtools", "debug json-render", "inspect the spec", "why is this element not rendering", "see the state at runtime", or requests to tap streams / capture action logs for `@json-render/devtools`.
tdd-repair
Test-Driven Repair — given a failing test, spawn a bounded headless `claude -p` (Read/Edit/Bash only) that makes the test pass without modifying it. Modeled on agent-harness-generator's ADR-175 Test-Driven Repair mode. Bounded cost via --max-budget-usd, bounded capability via --allowedTools. Closes the loop the TDD plugins didn't — we generate tests, this fixes the code to satisfy them.
waza-interactive
Interactive workflow partner for creating, testing, and improving AI agent skills with waza. USE FOR: run my evals, check my skill, compare models, create eval suite, debug failing tests, is my skill ready, ship readiness, interpret results, improve score. DO NOT USE FOR: general coding, non-skill work, writing skill content (use skill-authoring), improving frontmatter only (use sensei).
heygen-cli
Create AI videos, manage avatars, translate videos, and download results via the HeyGen API. Use when an agent needs to generate videos from text prompts, create avatar-based videos, translate existing videos, or automate video production workflows.
design-mcp-workflow
Design a Zoom MCP workflow for Claude. Use when deciding whether Zoom MCP fits a task, when planning tool-based AI workflows, or when separating MCP responsibilities from REST API responsibilities.
eval-harness-first
Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.