Agent Skills

---

name: et-test-write

description: ET test authoring workflow for WOW. Use when writing or modifying ATestHandler tests, choosing test package placement, naming test classes, creating test-only model types, preparing deterministic coroutine-style assertions, handling ObjectWait, constructing test config data, and enforcing EntityRef safety in tests.

---

name: et-unitybridge

description: UnityBridge workflow for AI operations in Unity Editor. Use when checking UnityBridge connectivity, Unity compile or PlayMode state, running deferred UnityBridge commands, operating assets/scenes/GameObjects/Inspector/Prefabs/GameView/screenshots, running Editor tests, or troubleshooting UnityBridge responses.

---

name: develop-timeline-studio-plugin

description: Design, evaluate, implement, or review image and video generation connectors for Timeline Studio. Use when adding a provider plugin, extracting the generation plugin host or registry, or checking a connector against Timeline Studio's authentication, output, localization, and My assets contract. Do not use for ordinary video editing or Codex plugin packaging.

---

name: edit-timeline-studio

description: Analyze images, video, speech, motion, products, and websites; route local vision, audio, depth, tracking, matting, identity, and restoration models; auto-edit, replicate, enhance, caption, voice, assemble, annotate, validate, and export editable Timeline Studio projects and videos. Use for reference-video remakes, filter and repeated-shot reconstruction, subject-aware reframing, clip splitting, source-time speed curves, Color Wheels grading, ramps and holds, person or product cutout, person or object outline, authorized face swap, shot and timing reconstruction, timeline markers, chapters, beat cues, review notes and ranges, supplied or web-sourced footage, AI video platform selection, cleanup, highlights, product promotion, website walkthroughs, image-to-video assisted edits, optical-flow editing, depth/2.5D/transition finishing, AI voiceover, subtitles, short-form production, .timeline automation, or editor evaluation.

---

name: edit-timeline-studio-browser

description: Use native WebMCP tools to edit the project open in Timeline Studio. Inspect clips and available assets, preview and apply multi-track, caption style/position and project framing edits; sample rendered media; run local voiceover/transcription jobs; insert media; undo; save; or export video with progress and cancellation. Use for the live browser editor, not local project-file editing.

---

name: video-translator

description: Real time video translation / dubbing skill. Translate user-provided video (file or URL) and return preview_url. 适用于视频直译、视频翻译、视频配音、字幕翻译出片。

---

name: architect

description: Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly. Multi-candidate evaluation for key decisions.

---

name: archon

description: Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition.

---

name: ascii-diagram

description: Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

---

name: autopilot

description: Intake-to-delivery pipeline. Processes pending items from .planning/intake/: briefs new ideas, executes approved work through research → plan → build → verify. Drop a file in .planning/intake/ and invoke this skill.

---

name: cost

description: Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model breakdown. Reads Claude Code's native session data for exact numbers. Complements /dashboard with focused cost views.

---

name: create-app

description: End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or feature addition to existing codebase. Routes through PRD, architecture, and Archon campaign with verification at every step.

---

name: create-skill

description: Creates new skills from the user's repeating patterns. Interview-driven: discovers the task, analyzes failure modes, generates a production SKILL.md, installs it, tests it on a real target, and teaches the user how to use it. Use when a user wants to encode a repeating workflow; do NOT use for one-off tasks or modifying existing skills.

---

name: daemon

description: Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then schedules the next session. Auto-stops on campaign completion or budget exhaustion. The thing that makes Citadel run overnight.

---

name: dashboard

description: Real-time harness observability dashboard. Reads campaigns, fleet sessions, telemetry, and pending queues to present a snapshot of harness state at a glance. Invoked by /dashboard, /do status, or phrases like "what's happening" and "show activity".

---

name: decision-map

description: Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for the autopilot to build.

---

name: deploy-steward

description: Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.

---

name: design

description: Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.

---

name: do

description: Unified router that auto-routes user intent to the right direct action, skill, orchestrator, or explicit Operation Control plan. Classifies input by scope, complexity, persistence needs, and parallelism, then dispatches to the cheapest path that can handle it: direct command, skill, marshal, archon, or fleet. Single entry point for all work.

---

name: doc-gen

description: Documentation generator with three modes: function-level (JSDoc/docstrings), module-level (directory READMEs), and API reference (endpoints/exports). Reads existing project doc style and matches it. Never generates docs that just restate what the signature already says.

---

name: evolve

description: Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and pattern library across sessions.

---

name: experiment

description: Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures with a metric command, keeps improvements, discards failures. Supports convergence detection and diminishing returns.

---

name: fleet

description: Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously.

---

name: grill

description: Relentless one-question-at-a-time interview that sharpens a vague plan or design into shared understanding before any build. The elicitation engine other planning skills call instead of inventing their own interview. Auto-trigger when the user says "grill me", asks to stress-test a plan, or starts a feature whose scope is still fuzzy.