Loading...
Loading...
Found 7 Skills
Use when setting up hcom, troubleshooting delivery or hooks, checking install state, or writing reusable multi-agent scripts across Claude Code, Gemini, Codex, or OpenCode. Use the separate `using-hcom` skill for practical current-session coordination patterns and house defaults.
Multi-agent communication for AI coding tools. Agents message, watch, and spawn each other across terminals. Use when setting up hcom or troubleshooting.
Use when beginning or resuming a plan file, including mixed local and hcom-delegated execution, while keeping verification, plan state, and handoff metadata accurate.
Expert patterns for combat systems including hitbox/hurtbox architecture, damage calculation (DamageData class), health components, combat state machines, combo systems, ability cooldowns, and damage popups. Use for action games, RPGs, or fighting games. Trigger keywords: Hitbox, Hurtbox, DamageData, HealthComponent, combat_state, combo_system, ability_cooldown, invincibility_frames, damage_popup.
Use when building or debugging React interfaces in Meteor 3: meteor create --react, createRoot, JSX or TSX entry points, Rspack React detection, Fast Refresh, react-meteor-data, useTracker, useSubscribe, useFind, withTracker, Suspense, and Tracker.withComputation. Triggers on isLoading being treated as a boolean, useFind receiving fetch(), stale closure inputs, duplicate tracker side effects, unstable Suspense keys, lost reactivity after await, state reset after refresh, or React tests leaking computations. Use this skill when the user asks about a React skeleton, React-specific rspack.config rules, reactive data hooks, or classic versus Suspense integration. Route general bundler configuration to meteor-modern-build-stack and Meteor 2 upgrades to migrate-to-meteor-3.
Build your total addressable market (TAM) list and stand it up as a deployed model in Cargo: your ICP, read from your context (or drafted from your website and customer stories), becomes an AI Ark company search setting industries, company size and countries, sized for free before it bills, and lands as one model other pipelines read. Triggers: "our TAM is a stale CSV", "build our account universe", "source every company that matches our ICP", "keep our market list in Cargo", "how big is our market, and give me the companies", "land our TAM as a model the other pipelines can read". Cargo project, aiArk, countCompanies, fetchCompanies; FullEnrich, Apollo or Sales Navigator as swaps. Skip when: you want a list handed back in the chat or as a CSV rather than a model in the workspace, which is build-tam-list; or the accounts already exist and need tiering, which is account-scoring.
Use when agents must debate, conference, deliberate, or reach consensus on a goal — competing positions argue and converge on one deliverable, adversarial review with synthesis, multi-stakeholder deliberation, structured disagreement with a forcing-field deliverable. Triggers: 'have agents debate X', 'reach consensus on Y', 'argue distinct positions and converge'. Not for saved team configs, agents/<slug> artifacts, implementation, or open-ended research.