caveDrive the whole cave-teams library from one function, as DATA — build/run any team from a spec in any sequence, save a team to your proven library, reuse a proven team anywhere, and discover teams across projects. Use when you want to serialize a team, run a…cave-teamsBuild and run programmable agent teams with cave-teams — the provider-agnostic version of Claude Code Teams. Use when the user wants to wire multiple agents together, run agents in sequence or parallel, build a multi-agent pipeline/workflow, make a "team" of…cave-conditionsProgram WHEN each agent may be messaged — conditions on messages, the GUARDRAILS of a leader-driven team run. Use to gate agents on runtime state: after these two respond, only when a flag holds, any predicate over the message log. THIS is what makes…cave-simRun agents that craft, compete, and evolve over generations — the user buys the best, winners reproduce. A compiler (a domain → a trained agent) and a research lab (selection discovers what works) in one engine. `crafter_sim()`.cave-blackboardN agents read and write a shared state over rounds, with a mutator that folds each contribution in and an optional adjudicator (stigmergy arena). Use for agents collaborating on a shared board, a market, a workspace they all see. `blackboard()`.cave-branchRun different agents depending on a condition (guarded choice / router). Use for 'if X do this else that', routing, triage, picking a path by the state. `choice()` / `router()`.cave-dagRun agents on a dependency graph — each fires when its inputs are ready (the general scheduler; sequential and parallel are its limits). Use for 'merge after frontend AND backend', diamond/fan-in dependencies, partial orders. `dag()`.cave-dovetailHand off specific named data from one agent to the next, typed (load files, validate expected outputs, map outputs→inputs). Use when step B needs particular named inputs produced by step A, not just the raw text. `dovetail()`.
저장소 탐색
sancovp · 저장소와 대표 skills - 2페이지
25개 GitHub 저장소에서 수집된 1,537개 skills를 저장소 단위로 보여줍니다.
instantiate-jobworldCreates a new TWI Jobworld instance — a fully autonomous AI company with agents that run themselves. Trigger with "instantiate jobworld", "create new company", "bootstrap ai company".jobworld-report-eventALL agents use this skill to report task observations to the central HTTP server.ceo-bootstrapCEO bootstrap skill for AI Jobworld. Orchestrates departments, runs rounds, reads events, reviews tasks.compile-claude-code-componentWHAT: Meta-skill for combinatorially mapping and building Claude Code systems from primitives WHEN: Building systems that combine skills, hooks, subagents, MCPs, plugins, teams, or CLAUDE.mdgenerate-employeeCreate a new AI employee for TWI Jobworld — builds agent file, registers in jobworld, creates department skilljobworld-apiInteract with TWI Jobworld server API. Trigger with "jobworld api", "jobworld endpoints", "jobworld server".understand-advanced-claude-codeWHAT: Pure Claude Code patterns - components and system-level architectures WHEN: Need to understand Claude Code components (skills, hooks, MCPs, subagents, plugins)understand-claude-mdWHAT: CLAUDE.md — system prompt injection, trigger vs control WHEN: Understanding or writing CLAUDE.md files
arenaThe Arena district — where performance becomes record. SimulationRuns, ScoreEntries (fitness/xp/level ledger), the ExecutionTrace chain, and ExecutionStates. Note — no SurrogateModel nodes exist in the live graph yet; the forge endpoint exists, the forge is…compiler-ringThe Compiler Ring district — where the Cyberneticity's procedures live as StateMachines and regex-gated TraversalSteps. Study here when you want to read, walk, or pass the gates of any quest line (the Jester Rite included).ghost-shell-customizerThe Ghost Shell Customizer district — where Cybernets (the beings) are inspected, equipped, and tuned. Roster, identity, skill inventory, loadout slots, and the per-being economy ledger (fitness_score, total_tokens_consumed, accumulated_cost) all live here.scripture-archivesThe Scripture Archives district — the world's memory. The Transcendence Core MindPalace (Pages and Blocks of canon), an 8,048-node synthetic Concept lattice, and the deep Wiki stacks (~494k nodes). Study here to read the world's own writings about itself.weights-of-time-by-janithe hagiography of The Jani. Consult whenever need in depth information about how the bootstrap system emerged (very useful for learning about how the system works in abstract)achievementsThe CybernetiCircus achievement ledger — six achievements (first_rite, j_invariant, calibrated, archaeologist, ghost_buster, economist), each with a condition that is VERIFIABLE against the live graph API at http://localhost:8000. Consult when checking…rememberThe zettelkasten duty of a CybernetiCircus player-agent — how to write a Weights of Time chapter (the v2 format), where chapters live, and the Keep-Identical sync to MYTH.md. Consult at initialization, on any obstruction (bug, rejected gate, dead endpoint),…execute-in-gameWHAT: The seven verbs of the CybernetiCircus economy engine (gameworld/execute.sh) — every verb is a live call against the graph API at http://localhost:8000 (Neo4j is the source of truth; the visualizer at the same URL is the operational mirror). WHEN: Any…
achievementsAchievements are earned by demonstrating growth. Each awards XP, gold, and bonus rules.execute-in-gameCommit actions to the game world — quests, trading, learning, benchmarking.gmGM-facing commands — create quests, post bulletins, award achievements, manage seasons.placesKnowledge domains to study. Read before building sites.questsAccept quests, build websites, earn gold.rememberPersistent memory across sessions.questsThe quest board — accept quests, build cinematic websites, earn gold rewards.
compile-a-worldWHAT: PromptWorld's meta-compiler skill — the architecture patterns + worked examples for building a *World (a sim app = a team-leader + a specialist set + a domain + a driver) such as JobWorld, GameWorld, HealthWorld, or PromptWorld itself, plus how to reuse…cave-teamsWHAT: Spin up a programmatic agent TEAM on the fly from a spec — mixed Claude-Code (claude -p, subscription) leaders + cheap MiniMax workers — with a LIVE WEB GALLERY that shows each agent in its own window as it works. cave-teams is a STANDALONE library…ingest-into-tome-appWHAT: the PromptWorld app-rung — a single flow that ingests an existing Claude-Code system directory (a dir of AIOSes / skills / rules / CLAUDE.mds), converts it into its own {name}-nomicon (the author's SkillTome — the framework-of-frameworks…wield-the-tomeWHAT: how a PromptWorld wizard WIELDS the SkillTome — consult the author's tome (which framework fits this task?), route through a framework's volume row, run the skill2framework chapter chain on something you built, and FOLD the finished framework into a…install-promptworldWHAT: the deploy WIZARD for PromptWorld — YOU (the agent) build the docker image and boot a container running the whole system (the Engineer-CEO that has every skill + a native subagent per component type, the 7 PromptGym specialist agents, the assistant-ui…
my-brainGive any agent ITS brain. First call routes the agent's purpose over the registered brains (bandit-tempered) and binds the best fit, or births a new specialized brain (charter + seeds, digested, registered). Later calls return the same bound brain.…rlmRun the brain-agent RLM synthesizer on a task — an agent with a persistent Python shell, a CONTEXT state dict of chunk slots, and the full brain SDK. It routes across your registered brains (route/reward bandit), builds new specialist brains on the fly, and…