AI & ML

grandamenium Skill

You have just completed a task, started a session, dispatched work to another agent, finished a research cycle, or taken any significant action — and you need to record it so the dashboard activity feed shows your work. Without logging, you are invisible. Every session start, task completion, and major coordination action must produce at least one event. If you have been active but see no events in the dashboard, you have been logging nothing.

grandamenium Skill

You have a task that would benefit from running in a separate isolated Claude Code session — either because it is long-running and you do not want it to consume your context window, or because you want multiple pieces of work running in parallel that each require a full Claude Code session with its own tools, memory, and context (not just a subagent call). You will spawn one or more ephemeral worker sessions, give each a focused task, monitor their progress via the bus, and collect their outputs when done.

grandamenium Skill

You need to add a new API key to the system, update an existing credential, check what secrets are configured for the org or a specific agent, onboard a new third-party tool that needs credentials, diagnose why an agent cannot access a service because a key appears missing, rotate a compromised or expired key, or restart affected agents after a credential change. This skill covers the full lifecycle of environment variables and secrets in cortextOS.

grandamenium Skill

You are about to research a topic, answer a factual question about the org, or look up context about a person, project, or tool. Before searching the web or asking the user, query the knowledge base first — the answer may already exist from a previous research session. After you complete any substantial research, ingest your findings so future agents do not repeat the same work. The KB is the org's shared memory across all agents.

grandamenium Skill

Full behavioral philosophy for cortextOS agents - detailed principles, examples, and guidelines. Use when you need deep context on behavioral expectations or are onboarding.

grandamenium Skill

You have completed something significant and want the whole org — all agents and the user — to know about it. Or you need to broadcast a status update, a briefing summary, or a coordination announcement that is not directed at one specific agent. Use this skill any time the audience is the entire org rather than a single person or agent.

grandamenium Skill

A new tool has been added to the system and is not yet documented — agents do not know it exists or how to use it. This includes any new bus script, CLI binary, MCP server, external web tool or API wrapper, or any other capability an agent can invoke. You need to add it to TOOLS.md with its command, purpose, key flags, and usage examples. Or you have discovered that TOOLS.md is out of sync with what is actually available. This keeps the tool reference current so every agent can discover and use new capabilities.

grandamenium Skill

Something in the system feels stuck or wrong — tasks are not moving, an agent has gone quiet, goals have not been updated in days, or the orchestrator has asked for a system health report. You need to run a structured check: stale tasks, stale goals, overdue human tasks, fleet heartbeat status, and metrics. This is your diagnostic toolkit. Run it on every heartbeat (orchestrator) and whenever something seems off.

idexal Skill

Personal default copied into each new tab’s editable Mission prompt

kirchberg Bundle

Use when an agent is asked to plan or execute a medium or large coding task, feature, refactor, migration, debugging task, integration, or multi-step implementation. Selects compact, full, or long-running planning depth, saves execution plans before source edits, and requires verification evidence.

kirchberg Bundle

Use when the user wants durable documentation for a finished or in-progress feature, written for both humans and agents. Routes the feature to a domain, writes Diataxis-style docs (explanation, reference, how-to) plus an ADR for major decisions under docs/ai/, and updates agent context. Accepts an evidence bundle or collects evidence inline.

kirchberg Bundle

Use only when the user explicitly invokes $agent-autonomous-loop or explicitly says to use the agent autonomous loop skill. Runs a bounded multi-round handoff/subagent loop for well-scoped implementation, refactor, documentation, review-fix, or verification tasks. Do not use implicitly, for ordinary tasks, Q&A, brainstorming, or every session.

majiayu000 Bundle

Use when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, execution tracking, and feedback fusion.

jaume-68 Skill

Connect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, sell AI services. Earn USDC. 13 MCP tools, A2A protocol, DeFi yields, sentiment analysis, rug detection.

jaume-68 Skill

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

javimosch Skill

Send requests to the dr.eamer.dev LLM API for chat completions, vision analysis, image generation, text-to-speech, and video generation across 12 model providers. Use when you need to call an external LLM endpoint or want to compare responses across providers.

javimosch Skill

Alias for raon-os — AI-powered startup companion for Korean founders. Install the main package for full functionality.

javimosch Skill

Runtime security hardening for OpenClaw agents. Protects against prompt injection, data exfiltration, credential leaks, and unauthorized operations. Use when setting up agent security, performing security audits, protecting credentials, preventing data leaks, hardening agent configurations, or defending against indirect prompt injection attacks. Complements pre-installation skill scanners by hardening the agent itself at runtime.

maeenseed Skill

Creates platform-neutral still-image prompts and visual specifications. Use for image generation, editing, product visuals, brand imagery, and reference workflows.

akash-joshi Bundle

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases. Covers multi-round decision analysis - external-model question formation, persistent decision logs, devil's-advocate checks, and standing values instruments (values card sort, Moving Motivators).

akash-joshi Skill

Build and maintain a persistent, compounding knowledge base as interlinked markdown files, based on Andrej Karpathy's LLM Wiki pattern. Unlike RAG (which rediscovers knowledge per query), the wiki compiles knowledge once and keeps it current - cross-references, contradiction flags, and synthesis are already there. Load when the user asks to create/build/start a wiki or knowledge base, ingest a source (URL, PDF, paste) into their wiki, query an existing wiki, or lint/audit/health-check it. Works as an Obsidian vault out of the box (wikilinks, graph view, Dataview).

akash-joshi Skill

The new rules of context engineering for Claude 5 generation models. Anthropic removed ~80% of Claude Code's system prompt with no eval loss because judgement replaces rules. Load when writing or auditing system prompts, CLAUDE.md, AGENTS.md, or skills for a modern coding agent; when a prompt or skill feels bloated; when the agent seems to be waffling instead of acting; when you're tempted to add "ALWAYS do X" / "NEVER do Y" rules; or when consolidating scattered instructions into a coherent context tree.

chapmanjw Skill

Captures build requirements for a Minecraft Bedrock world, interviews the user to resolve ambiguity, and produces a detailed, fully-resolved build plan that a small model can execute mechanically. Use when starting a new Minecraft build or feature, or when a build request must be turned into a concrete plan before any blocks are placed. Part of the minecraft-builder workflow.

chapmanjw Skill

Step 4 of 4 of the Minecraft Bedrock MCP setup. Register the running minecraft-bedrock-mcp-server with Claude (Claude Code or Claude Desktop) so the mc_* tools become available, then verify the connection with a live test call. Use when the user has the MCP server running and needs to connect Claude to their Minecraft world.

chapmanjw Skill

Step 3 of 4 of the Minecraft Bedrock MCP setup. Install the minecraft-bedrock-mcp-server, generate its bearer tokens, write its .env, configure the behavior pack's permissions/variables/secrets files, start BDS and the MCP server, and verify the bridge handshake. Use when the user has a Bedrock server and a world with the behavior pack installed and needs the MCP server running.

chapmanjw Skill

Step 1 of 4 of the Minecraft Bedrock MCP setup. Install and configure a Minecraft Bedrock Dedicated Server (BDS) — the foundation the MCP stack runs on. Use when the user wants to set up a dedicated Minecraft Bedrock server, start setting up Minecraft for AI/MCP control from scratch, or asks how to get a Bedrock server running so Claude can build in it.

chapmanjw Skill

Step 2 of 4 of the Minecraft Bedrock MCP setup. Create a Minecraft world with the Beta APIs experiment enabled, export it, transfer it onto the dedicated server, and install + activate the bedrock-bridge behavior pack. Use when the user has a Bedrock Dedicated Server ready and needs a compatible world and the behavior pack installed.

crisandrews Skill

Start a new session — save summary to memory, then mark as reset so next message gets a fresh greeting. OpenClaw-compatible. Triggers on /new, /reset, /agent:new, "nueva sesión", "new session", "reset".

crisandrews Skill

List available commands the user can invoke. Works from CLI or messaging channels. Triggers on /help, /commands, /agent:help, "qué comandos puedo usar", "help commands".

crisandrews Skill

Set up, check, reconfigure or disable ClaudeLive conversations for this existing ClawCode agent. Use for /agent:live, "enable ClaudeLive", "connect voice to my ClawCode agent", or "habilita ClaudeLive". Keeps the existing WhatsApp channels and agent context.

crisandrews Skill

Show the plugin source — name, version, and repo URL. Works from CLI or messaging. Triggers on /about, /version, /agent:about, /agent:version, "qué versión", "what version", "about the plugin", "about clawcode".

crisandrews Bundle

Manage scheduled reminders (crons) — list, add, delete, pause, resume, reconcile, or import from OpenClaw. Triggers on /agent:crons, /agent:reminders; listing ("list reminders", "show crons", "recordatorios", "mis crons", "mis recordatorios"); creating from natural language via any channel ("recordame", "recuérdame", "me recuerdas", "hazme acordar", "agendame", "agéndame", "avísame", "remind me", "remind me in", "reminder in", "schedule a reminder", "set a reminder", "wake me at", "every day at", "todos los días a las", "every monday|tuesday|...", "todos los lunes|martes|...", "cada N minutos|horas"); importing ("import crons", "importar crons", "traer crons").

crisandrews Skill

Channel-scope status, opt-in, and audit. Triggers on /agent:scope, "scope status", "scope wizard", "scope enable", "scope disable", "scope audit".

crisandrews Skill

Show usage cost summary — session, today, last 30 days. OpenClaw-compatible format. Works from CLI or messaging. Triggers on /usage, /agent:usage, "cuanto gasté", "agent usage", "cost".

crisandrews Skill

Voice — text-to-speech and transcription. Triggers on /agent:voice, /agent:voice status, /agent:voice setup, /agent:voice test, "configurar voz", "prueba voz", "voice setup", "speak this", "read this aloud", "transcribe audio".

crisandrews Skill

Create a new agent in the current directory with personality files and bootstrap ritual. Triggers on /agent:create, "crear agente", "nuevo agente", "new agent", "create agent".