Explorar skills

Generate a structured sync bundle that captures decisions, architecture changes, conventions, bug fixes, and roadmap updates from the current Claude.ai conversation for ingestion into local Project Swarm projects via Claude Code. Trigger when the user says "sync", "sync project details", "generate sync bundle", "save this for Claude Code", "update local projects", "export decisions", or any variat

Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or analyzing environment variable handling.

Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.

OpenClaw and NemoClaw operations — sandbox management, inference provider config, policy configuration, Tailscale integration, security hardening, skill vetting. Trigger on: "OpenClaw", "NemoClaw", "OpenShell", "sandbox", "openclaw tui", "agent assistant", "ClawHub", "gateway token", or any task involving the personal AI assistant deployment on node_primary.

Autonomous work execution across all Swarm projects. Reads last session summary, picks highest-priority work, executes it, then loops to the next item. Only stops when blocked on the operator or nothing remains. Trigger on: "what's the status", "project status", "what needs work", "prioritize", "what's next", "plan work", "coordinate", "which projects", "phase status", "roadmap", "backlog", "sessi

Intelligent model routing for Claude Code sessions. Recommends optimal model (Opus/Sonnet/Haiku) and effort level based on task complexity. Delegates mechanical work to cheaper subagents. Maximizes quality-per-dollar across the entire session. Trigger on: any new session, "save tokens", "cheaper model", "delegate this", "use sonnet", "effort level", "cost", or automatically when task complexity is

Self-assessment and auto-update for Claude Code's installed skills, CLAUDE.md files, and reference data. Audits for staleness, gaps, overlaps, and freshness. Triggers on: "update your skills", "skill audit", "skill assessment", "refresh skills", "are your skills up to date", "check your skills", "review your context", "tune yourself up", "make yourself better".

Identifies dependencies at heightened risk of exploitation or takeover. Use when assessing supply chain attack surface, evaluating dependency health, or scoping security engagements.

Minimize Claude token and cost waste across ALL surfaces — Claude Code subagents, API calls in code, and artifacts. Routes subagent model selection via the Agent tool's model parameter. Recommends /model switches when the current model is overkill or underpowered. Applies to any code importing anthropic or calling /v1/messages. Trigger on: "API call", "artifact", "pipeline", "multi-agent", "LangGr

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Audit and optimize an existing Claude Code configuration against current best practices. Use this skill when a user asks to review, improve, clean up, or optimize their Claude Code setup, CLAUDE.md, settings, hooks, MCP servers, or skills. Also use when the user says things like "check my config", "is my CLAUDE.md too long", "reduce token costs", "tighten permissions", or "my Claude Code setup fee

Inspect and flush staged audit-trail entries to the remote trail repository. Use when the user asks to "flush audit trail", "show what's pending in audit trail", "dry-run audit flush", "retry audit pending", or when diagnosing why a previous auto-flush was skipped (secret hit, push failure, manual mode).