Use when writing Rust code with `axllm` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.

Use when writing Python code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

Use when writing Python code with `axllm` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

Use when writing Java code with `dev.axllm:ax` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.

Use when writing C++ code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

Use when writing C++ code with `axllm` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

Use when writing Rust code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

Show the current state of the wiki — what's been ingested, what's pending, and the delta between sources and wiki content. Use this skill when the user asks "what's the status", "how much is ingested", "what's left to process", "show me the delta", "what changed since last ingest", "wiki dashboard", or wants an overview of their knowledge base health and completeness. Also use before deciding whether to append or rebuild. Includes an insights mode triggered by "wiki insights", "what's central", "show me the hubs", "central pages", "what's connected", "wiki structure" — analyzes the shape of the wiki itself to surface top hubs, cross-domain bridges, and orphan-adjacent pages. Also includes an equilibrium mode triggered by "is my vault at equilibrium", "wiki equilibrium", "is maintenance done", "is the vault converged", or "are my skills fighting" — runs every maintenance skill's audit-only pass and reports whether any of them still has a pending change.

Read-only delegate to cursor-agent (Composer) for questions, investigation, design discussion, and adversarial sanity checks. No worktree, no cherry-pick, no Lead diff review — cursor-agent is locked to ask mode and cannot write. Use when user says: ask cursor, cursor sanity check, get a second opinion, adversarial review, design discussion, investigate with cursor, cursor:ask. Do NOT load for: implementation, refactor, file edits, commit/push work, anything requiring write access (use cursor:do or breezing --cursor instead).

Open Knowledge Format (OKF) v0.2 guidance. Use when creating, reading, reviewing, or maintaining an OKF bundle; responding to OpenKnowledge `okf` plugin warnings; or choosing types, provenance, links, indexes, or logs.

Deploy Tinybird pipes and datasources for enter.pollinations.ai observability with the Tinybird Forward CLI.

Task planning and approach strategy for NIC. Use when starting any non-trivial task, reading issues or specs, planning before implementing, or when asked to create a plan for a change.

Use when working with Lightdash YAML files, dbt models with Lightdash metadata, the lightdash CLI (deploy, upload, download, preview, lint, warehouse-catalog, sql, set-warehouse, apps create/preview/validate), or managing charts, dashboards, spaces and access, AI agents, scheduled content, data apps, organization Data App themes, data-app external connections, users, groups, custom roles, metrics, and dimensions as code

Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.

How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.

Use when designing or reviewing a component's public API. Naming, props, compound component structure, CSS custom properties, and data-attributes.

Reconstructs focused MCP capabilities as small, tested Pi tool definitions. Use when an MCP server exposes too many tools, when wrapping selected MCP calls for an SDK harness, or when replacing an MCP dependency with native code and recorded fixtures.

Configure TOTP authenticator apps, send OTP codes via email/SMS, manage backup codes, handle trusted devices, and implement 2FA sign-in flows using Better Auth's twoFactor plugin. Use when users need MFA, multi-factor authentication, authenticator setup, or login security with Better Auth.