Browse Skills

Ask routes a question to an external advisor such as Claude or Gemini when configured. Use it for explicit consultation requests that need a second opinion before proceeding.

Autoresearch Goal runs validator-gated, durable research loops with explicit evidence boundaries and source-gap tracking. Use it when a research task needs checkpoints, critic checks, and a source-backed handoff.

Best Practice Research gathers official or upstream guidance for a specific technology and compares it to the user’s question. Use it when you need source-backed best practices from docs before choosing or implementing an approach.

Codegraph Refresh refreshes local code intelligence, summarizes repo structure, and prepares task-scoped handoff context before planning or implementation. Use when codegraph data is stale or a fresh navigation summary is needed without claiming execution evidence.

Context Budget Review plans compact context for long agent work, including token and cost budgets, summarization checkpoints, and overflow recovery. Use it when context size or drift could affect research, coding, or review tasks.

Cto Loop runs a leadership operating loop for roadmap, technical tradeoffs, delivery risk, release readiness, and follow-up handoffs. Use it when a request needs CTO/PM-style synthesis across product, engineering, QA, security, and ops.

Create Adapter covers building conversation adapters that import AI chat history from tools like Claude Code, Cursor, Warp, and Codex. Use it when creating or debugging an adapter’s parsing, caching, watch handling, or performance behavior.

Create Plugin explains how to build Sidecar plugins that implement the plugin interface, render Bubble Tea views, and wire keyboard input, footer hints, event bus, and lifecycle hooks. Use it when adding a plugin or debugging plugin rendering and init/stop behavior.

Ablation Planner designs reviewer-focused ablation studies for ML papers after main results support the claim. It helps plan, prioritize, and implement component, hyperparameter, and design-choice ablations.

Aris Experiment Plan turns a refined research proposal into a claim-driven experiment roadmap. Use it to decide the main ablations, evaluation protocol, run order, and compute budget for a paper-ready validation.

ARIS Infra sets up the ARIS research environment by registering MCP review servers, installing Python dependencies, and checking prerequisites. Use it first when configuring ARIS or adding review models.

Aris Meta Optimize analyzes ARIS usage logs and suggests changes to SKILL.md prompts, defaults, and workflow rules. Use it when optimizing the harness based on accumulated runs and manual overrides.