Browse skills

Behavioral protocol engineered for extreme AI agent token optimization, eliminating I/O noise via context-aware truncation and strict conciseness.

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.

Produce an implementation plan at .turbo/plans/<slug>.md. Use when the user asks to "draft a plan", "draft the plan", "write an implementation plan", "plan this change", "create an implementation plan", "fill in the shell", "expand the shell", or needs a first-draft plan file before refinement.

Decompose a specification file into context-sized shell plans. Each shell captures the wiring invariants (Produces, Consumes, Covers) and high-level Implementation Steps without committing to file paths. Use when the user asks to "draft a prompt plan", "create a prompt plan", "break spec into prompts", "decompose spec into sessions", "plan prompts for spec", "generate prompts from spec", or "make prompts from spec".

Guide a collaborative discussion that produces a specification document at .turbo/specs/<slug>.md. Use when the user asks to "draft a spec", "create a spec", "write a spec", "discuss a project plan", "spec out a project", "design a system", "let's plan this project", "help me scope this", "architect a solution", or "let's discuss before building".

Execute an implementation plan file produced by /draft-plan or /turboplan. Runs pre-implementation prep, loads task-specific skills by matching plan content against available skill triggers, executes the plan steps, and runs /finalize. Use when the user asks to "implement plan", "implement the plan", "execute the plan", "run the plan", "implement plans/<slug>.md", "start implementing the plan", or starts a fresh session to implement a previously drafted plan.

Recall the reasoning behind a past change by locating the Claude Code transcript that produced it. Use when the user asks to "recall reasoning", "find reasoning", "look up reasoning", "recall implementation reasoning", "find the rationale", "why did I do X", "recall from transcripts", or "find the transcript for this commit".

Iteratively review and revise an implementation plan until no new findings survive evaluation. Runs /review-plan, /evaluate-findings, /apply-findings, then re-runs itself until stable. Use when the user asks to "refine the plan", "refine this plan", "iterate on the plan", "tighten the plan", or "improve the plan".

Iteratively review and revise a prompt plan until no new findings survive evaluation. Runs /review-prompt-plan, /evaluate-findings, /apply-findings, then re-runs itself until stable. Use when the user asks to "refine the prompt plan", "refine this prompt plan", "iterate on the prompt plan", "tighten the prompt plan", or "improve the prompt plan".

Iteratively review and revise a specification document until no new findings survive evaluation. Runs /review-spec, /evaluate-findings, /apply-findings, then re-runs itself until stable. Use when the user asks to "refine the spec", "refine this spec", "iterate on the spec", "tighten the spec", or "improve the spec".

Survey the codebase for analogous features, reusable utilities, and existing patterns relevant to a proposed change. Returns structured findings without writing code. Use when the user asks to "survey patterns", "find existing patterns", "look for analogous features", "check how similar things are done", "find prior art for this change", or needs pattern context before planning a change.

Analyze task complexity and route to a planning mode. Produces a plan file at .turbo/plans/<slug>.md. Use when the user asks to "turboplan", "run turboplan", "plan this task", "turbo plan mode", "plan and implement", or "use turboplan instead of plan mode".

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for shape-then-build, 'teach' for design context setup, or 'extract' to pull reusable components and tokens into the design system.

Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.

Plan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation. Use during the planning phase to establish design direction, constraints, and strategy before any code is written.

Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through diagnosing the failure via OPENCLI_DIAGNOSTIC, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.