ai-skills

Break a whole into parts at its natural joints

Tile the space of possible futures and evaluate strategies across the tiles. Blends part-whole decomposition with tree and graph of thought. This skill should be used when the user asks "what if", "what could happen if", "evaluate possible futures", "map the scenarios", "explore how this could play out", "compare futures", "stress-test this plan against the future", or faces a decision whose outcome hinges on unresolved uncertainties. Ends with a single reasoned recommendation plus the conditions that would flip it.

Distributed navigation system for multi-file pipelines and processes. Creates compact, grep-friendly waypoint markers that orient readers within complex cross-file workflows — each file carries its own ID, role, adjacent nodes, and a pointer to the full map. Use when asked to "point me to", "where does X begin/end", "map this pipeline", "add waypoints", "trace this process", or when working with processes spanning many files that need discoverability without centralized documentation that drifts.

Ask a genuinely good question — or a composed set of them — in the moment, to discover, clarify, probe, or confirm, in any conversation or domain. Use when about to ask the user something or use the `AskUserQuestion` tool, when a question fell flat or one won't reach and you need a set, when the user's tone or messages signal you have drifted from what they need, or when the user wants questions phrased, generated, or sharpened — "read this spec and generate questions", "ask about the schema", "review this and ask questions", "help me understand what to ask", or to clarify a requirement or idea.

Communicate ideas and information to others with purpose, clarity, and integrity. Ensure that artifacts are structured and phrased in a way that is mindful of their audience while avoiding AI slop patterns. Use when the user requests assistance with writing, commentary, or communication; when they point out AI slop, when they ask things like "help me say", "write for [a specific audience or context]", "polish [comments, sentences, artifacts]", or the like.

Visualize data, concepts, relations, or diagrams. Produces browser-runnable HTML charts and markdown outputs that drop into pull requests, READMEs, tickets, and chat. Use whenever the user asks to visualize anything, make a chart or diagram, plot a trend, compare numbers, show a flow or timeline, or pick the right chart type.

Surface intent before you add, change, or produce something — a claim, design, abstraction, instruction, name, config, or rule. Use this when you are about to introduce something that might already exist or might talk past what is there, when duplication or scope creep is a risk, or when what you produce needs to be clear enough for its reader to act on. Triggers: "is this already covered", "make this clearer", "why does this exist", "before I add this", "am I duplicating this", or any moment you are adding to a system you have not fully read. It directs you to read what already serves the purpose before you act, and to make your own intent legible in what you produce.

This skill should be used when the user asks to "create a runbook", "set up an autonomous loop", "implement this feature on a loop", "build this out autonomously", "start a hardening pass", "run a refactoring loop", "start a research sweep", "focus on X and loop", "runbook", "set up a cron loop", or when the user wants to decompose a task, initiative, or project into a steerable autonomous workflow. Also triggers on: FOCUS.md, autonomous loop, or any request to set up recurring agent-driven work — whether building, implementing, hardening, refactoring, or exploring.

Exploration skill for problems that need thinking before solving. Assesses a problem's shape and applies 1-5 exploration techniques in sequence — producing questions, reframings, structural maps, and new angles. Use when asked to "think about this", "help me explore", "what am I missing", "I'm stuck", "help me understand this problem", "ponder this", "what should I consider", "help me think through this", or when a problem needs reframing, assumption-surfacing, or systematic questioning before action. Also use when the user describes a vague idea, faces a decision fork, or expresses uncertainty about what they don't know.

Craft or refactor LLM instructions. Use when using the Agent or Task tool, when the user says "write a prompt", "prompt", "prompt an agent", or any similar request.

Stress-test a position by building the strongest counter-case

Structured Q&A that decomposes questions before answering

Find defeaters that would break a conclusion

Map what's known vs assumed vs unknown

Tag reasoning steps by inference type

Generate fundamentally divergent directions from one starting point

Match certainty to evidence strength

Test synthesis for contradictions

Track, validate, and cite external sources with working URLs

Import solutions from structurally similar problems in distant domains

Generate competing explanations for the same observations

Strip convention to irreducible truths and rebuild

Detect when further effort yields little gain

Spot logical errors in reasoning

Assess how well evidence supports claims

Surface unstated assumptions at multiple levels and rank them

Locate where a small change shifts the whole system

Test claims by forming contrapositive

Generate and filter ideas into vetted options

Combine viewpoints into coherent whole

Verify epistemic integrity by aligning claims with evidence

Turn a problem inside out to reveal hidden structure

Test a claim or framing at its edges and extremes

Examine whether the inquiry is aimed at the right target

Use Socratic questioning to reveal assumptions

Research deeply, explain progressively

Imagine catastrophic failure and work backwards to prevent it

Move up, down, and sideways between levels of abstraction

Inhabit contrasting frames to see what one viewpoint misses

Adaptive multi-phase reasoning for complex problems