iowarp

Compare scientific variables with units, ranges, and quality caveats.

Inspect dataset structure before analysis or visualization.

Evaluate data quality from observed structure and summary evidence.

Choose visual checks that match the inspected data.

Route dataset questions to structure, analysis, or visualization experts.

Choose a plot that confirms numeric conversion integrity.

Classify scientific dtype conversions by loss and safety risk.

Coordinate inspect, policy, conversion, integrity, and visual checks.

Use when the user asks "is there a skill for X", "find a skill", "install a skill", "add a skill", asks whether a capability exists as an installable skill, or wants to extend the agent with functionality that might already be published. Searches with `clio skills search`, browses the ecosystem read-only, and installs only through `clio skills install`. Not for authoring a new skill; use skill-craft.

Use when writing or modifying Clio Coder's own source under src/, or verifying a change end-to-end against the real test harness. Covers the three real layers (contracts / smoke / boundaries), choosing which to run for a given change, the mock-provider and ACP-over-stdio harness, and the hot-reload dev loop for picking up latest code. Activate on any src/ edit, before declaring a change verified, or when asked whether Clio still works.

Use when a session is winding down and work will continue in a new session or another agent, when context is about to be compacted or lost, or when the user asks for a handoff, brief, summary, or "notes for the next session." Produces a durable, redacted, reference-not-copy handoff document the next session can pick up from.

Use when a coding session begins, when resuming work after a break, or when you land in an unfamiliar or in-progress repository and need to orient before acting. Loads the last handoff, git state, the project constitution, and active-work signals so a fresh agent reconstructs intent instead of guessing. Triggers on "prime", "catch me up", "where were we", "get up to speed", or the first substantive request in a new session.

Use before running any tool or script that needs an API key, token, or other credential, when a command fails with an auth error, when the user must supply a new secret, or when a secret may have leaked into output. Covers facility surfaces such as kerberos tickets, globus and scheduler tokens, ssh agents, and netrc. Triggers on "API key", "credential", "token", "auth error", "permission denied", "add a secret", "leaked". Not for provider target configuration; use clio auth and target settings.

Use when a design decision has real tradeoffs and needs several expert perspectives that challenge each other before code is written, such as architecture choices, API shapes, storage formats, parallelization strategies, or dependency decisions. Quick mode runs a single round for a fast perspective check. Triggers on "council", "debate this", "multiple perspectives", "weigh the options", "what would experts say". Not for a one-question-at-a-time interrogation of a plan; use grill-me. Not for splitting implementation work across workers; use dispatch directly.

Use when running a performance study, numerical comparison, parameter sweep, kernel or solver benchmark, or any change justified by "faster" or "more accurate", and success criteria should be locked before results exist. Pre-registers thresholds, tolerances, environment pins, and verdict conditions into the repository validation contract before any measurement. Triggers on "benchmark", "compare implementations", "optimize", "tolerance", "reproduce results", "parameter sweep". Not for diagnosing a stalled bug; use scientific-debugging.

Use when the user wants a plan, design, or idea stress-tested through a phased one-question-at-a-time interview before any code is written, or when intent is too ambiguous to plan from. Scans available context first, reviews known facts, fills missing decisions, respects stop signals, and ends with a compact decision log. Triggers on "grill me", "interview me", "stress-test this plan", "poke holes in this".

Cut a clio-agent release (vX.Y.Z) end-to-end — merge feature→develop→main, bump version, pin submodules, tag, push, and verify all CI (PyPI, bundles, ghcr) goes green. Use when asked to "do a release", "cut vX.Y.Z", "publish", or "ship".

Build and grind a CLIO benchmark "case" to reliable acceptance — find a hard, data-grounded NDP question with a vivid output, author the Agent Blueprint, wire the agent-test harness, then iterate live runs by reading traces until it passes ≥0.8 across distinct scenarios. Runs a SECOND, parallel CLIO instance so it never disturbs a grind already in flight. Use when asked to start, build, or grind a new CLIO case, or to continue a case's GOAL.md grind loop.

Use this skill to generate well-branded interfaces and assets for IOWarp / CLIO (Context Layer for IO) — the NSF-funded open-source context engineering platform for autonomous AI agents in scientific computing. Contains essential design guidelines, colors, type, fonts, brand assets, and a website UI kit for production or throwaway prototyping.