clio-coder

Materio: materials research interviews, supplied-corpus synthesis, lab feasibility, task execution and verified paper handoff.

6 skills

HPC pack: Slurm job arrays and sweeps through the clio-kit Slurm server, Lmod and Spack software environments, parallel HDF5 and MPI-IO, Darshan I/O analysis, and ChronoLog run records. The skills drive the cluster's own command-line tools; the clio-kit Slurm server needs one online launch to build its environment before it runs offline.

5 skills

Life-science pack: skills that query the RCSB Protein Data Bank, UniProtKB and PubChem over their public, key-free REST APIs with web_fetch, and stamp each answer with the source's entry revision or release. Every lookup needs network; offline the skills say the source is unreachable.

3 skills

Literature pack: verifies citations and resolves DOIs and arXiv IDs through the CiteNexus MCP server (cite-nexus-mcp 0.2.2, key-free Crossref, DataCite, Europe PMC and arXiv), with an offline extractor for BibTeX and Markdown and a web_fetch fallback. Adds a hypothesis workflow: cited grounding, independent council proposals, a testability ranking and the smallest experiment per hypothesis, ending at the operator's own choice. Extends arxiv-literature. Needs network for every lookup; the server needs one online launch to install.

2 skills

Decides the engineering approach for an intent in an interactive session: investigates, proposes two or three genuinely different approaches with trade-offs, recommends, lets the user decide, and writes the decision doc. Not a task-by-task plan; use sprint-plan. Not a multi-perspective debate; use design-council. Not product intent; use product-intent. Not a typed implementation handoff; use tech-spec.

1 skill

Searches arXiv, summarizes or compares papers, and builds a compact literature survey as citation-ready, source-linked paper cards, with BibTeX export and ID verification through the CiteNexus server when the literature pack is installed. Prefer the Researcher shadow agent for noisy multi-paper retrieval.

1 skill

Structural code search with ast-grep rules: finds code by shape when grep on text is too noisy, and never rewrites it. Not for plain string or filename lookups; use grep or find.

1 skill

Turns a finished PRD or architecture doc into a ticket backlog of small stories with verifiable acceptance criteria, confirmed, then created as GitHub issues or in another configured tracker. Not for local sprint slicing into a SPRINT.md; use sprint-plan.

1 skill

Proves merged work on the canonical base, inspects and removes associated worktrees through Git, deletes local branches safely, and audits surviving repository refs. Not for creating worktrees; use worktree-create. Not for integrating branches; use worktree-merge.

1 skill

Develop Clio Coder inside its own repository: orient on the running build versus the workspace, trace owners, avoid the checks that fail landings, apply each edit the right way and hand the work back. Use before changing Clio source, prompts, tools or library; pair with clio-coder-test for validation.

1 skill

Validate Clio Coder changes: pick checks from the diff, know what each test tier proves, keep runs isolated, verify behaviour live in a candidate build and report evidence without claiming unrun coverage. Use when developing or diagnosing Clio itself.

1 skill

Correct-by-construction TypeScript rules (errors as values, parse don't validate, illegal states unrepresentable, deep modules) for writing or refactoring TypeScript when the project has not pinned its own standards.

1 skill

Writes a durable, redacted, reference-not-copy handoff document when a session winds down or context is about to be compacted or lost, so the next session or agent can continue. Not for orienting at the start of a session; use context-prime.

1 skill

Orients a fresh session in a repository by loading the last handoff, git state, the project constitution, and active-work signals before acting. Not for writing the handoff; use context-handoff.

1 skill

Handles API keys, tokens, and facility credentials (kerberos tickets, globus and scheduler tokens, ssh agents, netrc) before a tool needs one, after an auth error, when a new secret is supplied, or when one may have leaked. Not for provider target configuration; use clio-coder auth and target settings.

1 skill

Convenes several expert perspectives that challenge each other on a design decision with real trade-offs before code is written; quick mode runs a single round. Not for a one-question-at-a-time interrogation of a plan; use plan-interview. Not for splitting implementation across workers; use dispatch directly.

1 skill

Pre-registers a performance study, numerical comparison, parameter sweep, or benchmark: thresholds, tolerances, environment pins, and verdict conditions locked into the validation contract before any measurement. Not for diagnosing a stalled bug; use scientific-debugging.

1 skill

Builds, tests, and debugs Clio Coder api 2 extensions with declared capabilities and host-rendered views. Not for instruction-only skills; use skill-authoring.

1 skill

Turns something noticed mid-session into a tracker issue: captures evidence, dedups against existing issues, composes a labeled issue with acceptance criteria, confirms, and creates it via gh. Not for batch ticket creation from a PRD; use backlog. Not for diagnosing an existing issue; use fix-issue.

1 skill

Finds published skills and prepares their Library installation for the operator when the user asks whether a capability exists as a skill. Not for authoring a new skill; use skill-authoring.

1 skill

Resolves a tracker issue end to end: fetches it, diagnoses only when the issue does not name the code, fixes test-first, and self-reviews against the acceptance criteria, leaving a verified uncommitted change. Not for filing; use file-ticket. Not for committing or PRs; use ship.

1 skill

Interactive codebase maps from verified repository structure, symbols and imports, rendered natively as standalone HTML.

1 skill

Stress-tests a plan, design, or idea through a phased one-question-at-a-time interview before code is written, ending in a compact decision log. Not for a multi-perspective debate; use design-council.

1 skill

Turns an idea into a product requirements document through a phase-gated interview, ending in PRD.md plus per-milestone prompt files ready to drive a coding agent. Not for the problem-first product thesis; use product-intent.

1 skill

Writes a problem-first product document for a greenfield effort: interviews for the problem, evidence, and a falsifiable hypothesis, with zero engineering decisions. Not for engineering decisions; use architecture. Not for turning a locked idea into milestone build prompts; use prd.

1 skill

Answers a design question with throwaway code: a clearly marked, runnable, no-persistence prototype whose verdict is kept and whose code is discarded. Not for pre-registered performance experiments; use experiment-protocol. Not for production implementation.

1 skill

Resolves a merge, rebase, or cherry-pick stopped on conflicts by reconstructing both sides' intent, validating with the project's own checks, and completing the operation. Not for integrating many branches; use worktree-merge.

1 skill

Science data pack: a skill that finds datasets and keeps results in the store, reads HDF5, NetCDF, Parquet and CSV with Clio's data tool first, and declares the clio-kit parquet and pandas MCP servers with per-tool action classes for analysis beyond it. Read tools run without asking; file-writing tools ask first; each server needs one online launch to build its environment before it runs offline.

1 skill

Diagnoses stalled or cross-system failures and wrong, NaN, nondeterministic, or unexpectedly slow scientific results through falsifiable hypotheses across distinct fault classes, with evidence-cited verdicts before any fix. Not for designing benchmarks or pre-registered experiments; use experiment-protocol.

1 skill

Modernizes, ports, rewrites, packages, or replaces established scientific software in independently validated stages against an external scientific oracle, settling compatibility and upstream stewardship before calling it complete. Not for an isolated benchmark; use experiment-protocol. Not for diagnosing wrong results; use scientific-debugging.

1 skill

Ships finished work: writes one reviewed atomic commit, keeps maintainer branches local, or pushes a contributor branch to their fork and opens a PR only on explicit intent. Not for producing the change; use fix-issue.

1 skill

Writes, reviews, or prunes a SKILL.md, judging whether its description, body, and length earn their cost. Not for packaging a workflow that just happened; use workflow-capture.

1 skill

Submits a batch script or job array to Slurm through the clio-kit Slurm MCP server, polls every task to a terminal state, fetches its output, and stamps the scheduler job id into the final answer. Not for writing the science inside the script or for interactive allocations.

1 skill

Slices an existing plan, PRD, or milestone into an executable sprint of dependency-ordered vertical slices sized for one agent run each, with done-when verification per slice; never fabricates a plan. Not for deciding the approach; use architecture.

1 skill

Builds a feature or fix test-first, red to green at pre-agreed public seams, one vertical slice at a time. Not for designing benchmark criteria; use experiment-protocol.

1 skill

Writes a typed call-stack architecture handoff: code-shaped contracts plus execution flows, implementation-ready for another engineer. User-invoked only. Not for weighing approaches or deciding the design; use architecture first.

1 skill

Packages a workflow that just happened into a reusable SKILL.md: reconstructs it from the session record, checks overlap with installed skills, gates on approval, then writes it following skill-authoring. Not for authoring a skill with no prior workflow; use skill-authoring.

1 skill

Stands up one or more git worktrees for parallel work, each on its own branch with gitignored config copied in, dependencies installed, and a verified health check. Not for merging finished worktrees; use worktree-merge. Not for closeout; use branch-closeout.

1 skill

Integrates finished worktree branches through one throwaway integration branch, testing after each merge and running the full suite before the main line moves, with exact rollback on failure. Not for creating worktrees; use worktree-create. Not for closeout; use branch-closeout.

1 skill