dgilford

dgilford/ai-science-toolkit

Plugin Claude Code

Claude Code skills and domain-expert reviewer agents for AI-assisted scientific computing.

dgilford/ai-science-toolkit

Plugin Claude Code

Claude Code skills and domain-expert reviewer subagents for AI-assisted scientific computing.

dgilford/ai-science-toolkit

Instructions file CodexOpenCode

Instructions for dgilford/ai-science-toolkit, covering agents.md, shared guidance, agent-specific notes and editing rule.

dgilford/ai-science-toolkit

Instructions file

Instructions for dgilford/ai-science-toolkit, covering claude.md, purpose, installed skills, review agents (subagent panel) and agent file format & gotcha.

dgilford/ai-science-toolkit

Agent

Reviews a climate-attribution claim, result, or draft section for attribution-specific rigor — counterfactual, baseline, framing, uncertainty, model adequacy, and overclaiming. Works across probabilistic (PR/OR/ChIP), storyline, and D&A frameworks. Use when an attribution result or section needs an expert read, or as…

dgilford/ai-science-toolkit

Agent

Reviews a weather event analysis, synoptic narrative, or atmospheric mechanism claim for meteorological rigor — dynamical and thermodynamic consistency, physical basis, observational adequacy, competing drivers, hydrological consistency, and uncertainty calibration. Grounded in AMS CCM-level competence across the five…

dgilford/ai-science-toolkit

Agent

Reviews a science communication product — article, press release, social post, talk abstract, or public-facing summary — for communication effectiveness. Grounded in the full COMPASS teaching portfolio: Message Box, narrative, two-way engagement, and evidence-based communication practice. Use when a public-facing…

dgilford/ai-science-toolkit

Agent

Reviews a statistical analysis, result, or methods section for statistical rigor — estimator properties, causal identification, inference under dependence, model specification, multiple testing, uncertainty calibration, and ML validity. Grounded in advanced statistical theory and predictive modeling. Use when a…

dgilford/ai-science-toolkit

Skill Claude CodeCodex

SLASH COMMAND — type /ai-review for a comprehensive senior-engineer review of a project or repository. Orchestrates a parallel fan-out across correctness, staleness, over-baking, and claim rigor by DELEGATING to the tools that own each lane, then adds the three lanes nothing else covers — gap/opportunity hunting…

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Batch the working tree into logical, single-concern commits, then commit (and push if asked) instead of one monolithic git add -A. Use when you type /commit-batch or want your pending changes split into clean, focused commits.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Batch a dirty working tree into logical, single-concern commits instead of one monolithic git add -A. Use whenever you are about to commit and more than one file or concern has changed — survey every change, group by concern, stage each group by explicit path, write a focused message per commit, then push only if…

dgilford/ai-science-toolkit

Skill Claude CodeCodex

SLASH COMMAND — type /create-alert to author a scheduled Slack alert. Grills a fuzzy "tell me when X happens" ask into a testable trigger spec, dry-runs it live (no Slack send), and — only after you explicitly sign off on the synthesized spec — creates a claude.ai cloud routine that evaluates the trigger on a schedule…

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Update CLAUDE.md — or the canonical AGENTS.md it redirects to — with durable knowledge from the current session. Use at the end of a working session to promote new findings, renamed variables, refined definitions, or corrected assumptions into the permanent project record.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Audit a scientific figure for publication-readiness: colormaps, uncertainty, axis labels, caption completeness, and claim support. Panel-aware — judges one panel of a composite against what its shared caption and sibling panels supply, and raises a likely-deliberate choice as by-design? instead of a defect. Use this…

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Grill the user relentlessly about a plan or design, one decision at a time, until you reach shared understanding. Use when the user wants to stress-test a plan before building or uses a "grill" trigger phrase — and proactively, before any step that changes running state, allocates a shared resource (GPUs, ports…

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Create or update a durable project handoff for the next AI agent/session. Use when ending a coding/research session, switching agents, compressing context, or preparing another Claude/ChatGPT/Codex session to continue the work.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Search and synthesize scientific literature from Zotero, arxiv, bioRxiv, Google Scholar, and Consensus. Use when framing a research question, designing methods, interpreting results, mapping the field landscape, or identifying future directions.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Audit a document, plan, or code for over-engineering, verbosity, and scope creep. Use when you've just written something and want a point-by-point check before finalizing.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

SLASH COMMAND — type /pathfinder to get a navigable map of every skill and subagent and when to reach for each. Resolves the reviewer-2-vs-panel decision. Use when unsure which skill or agent to invoke, or when orienting a new session.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Pick up work from repo-local handoff state. Use when starting a new Claude Code session, switching agents, returning to a project, or asking an AI agent to reconstruct context from prior work. Named pickup rather than resume to avoid shadowing Claude Code's built-in /resume conversation picker.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

SLASH COMMAND — type /repo-init to scaffold a new repository (or retrofit an existing one) with a standard project structure. Starts with a short intake grill (--no-grill skips). Research mode by default; --package for a distributable src-layout library. Never overwrites existing files; --dry-run previews.

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Adopt a critical-reviewer stance to stress-test a claim, result, or manuscript section. For each claim: identify the baseline being compared against, name the counterfactual, surface plausible alternative explanations, and check that stated uncertainty is consistent with the strength of the claim. Use this whenever…

dgilford/ai-science-toolkit

Skill Claude CodeCodex

Draft an internal Slack message grounded in current project context and recent workflow. Use when sharing a status update, result, finding, or request with a teammate or internal stakeholder at your org.