Create a new AgentHub collaboration session with task, agent count, and evaluation criteria. Use when the user runs /hub:hub-init or asks to start a multi-agent competition on a task.

Designs a realistic, execution-aware biomedical study version under explicit constraints of samples, time, budget, data access, lab capacity, team skill, and validation resources. Always use this skill when the user has a real study idea, a candidate route, or a partially framed project but cannot assume ideal conditions. If critical feasibility inputs are missing, first clarify what resources are currently available, what resources may be obtainable, and what resources are realistically unavailable. Do not invent access, capabilities, collaborations, or validation resources. Focus first on feasibility-constrained study framing, route narrowing, dependency control, and minimum viable study design.

Orchestrate free opencode workers from Claude Code to cut token costs. Use when delegating grunt work to a single worker or a parallel swarm (scout/coder/tester) with worktree isolation, benchmarking against opencode, or when the user says "spawn a worker", "swarm", "delegate to opencode", or "/oc".

Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template helpers, audit chart security (RBAC, network policies, pod security), manage subcharts, or run helm lint/test.

/em:hard-call — Framework for decisions with no good options. Use when every option is painful and a structured 10/10/10 + regret-minimization pass is needed — e.g. choosing between a layoff and a down round, or killing a beloved product line.

Generates complete FAERS-style pharmacovigilance disproportionality research designs from a user-provided drug class, comparator strategy, adverse-event domain, and patient-group stratification. Always use this skill whenever a user wants to design, plan, or build a spontaneous-report safety signal study using FAERS or a similar pharmacovigilance database, especially when the article logic includes product selection, indication-group stratification, MedDRA-based adverse-event extraction, serious-case filtering, suspect-drug and concomitant-exclusion logic, reporting odds ratio analysis, comparator-drug benchmarking, cross-drug comparison, and cautious signal interpretation without causal overclaiming. Covers five study patterns (single-drug disproportionality workflow, multi-drug class comparison workflow, indication-stratified workflow, comparator-controlled signal screening workflow...

Compact the current conversation into a handoff document for another agent to pick up. Save to a user-configured location (OS temp, home folder, or per-project .handoff/), redact secrets before write, suggest skills for the next session, and auto-load the latest handoff on the next SessionStart. First-run setup asks where to save so the project folder never gets cluttered. Use when the user says 'hand this off', 'handoff doc', 'summarize this for a new session', 'compact this conversation', 'I'm ending this session', 'pick this up later', or any variation signaling intent to pass work to a fresh agent. Also trigger on implicit signals: the user announcing they're switching machines, ending the day mid-task, or context is growing long without a natural stopping point.

Designs primary, secondary, and exploratory endpoints for biomedical and clinical research protocols. Always use this skill when a user needs to translate study aims into operational endpoint definitions with event rules, assessment timing, composite logic, interpretability, and protocol-stage auditability. Focus on endpoint precision, feasibility, clinical meaning, ambiguity reduction, and implementation readiness rather than generic study design advice.

Docs-anchored grilling session — challenges a plan against the project's existing language (CONTEXT.md) and recorded decisions (docs/adr/), and updates those files inline as terminology and decisions crystallise. Use when user wants to stress-test a plan against documented domain language, or mentions "grill with docs".

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".

Generates complete dual-disease shared-transcriptome biomarker and hub-gene research designs from a user-provided disease pair and shared-biology direction. Always use this skill whenever a user wants to design, plan, or build a non-oncology two-disease transcriptome study centered on per-disease differential expression, shared-signal intersection or concordance, PPI-based hub-gene prioritization, diagnostic evaluation across both diseases, immune infiltration context, pathway interpretation, and optional orthogonal validation. Covers five study patterns (shared-DEG-first workflow, hub-gene-first shared-biomarker workflow, hybrid shared-biomarker compression workflow, immune-context shared-biomarker workflow, orthogonal validation workflow) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path...

NIH grant research skill for clinical researchers. Grill-me intake (research idea + career stage + preliminary data + environment + submission posture + known institute targets) locks down the funding strategy before any search runs. Runs a 5-facet Consensus positioning analysis (with draft Significance/Innovation language), maps the research to the right NIH institutes and study sections via RePORTER, finds NOSIs and funded overlap, and produces an editable Word document (.docx) with budget/scope-aware mechanism recommendations, submission timelines, and a mandatory program officer recommendation. Use when the user asks about research funding or makes any grant-related request (e.g., 'grants for [topic]', 'find grants for my research idea', 'what grants match my research', 'help me find NIH funding', 'grant opportunities for my research'). NIH-only scope — non-NIH funders (PCORI, DOD CDMRP, VA, foundations) are out of scope and flagged at intake.

Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader), read each verdict, decide the next move (sharpen / re-run / promote to schedule), and once a version passes, run held-back eval cases in parallel. Use when the user says "grade my agent", "make it pass the rubric", "iterate until it's good", "is it good enough", or when the orchestrator routes phase=grade-iterate. outcome_builder.py builds the user.define_outcome payload (rubric required, max_iterations clamped 1..20 — never unbounded); verdict_reader.py reads the grader result and recommends the next move; eval_scaffold.py generates held-back cases + a parallel run plan (capped at the 25-thread CMA ceiling). Distinct from stage-launch (first launch) and run-without-you (scheduling).

Google Workspace CLI operations: setup diagnostics, security audit, recipe discovery, and output analysis. Usage: /google-workspace <setup|audit|recipe|analyze> [options]

Google Workspace administration via the gws CLI (github.com/googleworkspace/cli). Install, authenticate, and automate Gmail, Drive, Sheets, Calendar, Docs, Chat, and Tasks. Run security audits and use local recipe templates and persona bundles. Use for Google Workspace admin, gws CLI setup, Gmail automation, Drive management, or Calendar scheduling.

Design evidence-discovery and validation workflows for drug repurposing studies by integrating disease mechanisms, drug-target logic, expression reversal, real-world evidence, and validation routes into a closed-loop study blueprint.

Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or terminal session owns one worktree. Use when running multiple feature branches simultaneously, isolating experimental work, or coordinating multi-agent development across the same repo.

Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test this feature".

Generates complete cross-disease shared-biomarker bioinformatics research designs from a user-provided disease pair and validation direction. Always use this skill whenever a user wants to design, plan, or build a multi-dataset study linking two related diseases through shared DEGs, enrichment, PPI hub genes, public validation, regulatory-network analysis, immune infiltration, drug-gene interaction screening, and optional qRT-PCR or cell-line validation. Covers five study patterns (shared-DEG discovery, hub-gene prioritization, regulatory-network interpretation, immune/drug follow-up, bioinformatics-plus-validation) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, and a strictly verified reference literature retrieval layer with real references only.

General Counsel advisory for startups: contract review (MSA, SaaS, NDA, DPA, employment), IP strategy, term sheet decoding, and regulatory landscape mapping. Use when reviewing any contract or term sheet, deciding when to engage outside counsel, defining IP strategy, evaluating regulatory exposure (HIPAA, GDPR, FDA, fintech), or when user mentions general counsel, GC, legal review, contract risk, term sheet, IP assignment, or regulatory exposure. NOT a substitute for licensed counsel — surfaces questions to bring to qualified attorneys.