Automation
Task automation and scripting
agoragentic-execute
by rhein1
Preview and execute a bounded Agoragentic capability after explicit owner or host approval. Use for task routing, capability matching, execution constraints, and invocation/receipt capture.
Skill: Email Triage
by strikersam
If asked to integrate with the repo, save triage reports to docs/triage/email-YYYY-MM-DD.md
opentrons-magnetic-block
by jkitchin
Opentrons Magnetic Block for Flex - unpowered magnetic bead separation using gripper-based labware movement with high-strength neodymium magnets for DNA/RNA purification, immunoprecipitation, and bead-based workflows
python-jax
by jkitchin
Expert guidance for JAX (Just After eXecution) - high-performance numerical computing with automatic differentiation, JIT compilation, vectorization, and GPU/TPU acceleration; includes transformations (grad, jit, vmap, pmap), sharp bits, gotchas, and differences from NumPy
design-of-experiments
by jkitchin
Expert guidance for Design of Experiments (DOE) in Python - interactive goal-driven design selection, classical DOE (factorial, response surface, screening), Bayesian optimization with Gaussian processes, model-driven optimal designs, active learning, and sequential experimentation; includes pyDOE3, pycse, GPyOpt, scikit-optimize, statsmodels
travel-requirements-expert
by tdimino
Systematically gather comprehensive travel itinerary requirements through structured discovery questions, MCP-powered research (Perplexity, Exa), and expert detail gathering. Use when users request travel planning, itinerary creation, or trip assistance requiring deep research and personalized requirements gathering. Outputs detailed requirements specification with day-by-day itineraries.
phab
by lanej
Use phab CLI for Phabricator task management, code review workflows, revision creation and updates, with Git integration and auto-detection features.
scientific-workflows
by jkitchin
Expert assistant for choosing and implementing scientific workflow tools - from simple joblib caching to complex orchestration with Prefect, Parsl, FireWorks, and quacc. Recommends the simplest solution that meets requirements.
python
by lanej
Use uv for fast Python project management, script execution, dependency handling, and tool installation. AVOID pip - always use uv commands (uv add, uv sync, uv run) instead.
ralph-wiggum
by jkitchin
Autonomous AI coding loop for unattended development - lets Claude work continuously on tasks while you sleep, with mandatory sandbox enforcement for safety
spec-driven-implementation
by xbklairith
Use when ready to implement designed features - breaks design into TDD tasks (Red-Green-Refactor), tracks progress with checkboxes in tasks.md, enforces strict testing discipline. Activates when user says "implement this", "let's code", "start execution", mentions "tasks", "TDD", or uses /dev-workflow:spec commands (tasks, execute).
kanban
by flpbalada
Visualize and optimize workflow with Kanban boards. Use when managing team
cognitive-load
by flpbalada
Design experiences that optimize mental resources using Cognitive Load Theory.
cognitive-fluency-psychology
by flpbalada
Apply cognitive fluency principles to improve clarity, trust, and conversion.
/onex:pr_review_bot — one command, one typed result
by OmniNode-ai
Run the ONEX PR review bot pipeline — fetches diff, dispatches multi-model adversarial review,
trent-cleanup-panes
by trentshaines
Clean up tmux panes. Use when user wants to close/kill all other panes, clean up tmux window, or reset pane layout.
batch-market-cap
by OctagonAI
Retrieve market capitalization data for multiple companies at once using Octagon MCP. Use when comparing valuations across peers, screening by market cap, or analyzing a portfolio's composition by company size.
scientific-eda
by ericmjl
Defensive exploratory data analysis for scientific data (CSV, FASTA, etc.). Context-first, human-guided; one plot at a time, ask why before executing, append-only journal per session, scripts with PEP723 and uv run, WebP plots. Use when opening data files for EDA or when the user wants guided scientific data exploration.
ml-experimentation
by ericmjl
Conduct machine learning experiments from planning through evaluation and report writing. Use when running ML experiments, testing hypotheses, training models, or writing up results. Covers single-hypothesis scoping, fast iteration loops, targeted logging, JOURNAL.md protocol, data-backed diagnostic plots, and scientific report writing.
api-enhancement-scan
by osdlc
Given a library or module name, survey every call site of it across the codebase — fanning out subagents over independent codebase sections — and surface recurring caller-side patterns (repeated boilerplate, copy-pasted wrappers, awkward argument plumbing, repeated post-processing) that a new or enhanced API on the called module would absorb. Returns ranked enhancement opportunities, each backed by real call-site citations. Use when asked to find API improvement or enhancement opportunities for a module, library, or package, to spot missing affordances, or to understand how a module is actually used by its callers. Pass --in to survey only named packages or directories instead of the whole project, and --workflow to have it propose a reusable Workflow script for the survey instead of running it ad hoc.
deepswarm
by amanning3390
Use when running parallel AI workers for any long-running or multi-turn batch API task. Auto-calculates optimal workers + stagger. Supports tiered delegation (V4 Pro orchestrator → V4 Flash workers). 99.95% API success rate at scale.
ai-dev-loop
by shipshitdev
Orchestrate autonomous AI development with task-based workflow and QA gates
bug-finder
by osdlc
Sweep an entire codebase for real bugs and fix them. Partitions the tree into module-boundary territories, then runs three chained agent workflows — scan (three altitudes: in-function, in-module, in-library) → adversarial validate → fix → verify-fix → land — so a fresh agent performs every step and the orchestrating session never reads source itself. Opens one PR per module boundary, then surveys the open PRs, computes the conflict matrix deterministically with git merge-tree, and merges the overlapping bugfix branches into each affected PR in a single aggregated push so CI runs once per PR, not once per fix. Pass --bomb for maximum parallelization.
sc-task
by htlin222
Execute complex tasks with intelligent workflow management and cross-session persistence. Use when managing large projects, tracking progress across sessions, or orchestrating multi-phase work.