superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Experiment records, session handoffs and an owner decision queue, kept inside your project's knowledge base.
Plugin slate from marketplace slate in moeyensj/slate. Commands read from the repo's manifest — 26 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
arcList slate arcs, or open a new arc (a campaign, a feature, a release step) anchored to the owner's directive in their own words.
datasetRecord how a dataset was made - its sources, the recipe that filtered and built it, the code version, its parent datasets and a manifest of the resulting files - or register one that already exists, so experiments can reference it by id and hash. Use when the user builds, filters, subsets or registe
decisionsShow the queue of questions waiting on the owner across all slate arcs, and record the owner's rulings verbatim. Use when the user asks what is waiting on them, or rules on an open question.
experimentRun an experiment as a record in the knowledge base - the plan (question, hypothesis, prediction, decision rule, controls) is written before the run, one agent runs it, and the result is logged with enough provenance to reconstruct it. Use when the user asks to run, measure, benchmark or compare som
filesShow which input and output files slate experiments and datasets hold on disk, mark the ones nobody needs any more for deletion, and sweep marked files after a dry run.
findingsSummarise what a set of slate experiments established - the important conclusions across an arc or the whole knowledge base, each one cited to the experiments behind it, with the citations checked by script.
handoffEnd a session by writing a handoff note into the knowledge base - the first action for the next session, verified state, what is still running, open owner decisions, traps. Use when the user asks for a handoff or wants to stop and continue later.
harvestSettle slate experiments whose runs finished while no session was watching - verify their outputs, record the result, and conclude them.
initSet up a knowledge base for slate - writes slate.toml, chooses where arcs live, and connects the issue tracker (beads or none).
pickupStart a session from a slate handoff note - lists the open handoffs, checks the chosen note against the present state of the repositories and the tracker, and resumes at its first action. Use when the user wants to pick up, continue or resume earlier work.
promoteTurn a concluded slate experiment or a settled ruling into a durable knowledge-base note that cites its evidence; with no argument, list what is ready to promote and which notes rest on evidence that has aged.
rerunRepeat a concluded slate experiment against the exact recorded state - commits, uncommitted changes, inputs - and report whether the result reproduces.
experimenterRuns one slate experiment from a complete brief - writes the run script and configuration into the record, passes the pre-run check, starts the run, and records the result as facts. Spawned by /slate:experiment; short-lived.
"${CLAUDE_PLUGIN_ROOT}/bin/slate" status 2>/dev/null || true
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Query Trackio projects, runs, and metrics using the `trackio` CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system metrics. Designed for LLM agents and automation scripts.
1 skill
Use Amplitude as an expert analyst — instrument Amplitude, discover product opportunities, analyze charts, create dashboards, manage experiments, and understand users and accounts.
36 skills · 1 MCP server
ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows
2 skills · 1 command · 3 agents
Plan, build, and debug Zoom integrations across REST APIs, Meeting SDK, Video SDK, webhooks, bots, and MCP workflows. Search meetings, retrieve recordings, access transcripts, and design AI-powered Zoom experiences.
44 skills · 3 MCP servers
Personal knowledge brain for your coding agent — hybrid search, synthesis, and durable cross-session memory, plus a curated brain-first skill set.
80 skills · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.