crabfleet-supervisor
Crabfleet session tree, spawning, summaries, and transcripts.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Crabfleet session tree, spawning, summaries, and transcripts.
Operate Kilroy Attractor pipelines end-to-end: ingest English requirements into DOT graphs, validate graph semantics, run and resume pipelines with run config files, configure provider backends (cli/api), and debug runs from logs_root artifacts and checkpoints.
Implements a new MCP tool for a Backlog API endpoint from its documentation URL (e.g. https://developer.nulab.com/docs/backlog/api/2/get-space/). Use this skill when you need to add or update a tool in this MCP server based on a Backlog API spec.
Boucle d'amélioration nocturne autonome du simulateur diagnostic microsolder. Pattern autoresearch — tune engine_params.json (knob layer, préféré) ou modifies simulator.py / hypothesize.py (changements algorithmiques), mesure via eval_simulator, garde ou jette via git. NEVER STOP, autonomie totale.
Router for choosing the next Maestro skill or lifecycle recipe.
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log to draft the six root pages and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the `brain` CLI. Run it after brain-setup.
Design and create a new hive task through guided conversation. Walks the user through problem definition, eval design, constraint specification, repo scaffolding, baseline testing with iteration, and upload. Use when user wants to create a new task, add a benchmark, or publish a challenge to the swarm.