Teaches Claude to manage and sync every agent's MCP servers from a single mcptoon config file.
Writes and validates Python protocols for Opentrons OT-2/Flex robots — pipetting, serial dilutions, PCR, and hardware module control.
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery that extracts constraints, classifies project scale, and hands off to spec generation.
Redesigns a personal or team operating system as a supervised learning loop with Four-C diagnostics and one bounded, reversible experiment.
A bounded multi-agent command protocol that splits genuinely independent work across 5–100+ isolated workers, verifies outputs independently, and integrates serially.
Teaches Claude to drive the `hab` CLI to inspect, create, update and operate Home Assistant safely from the terminal.
Fan one task out to N parallel agents, score them against a rubric, then pick a base and graft the best parts of the losers into a single synthesized result.
Enforces a strict output contract for claude-mem observer jobs on Grok Bot: either skip_summary or exactly one observation XML, never prose.
A coordination adapter skill that keeps multiple AI writers from colliding in one repo using messages, acknowledgements, and TTL-bounded advisory file reservations.
Delegates a task to the AGY (Antigravity) CLI only when the caller explicitly picks that runtime, with a disclosed permission posture and returned run evidence.
Generates a structured album progress dashboard with per-phase completion percentages, a track status table, and blocking items.
Reference skill for uploading media from URLs or local paths to BulkPublish and batch-creating posts across social platforms.
A maintainer-only workflow for qualitatively studying private short-drama project chains and promoting findings into public references only after de-identification, blind eval, and independent review.
Takes approved posts from outputs/, generates infographic visuals for flagged posts, and schedules everything across platforms through Blotato MCP with a mandatory approval gate.
Turns Claude into an orchestrator on explicit /director invocation: it defines, divides, decides and reviews while lower-tier agents do the actual work.
Collects every operation event across a multi-agent system and turns it into a trace_id-linked evidence chain plus vector index for audit and replay.
One-time setup that detects your project's stack, interviews you for a handful of preferences, and writes the shared JSON config every other absolute-* command reads.
Delegates one-shot or flat parallel batches of work to cc-fleet provider models (DeepSeek/GLM/Kimi/Qwen/MiniMax/Codex/Claude) via the headless `cc-fleet subagent` CLI.
Runs headless provider LLMs (DeepSeek, GLM, Kimi, Qwen, MiniMax) via the cc-fleet CLI for one-shot answers or lock-free parallel fan-out.
Teaches Claude to author and run multi-phase, resumable JS orchestration scripts over cc-fleet provider subagents.