Cuts a full release: changelog section, per-plugin version bumps, per-plugin tags, and a GitHub release — with approval gates before anything irreversible.
A disciplined playbook for splitting work across multiple agents with dependency graphs, handoff contracts, approval gates, and verified synthesis.
An end-to-end npm release runbook: local verification, tag push, approval-gated GitHub Actions publish, then post-publish verification and cleanup.
A gated end-to-end runbook for releasing Compass: sync main, bump versions, open the PR, tag the merge commit, build six platforms, and verify every download.
An autonomous 13-step loop that pulls the next TaskMaster task, dispatches a complexity-tiered subagent, and only marks it done after evidence-gated triple verification and a reachability sweep.
Orchestrator skill that runs task waves across isolated git worktrees, verifies each worker branch by evidence, merges sequentially, and ends with a single PR.
Designs property-service operations with an ontology plus DMAIC control plan covering work orders, dispatch, quotes, evidence, CTQs and control dashboards.
A rulebook for delegating independent, non-overlapping tasks to parallel agent workers or selected persistent role sessions.
A judgment skill that returns a single artifact-free CONTINUE/STOP verdict on whether a work traversal earns its cost or is just process ceremony.
Sends one question to several Chinese AI platforms, preserves each raw answer and citation, aligns the claims point by point, and verifies them with authoritative evidence across four separate reports.
A scheduled maintenance skill that closes already-shipped issues and keeps a curated 15–25 issue contributor backlog for the awesome-claude repo.
Turns any source that describes how a task gets done — a SKILL.md, chat log, runbook, or plain prose — into a runnable Flowtrace DAG and drives the full run lifecycle to verify it.
Rules for passing subagent results through files instead of TaskOutput so the main conversation's context stays clean.
Helps you choose between BoltzGen, BindCraft, RFdiffusion and Germinal, then lays out the full de novo binder design pipeline.
A standardized five-stage multi-agent pipeline — research, plan, validate, TDD implement, review — using background agents and file-based handoff.