Provider-neutral skills for coordinating AI agents, covering acceptance gates, context budgets for subagent handoffs, adversarial debate between options, and a Python harness for bounded, resumable agent work.
@wenyuchiouUse when about to commit or push a diff that touches two or more locale variants of one file stem, adds catalog or listing…
@wenyuchiouUse when launching parallel or background subagents, or when a handoff, log, or result would be more than a short summary…
@wenyuchiouUse when a consequential decision has two plausible, materially different options and you are about to pick one. Runs two opposed…
@wenyuchiouUse when a plan, prompt, or doc still names agent-output-reconciler. Since 0.6.0 reconciliation is step 1 of…
@wenyuchiouUse when a plan, prompt, or doc still names agent-plan-act-reflect. Deprecated in 0.6.0; ordinary iterate-until-it-passes work…
@wenyuchiouUse when a plan, prompt, or doc still names agent-shared-memory. Since 0.6.0 proposal-only coordination memory is the Durable…
@wenyuchiouUse when about to run two or more subagents, workflow lanes, or delegated CLI executors on one goal. Gives each lane a role, a…
@wenyuchiouIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
