executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
graph-writeWrite, propose, commit, repair, and nudge Potpie Context Graph records safely.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when the task is about adding durable memory, proposing graph mutations, committing plans, handling inbox items, running graph quality checks, or nudging agents from graph evidence.
potpie record, potpie graph propose, potpie graph commit, potpie graph mutate, potpie graph mutation-template, potpie graph bulk apply, potpie graph import, potpie graph repair, potpie graph history, potpie graph inbox, potpie graph quality, or potpie graph nudge.graph mutate wrapper.../graph-read/SKILL.md.../workspace-boundaries/SKILL.md.../runtime/SKILL.md.../auth-integrations/SKILL.md.graph propose to validate and stage, then graph commit with explicit approval and verification as needed.graph mutation-template before authoring payloads when the DSL or entity label is uncertain.graph inbox, graph quality, graph history, and graph inspect to review pending, stale, or questionable graph state before applying more writes.record as a convenient durable-memory write path and graph nudge as a bridge from graph evidence to agent guidance.references/workflow.md — write command matrix, flat mutation DSL, approval/verification, inbox, quality, bulk, and nudge flows.references/troubleshooting.md — malformed payloads, review gates, expired plans, bulk failures, inbox states, and quality repairs.