Meta-skill for understanding and customizing Mindfold Trellis — the all-in-one AI workflow system for 11 AI coding platforms (Claude Code, Cursor, OpenCode, iFlow, Codex, Kilo, Kiro, Gemini CLI, Antigravity, Qoder, CodeBuddy). Documents the original Trellis system design including architecture, commands, hooks, multi-agent pipelines, monorepo support, and task lifecycle hooks. Use when understanding Trellis architecture, customizing workflows, adding commands or agents, troubleshooting issues, or adapting Trellis to specific projects. Modifications should be recorded in a project-local trellis-local skill, not here.
Use when encountering a bug, failing test, build failure, performance issue, or unexpected behavior in a Trellis task. Requires root-cause investigation before proposing fixes.
Use after a Trellis PRD has been approved and before implementation begins for a non-trivial task. Converts the PRD into a precise Trellis implementation plan with exact files, tests, commands, expected outputs, TDD steps, and no placeholders.
Use after each logical implementation step, after a major feature, before merge, or when stuck. Runs Trellis-first review using PRD, implementation plan, diff, specs, and verification evidence.
Use before implementing any Trellis task that changes behavior, fixes a bug, refactors code, or adds a feature. Enforces test-first red-green-refactor inside the Trellis task workflow.
Use before saying work is complete, fixed, passing, ready, merged, or safe. Requires fresh verification commands and evidence before any completion claim.
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.