Run an evaluator-gated performance optimization loop with durable WorkBuddy artifacts and safe handoffs. Use when the user wants measurable performance/optimization work (latency, throughput, memory) driven by a pass/fail benchmark rather than a one-off review. Triggers: 'optimize performance', 'reduce latency'…
Configurable orchestrator that sequences planning/execution/review stages as ordered WorkBuddy skill invocations with a task-list state and resume support. Use to run a repeatable multi-stage workflow (interview → plan → execute → review → QA). Triggers: 'run the pipeline', 'autopilot pipeline', 'sequence stages'…
Strategic planning with optional interview, consensus (Planner→Architect→Critic), and review modes. Use to scope vague ideas, produce quality-gated work plans, or review an existing plan before implementation. Triggers: 'plan this', 'let's plan', 'ralplan', 'review this plan', 'plan --consensus', 'plan --review'.
Clean-room interview-driven planner with three voices (Metis clarifies, Momus challenges, Oracle synthesizes), then hands off to ultragoal/team. Use for rigorous pre-execution planning when ambiguity is risky. Triggers: 'prometheus strict', 'strict plan', 'interview-driven plan', 'rigorous planning before execution'.
Self-referential persistence loop that keeps working on a task until it is fully complete and architect-verified, with parallel delegation, automatic retry, and a mandatory verification gate. Use when guaranteed completion matters. Triggers: 'ralph', 'don't stop', 'must complete', 'finish this', 'keep going until…
Alias for plan --consensus. Triggers iterative Planner→Architect→Critic consensus planning with RALPLAN-DR structured deliberation. Use when you want multi-perspective sign-off on a plan before execution. Triggers: 'ralplan', 'consensus plan', 'plan --consensus'.
Create and execute durable repo-native multi-goal plans. Break a brief into tracked goals, drive them to verified completion, and steer as findings change.
Parallel execution engine for high-throughput task completion — ground context, set acceptance criteria, fan out independent work via the Agent tool, and close with lightweight evidence. Triggers: "ultrawork", "ulw", "parallel execution", "run tasks in parallel".
Visual frontend delivery loop — build or restyle UI from a generated reference, a static reference, or a live URL, iterating with measured visual-verdict scoring and pixel-diff evidence until the implementation matches and leaves a reproducible design system. Triggers: "visual ralph", "build UI from reference", "clone…
Deprecated. Visual verdict scoring is now part of the visual-ralph workflow; do not invoke this skill directly. Triggers: "visual verdict", "visual-ralph verdict".
Deprecated. Live-URL website cloning is now handled by the visual-ralph skill (visual implementation + visual QA). Do not invoke this skill directly. Triggers: "clone website", "clone this URL", "web clone".
Protocol for a unit of work assigned to a WorkBuddy subagent (Agent tool) — ACK, claim-safe lifecycle, evidence-backed completion, and clean blocking escalation. Triggers: "worker protocol", "subagent task lifecycle", "claim task", "team worker".
One-line summary of what this skill does, including natural trigger phrases. Use when the user says "my-skill", "do X", or needs Y.
★not rated 2 2mo agoA36 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: