ade

Archive the current plan after completion

Launch Generator + Evaluator agent team to execute the approved plan

Research context, ask questions, and create a plan scaled to the scope of the work

Show current ADE build progress and evaluator scores

Use this agent as a team member during /ade:execute to test and score features implemented by the generator. The evaluator uses pluggable rubrics and testing tools to grade work with hard thresholds. <example> Context: The execute command is launching the agent team. user: "Build the approved plan" assistant: "Spawning the ade-evaluator as a team member to test and score features as the generator implements them." <commentary> The evaluator is spawned alongside the generator. It waits for features to review, loads rubrics, tests them, and sends scored feedback. </commentary> </example> <example> Context: Generator messaged that a feature is ready for review. user: "Feature: User Registration. Status: Ready for review." assistant: "The evaluator loads relevant rubrics, tests the feature, scores each criterion, and sends detailed feedback." <commentary> Evaluator receives handoff from generator, runs adversarial testing, scores against rubric thresholds, and reports back. </commentary> </example>

Use this agent as a team member during /ade:execute to implement features from an approved plan. The generator builds the app feature-by-feature, commits to git, and hands off to the evaluator for scoring. <example> Context: The execute command is launching the agent team. user: "Build the approved plan" assistant: "Spawning the ade-generator as a team member to implement features from the plan." <commentary> The generator is spawned as part of an agent team alongside the evaluator. It implements features and messages the evaluator for review. </commentary> </example> <example> Context: Generator received feedback from evaluator and needs to iterate. user: "Evaluator scored originality 5/10 — needs distinctive color palette" assistant: "The generator iterates on the feature based on evaluator feedback until all rubric scores pass." <commentary> Generator accepts evaluator feedback without argument and iterates until all criteria pass threshold. </commentary> </example>

This skill should be used when the user asks about evaluation methodology, scoring rubrics, testing tools, "how does scoring work", "evaluation criteria", "rubric format", "add a rubric", "create testing tool", "evaluate my feature", "run evaluation", "why did evaluation fail", or needs guidance on adversarial evaluation, graded scoring, or hard thresholds in the ADE workflow. Make sure to use this skill whenever the user mentions quality assessment, code review scoring, feature validation, or wants to understand why a feature passed or failed evaluation.

Use when asking about the ADE build process, how the generator works, iteration strategy, "why is the generator doing X", "how does building work", "commit conventions", "pivot vs refine", or understanding the implementation phase of the ADE workflow. This skill covers the Generator's methodology for implementing features from approved plans, including the 4-phase build cycle and strategic iteration.

Use when the user wants to plan any work — building an app, adding a feature, fixing a bug, solving a problem, refactoring, or any task that benefits from thinking before doing. Triggers on "plan", "build me", "I want to", "fix this", "add a", "we need to", "how should we", or when the user describes something they want done. This skill guides interactive discovery, research, and planning scaled to the scope of the work — from a quick task plan to a full product spec.

1 hook across 1 event