AI Agent Workflow Collection

Analyze architecture for consistency between ADRs and AD, completeness, and quality issues. Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or periodically to detect drift.

Refine and validate system-level ADRs through targeted clarification questions. Use when ADRs need review, gaps need filling, or ADR status must be approved before architecture generation.

Generate a full Architecture Description (AD.md) from accepted ADRs using multi-agent DAG orchestration. Use when accepted ADRs exist and you need to produce or update unified architecture documentation.

Reverse-engineer architecture from an existing codebase to create ADRs documenting discovered decisions. Use when bootstrapping architecture documentation for brownfield projects.

Interactive PRD exploration and system-level ADR creation for greenfield projects. Use when transforming a PRD or high-level system description into Architecture Decision Records.

Analyze evaluation results and close the loop. Specification failures create local CDRs to fix agent rules; generalization failures go to evaluator backlog.

Refine, cluster, and accept draft criteria into the published goldset. Isolates 20% holdout split and publishes goldset.md + goldset.json.

Generate executable graders and configs from goldset. Generates Python graders / metrics and auto-runs unit tests to verify grader correctness.

Initialize evals/{system}/ directory structure for evaluation system following EDD principles (Standalone). Choose PromptFoo or DeepEval based on tech stack, generate security baseline.

Extract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes proposed criteria to .adlc/drafts/evals/.

Run evaluations and validate evaluator quality (SLA compliance, TPR/TNR, statistical accuracy). Executes PromptFoo or pytest DeepEval.

Review, accept, reject, or defer Context Directive Records (CDRs) discovered by levelup-init or proposed by levelup-specify. Interactive one-CDR-at-a-time workflow.

Reverse-engineer Context Directive Records (CDRs) from an existing codebase for contribution to team-ai-directives. Use when bootstrapping team knowledge from brownfield projects.

Compile accepted Context Directive Records (CDRs) into team-ai-directives artifacts and create a draft PR. Builds context modules, evals goldensets, and/or skills based on CDR context types.

Extract Context Directive Records (CDRs) from the current session after completing work. Identifies reusable patterns (rules, personas, examples, evals) and captures directive compliance cases for team-ai-directives.

Mission-driven SDD orchestrator: take a feature description, structure it into a Mission Brief (goal, constraints, success criteria), generate an ordered step list with prompts that trigger installed SDD skills via model invocation or command-file discovery, and walk those steps to converged implementation. Use when you want an end-to-end specify → plan → implement ↔ converge loop with gates, a circuit breaker, resume, and an audit trail — without YAML files or per-framework profiles.

Read-only analysis of PDR↔PRD consistency, PDR quality, cross-PDR conflicts, and staleness. Outputs a structured markdown report with severity-assigned findings. Use after /product.implement or periodically to detect drift.

Refine and validate Product Decision Records through targeted clarification questions. Review PDR completeness, detect conflicts, approve decisions, and update status to Accepted. Use before /product.implement.

Generate a full Product Requirements Document (PRD.md) from accepted PDRs using multi-agent DAG orchestration. Reads individual PDR files, generates PRD sections from templates, validates output, and promotes accepted PDRs to memory. Use after /product.clarify.

Reverse-engineer Product Decision Records (PDRs) from an existing codebase and documentation using multi-agent feature-area analysis (brownfield). Use when documenting product decisions inferred from an already-built product.

Interactive PRD exploration and Product Decision Record (PDR) creation for greenfield products. Facilitates product discovery discussions, surfaces trade-offs, and documents decisions as individual PDR files. Use when starting a new product or major pivot.

Bootstrap the session with team AI directives context (constitution, CDR index, PDR/ADR indexes, skill registry). Runs automatically at session start via the event hook.

Interactively create or amend the team constitution in team-ai-directives. Use when bootstrapping a new team AI directives, establishing team-wide principles for the first time, or amending existing ones.

Manually re-scan team context modules and produce a structured discovery table with relevance assessments. The CDR index is already in the system prompt; use this for explicit re-discovery.