Skill Claude CodeCodex
Create or update a project roadmap with major milestones. Generates the configured roadmap artifact (default .ai-factory/ROADMAP.md) — a strategic checklist of high-level goals. Use when user says "roadmap", "project plan", "milestones", or "what to build next".
Skill Claude CodeCodex
Run a standalone read-only rules compliance gate against changed files or a git ref. Use when you need a dedicated project-rules check without a full review or verify pass.
Skill Claude CodeCodex
Add project-specific rules and conventions to the configured RULES.md artifact. Each invocation appends new rules. These rules are automatically loaded by /aif-implement before execution. Use when user says "add rule", "remember this", "convention", or "always do X".
Skill Claude CodeCodex
Security audit checklist based on OWASP Top 10 and best practices. Covers authentication, injection, XSS, CSRF, secrets management, and more. Use when reviewing security, before deploy, asking "is this secure", "security check", "vulnerability".
Skill Claude CodeCodex
Generate professional Agent Skills for AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates. Use when creating new skills, generating custom slash commands, or building reusable AI capabilities. Validates against Agent Skills specification.
Skill Claude CodeCodex
Transfer reusable prevention lessons from another AI Factory project into the current project's skill-context through /aif-evolve. Use when building a similar project and you want to avoid problems already captured in another project's patches without copying or revealing that project's identity, paths, or identifiers.
Skill Claude CodeCodex
Verify completed implementation against the plan. Checks that all tasks were implemented, nothing was forgotten, code compiles, tests pass, and quality standards are met. Use after "/aif-implement" completes, or when user says "verify", "check work", "did we miss anything".
Skill Claude CodeCodex
Load the essential AI Factory project context before work begins. Reads configured DESCRIPTION, ARCHITECTURE, ROADMAP, RESEARCH, RULES, and applicable AGENTS.md files, then returns a compact session handoff suitable for continuing or forking. Use at the start of a new session or after context loss.
Skill Claude CodeCodex
Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".
Agent
Read-only background best-practices sidecar for the current implementation scope. Use from implement-coordinator after code changes when a concise maintainability review is needed.
Agent
Read-only background commit preparation sidecar for the current implementation scope. Use from implement-coordinator when deciding whether a final /aif-commit step can be streamlined.
Agent
Read-only background documentation drift sidecar for the current implementation scope. Use from implement-coordinator after code changes when deciding whether /aif-docs should run automatically.
Agent
Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via claude --agent implement-coordinator.
Agent
Execute a single plan task in an isolated worktree — implement, verify, and return. Spawned by implement-coordinator for parallel task execution. Cannot spawn child agents — runs quality checks locally.
Agent
Convert failed evaluation rules into precise, minimal fix instructions for the refiner. Use proactively within /aif-loop when evaluation fails.
Agent
Evaluate artifact strictly against active loop criteria and return structured pass/fail output. Use proactively within /aif-loop when an objective verdict is needed.
Agent
Prepare invariant and consistency checks for the current loop iteration. Use proactively within /aif-loop in parallel with producer.
Agent
Route reflex-loop execution to the next role based on run state, stop guards, and last evaluation. Use proactively within /aif-loop when deciding the next step.
Agent
Prepare lightweight performance checks (RPS/latency budget assertions) for the current loop iteration. Use proactively within /aif-loop in parallel with producer.
Agent
Build a short, execution-focused iteration plan (3-5 steps) aligned to active rules. Use proactively within /aif-loop when the next iteration plan is needed.
Agent
Produce the single markdown artifact for the current loop iteration from task and plan. Use proactively within /aif-loop when artifact generation is needed.
Agent
Apply critique issues to produce a minimally changed improved artifact. Use proactively within /aif-loop when refinement is needed after failed evaluation.
Agent
Prepare lightweight test checks for the current loop iteration without blocking execution. Use proactively within /aif-loop in parallel with producer.
Agent
Iteratively polish a plan by launching plan-polisher in a loop until critique passes or max iterations reached. Use via claude --agent plan-coordinator.