framework

Initialize or refresh the project memory bank. Use when the user wants to set up or regenerate the project's memory files. Not for updating one memory file after it exists or editing a single rule directly.

Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface.

Design and validate a new SaaS's architecture into an INSTALL.md via Q&A and stack comparison. Use when the user starts a project, chooses a stack, or picks an architecture pattern. Not for editing an existing stack or scaffolding code.

Route a request to generate a context artifact (skill, rule, agent, command, or hook) to its generator when the kind is unnamed. A named kind triggers its generator directly. Not for listing existing artifacts.

Generate a router-based skill across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor a skill, or turn a workflow into one. Not for other artifacts like rules, agents, commands, hooks.

Generate a coding rule that governs editor and agent behavior across the host AI tools. Use when the user wants to write, add, or refactor a rule, convention, or coding standard. Not for other artifacts like skills, agents, or hooks.

Generate an agent across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor an agent, subagent or specialized role. Not for other artifacts like skills, rules, commands, hooks.

Generate a flat slash command across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor a one-shot slash command. Not for multi-step skills or other artifacts like rules, agents, hooks.

Generate a valid Mermaid diagram from a written source through a plan, generate, review loop. Use when the user wants to turn an architecture, lifecycle, or flow into a Mermaid diagram. Not for other diagram formats or image rendering.

Capture durable project learnings from the conversation or git history into memory, a record, a rule, or a skill. Use when the user asks to capture, record, or remember a decision or lesson. Not for AI preferences or already-captured items.

Explore the current project across its tooling, context, and codebase. Use to survey what is installed, see what is available, or find which skill, agent, or rule fits a goal. Not for choosing the next step or running an item; it only points.

Manage the project's recipes and how-to sheets. List them as a table, or create and update one from the canonical template. Use when the user wants to list, create, update, or cook a recipe.

Orchestrate the full dev flow, a free-form request to shipped code, every step delegated. Use to take a request end to end, not a single step. Interactive by default; say auto for unattended.

Turn a request, ticket, or file into a phased implementation plan. Use to plan a feature before building, or to turn a ticket into phases. Do NOT use to write code or review a diff.

Write an existing plan's code, phase by phase, until every acceptance criterion holds. Use when a plan exists and needs implementing. Do NOT use to write a plan, review a diff.

Assert the work behaves by iterating the project's coding assertions until they pass, plus optional architecture and frontend facets. Use to validate an implementation. Not for reviewing or writing tests.

Audit a codebase read-only across seven quality pillars into one ranked report. Use when the user wants to assess, health-check, or audit a codebase or one pillar. Not for fixing findings, reviewing a change, or checking a feature works.

Review a diff read-only on three axes, code, behavior versus the plan, and relevancy, into one verdict report. Use before shipping a change. Not for fixing findings or auditing a codebase.

Write and iterate tests until they pass, or validate a user journey end to end in the browser. Use when the user wants to add coverage, find what's untested, or walk a flow. Not for auditing test health or debugging a failure.

Improve code across four axes (cleanup, performance, security, architecture) by scanning and fixing, or applying a pushed audit report. Use when the user wants to refactor, optimize, harden, or remove code. Not for read-only diagnosis or adding tests.

Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.

Run an iterative agent loop that retries until a runnable success condition passes. Use when the user says "for sure", "keep trying until", or wants guaranteed completion against a success command. Not for one-shot tasks or uncheckable goals.

Split the user prompt into independent todos and run one executor agent per todo in parallel, then report a minimal table. Use when the user says "todo" or asks to fan out a multi-part request into parallel implementations.

Drive the async-dev pipeline from one entry point, whether setup, run, or review. Use when the user wants to install async dev, run a ready issue, or address PR review comments, or on a webhook trigger. Not for plain status checks.

Retrieve and display a ticket from the configured ticketing tool. Use when the user wants to see, show, or look up a ticket's details. Not for creating a ticket, or commenting on, transitioning, or reassigning one.

Turn a feature or epic into a prioritized, estimated, INVEST-compliant user-story backlog in the tracker. Use when the user wants to create, split, estimate, or prioritize user stories. Not for source code or a PRD.

Generate a structured Product Requirements Document from a need, idea, or brainstorm, confirmed before save. Use when the user wants to draft or generate a PRD or product requirements. Not for user stories or a technical plan.

Generate or refine a spec, a feature's immutable contract, from a request, a PRD, or review findings. Use to draft or refine a spec. Do NOT use to write code, a full PRD, or change a locked spec.

Clarify a vague idea through deep questioning until it is precise enough to act on. Use when the user surfaces a half-formed idea or under-specified request, or asks to brainstorm or refine. Not for scanning an artifact for gaps or writing code.

Rethink just-completed work against an agreed plan, classifying findings as deal-breaker, suggestion, or correct, with a confidence score. Use to challenge or critically review recent work. Not for line-by-line style review or writing code.

Toggle terse output mode (lite, full, ultra) that drops filler while code and errors stay verbatim, and report token savings. Use to condense output, switch intensity, or check savings. Not for editing prose or compressing code.

Scan a markdown artifact (idea, stories, PRD, spec) for blind spots into a shadow report grouped by category and severity. Use to find gaps or what is missing in a written artifact. Not for interactive Q&A or code review.

Verify factual claims in a text against authoritative sources and rewrite it with footnote citations, hedging the unconfirmed. Use to fact-check, verify a claim, or cite sources on request. Not for judging code or clarifying requirements.

Smoke-test that confirms the aidd-ui plugin loads. Use when the user wants to verify the alpha aidd-ui plugin is installed and reachable. Not for real UI or UX design work.

Initialize a project repository with git init, a default branch, a bootstrap commit, CONTRIBUTING.md, and optionally the remote. Use when the user wants to init or set up a new repo, or publish to a remote. Not for committing, opening a PR, or tagging.

Create an atomic git commit with a conventional message, optionally pushing. Use when the user wants to commit changes, optionally pushing the branch. Not for amending, rebasing, opening a pull request, or tagging a release.

Create a draft pull or merge request from the current branch, in whatever VCS tool the project uses. Use when the user wants to open a pull or merge request. Not for committing, pushing, or merging a branch.

Cut a semver release with an annotated tag and release notes. Use when the user wants to release, tag a release, bump the version, or cut a version. Not for a plain commit, a pull request, or amending an existing tag.

Create an issue in the configured ticketing tool. Use when the user wants to file a bug, open an issue, or report a problem. Not for committing, opening a pull request, or commenting on an existing issue.

Generate a hook, a handler that runs at a lifecycle event, across the host AI tools. Use when the user wants to create, scaffold, or refactor a hook, or automate an action at a lifecycle point. Not for other artifacts like skills or rules.