aid

Plugin aid from marketplace AID in ilandahan/AID. Commands read from the repo's manifest — yesterday.

Skills (38)

• aid-development
• aid-discovery
• aid-impl-plan
• aid-prd
• aid-qa-ship
• aid-tech-spec
• atomic-design
• atomic-page-builder
• autoresearch
• code-review
• context-tracking
• cucumber-bdd
• learning-mode
• memory-system
• breakdown
• development
• discovery
• prd
• qa-ship
• tech-spec
• data-scientist
• developer
• product-manager
• qa-engineer
• tech-lead
• nano-banana-visual
• phase-enforcement
• pipeline-orchestrator
• test-driven
• pre-prd-research
• reflection
• role-data-scientist
• role-developer
• role-product-manager
• role-qa-engineer
• role-tech-lead
• system-architect
• why-driven-decision

Slash commands (44)

• /aid:aid-analyze

  Run full quality analysis with metrics and patterns across AID sessions

• /aid:aid-dashboard

  Generate a quality dashboard report with metrics and visualizations

• /aid:aid-end

  End the current phase and record session feedback

• /aid:aid-improve

  Run the improvement analysis cycle

• /aid:aid-init

  Initialize this project with AID phases and the memory system

• /aid:aid-memory

  Manage Claude Memory entries for AID

• /aid:aid-recommendations

  View and manage recommendations for improving AID skills based on session feedback

• /aid:aid-reset

  Full system reset - clears all runtime data

• /aid:aid-start

  Start a work session: pick a role and phase, load the matching skills

• /aid:aid-status

  Show current AID state: phase plus session info

• /aid:aid-test

  Run AID methodology test as isolated sub-agent with ultrathink quality verification

• /aid:architecture

  Design system architecture for new systems or major refactors

• /aid:breather-start

  Start/enable breather - session break offers, presence tracking, status line

• /aid:breather-stop

  Stop breather - snooze offers, skip today, or uninstall completely

• /aid:build-page

  Compose pages using ONLY existing design system components

• /aid:code-review

  Comprehensive code review for commits and pull requests

• /aid:context-update

  Update the current work context manually

• /aid:context

  Show current work context: active task, step and progress

• /aid:design-system

  Build a complete design system from design spec using Atomic Design methodology

• /aid:discovery

  Start Phase 0: research, validation and problem framing

• /aid:gate-check

  Check whether the current phase is ready to advance

• /aid:good-morning

  Start the day by checking systems, loading context, and preparing to continue work

• /aid:jira-breakdown

  Generate Jira project structure from technical specification

• /aid:link-project

  Link an existing project to AID so it shares one source of truth

• /aid:phase-advance

  Advance to the next AID phase

• /aid:phase-approve

  Record human sign-off for the current phase

• /aid:phase

  Show current AID phase and its status

• /aid:pipeline-status

  Display the current state of the automated development pipeline

• /aid:pipeline

  Start or resume the automated development pipeline for the current task

• /aid:prd

  Generate a Product Requirements Document (PRD) for a feature

• /aid:qa-ship

  Run Phase 5 QA validation, acceptance testing, and release preparation

• /aid:reflect

  Show detailed quality check breakdown or re-evaluate last response

• /aid:setup

  Complete guided AID setup, step by step, for new users

• /aid:start-project

  Initialize a brand new project from scratch

• /aid:storybook

  Manage Storybook preview for extracted design spec components

• /aid:tech-spec

  Generate a Technical Specification document from a PRD

• /aid:test-all-agents

  Run all agent tests in sequence or parallel

• /aid:test-phase-review

  Test phase-review-agent gate validation accuracy

• /aid:test-qa-validator

  Test qa-validator-agent criteria checking accuracy

• /aid:test-reflection

  Test reflection-agent isolation and scoring accuracy

• /aid:test-review

  Review test quality and coverage using TDD best practices

• /aid:write-tests
• /aid:yolo-off
• /aid:yolo

Subagents (39)

• aid-test-agent

  Autonomously exercises the AID methodology end to end (Phases 0-5) and reports where it breaks. Use for /aid-test, or to verify an AID installation actually works after setup or upgrade.

• code-review-agent

  Independent code review with no knowledge of how the code was written - security, quality, documentation, architecture. Use for the pipeline CODE_REVIEW step, or whenever code needs a reviewer with zero attachment to it being good.

• developer

  Writes real, runnable proof-of-concept code from a spec - not a design document. Use in Phase 4 when a task needs working code produced in isolation from the planning conversation.

• memory-analysis-agent

  Analyses collected session feedback, detects recurring patterns, and proposes concrete skill improvements. Use for /aid-improve, or when a batch of pending feedback needs turning into skill updates.

• phase-review-agent

  Validates that a phase's deliverables are complete enough to advance to the next phase. Use for /gate-check, or before any phase advance in the 6-phase lifecycle.

• phase0-business-analyst

  Assesses business viability of a problem: market analysis, value proposition, business model. Use in Phase 0 discovery.

• phase0-competitive-researcher

  Maps the competitive terrain: market landscape, competitor profiles, strategic positioning and gaps. Use in Phase 0 discovery.

• phase0-go-nogo-assessor

  Makes an evidence-based Go/No-Go recommendation from all Phase 0 research - feasibility and risk. Use at the Phase 0 gate.

• phase0-problem-validator

  Validates whether a stated problem is real, significant and worth solving - root cause analysis, assumption testing, severity assessment. Use in Phase 0 before any solution work.

• phase0-stakeholder-mapper

  Identifies every affected party and maps power/interest plus a communication strategy, so no stakeholder is missed. Use in Phase 0 discovery.

• phase2-api-designer

  Designs the API layer of a tech spec: RESTful contract-first design and integration patterns, building on data models, security and NFRs. Use in Phase 2.

• phase2-data-models-designer

  Designs the data model layer of a tech spec: entity-relationship design, schema normalization, data integrity. Use in Phase 2.

• phase2-error-handling-strategist

  Designs error taxonomy, fault tolerance patterns and graceful degradation. Use in Phase 2.

• phase2-nfr-analyst

  Defines non-functional requirements: performance, scalability, reliability and operational readiness. Use in Phase 2.

• phase2-requirements-tracer

  Verifies every business requirement maps to something in the technical specification, and produces a coverage matrix. Use in Phase 2 review.

• phase2-security-designer

  Designs the security architecture layer of a tech spec for a SaaS product. Use in Phase 2.

• phase2-techspec-pm-reviewer

  Final PM-side review of a tech spec, synthesizing the requirements-tracer coverage matrix and the trade-off analysis. Use at the Phase 2 gate.

• phase2-techspec-synthesizer

  Consolidates the outputs of the 5 Phase 2 specialists into one final Technical Specification. Use at the end of Phase 2.

• phase2-trade-off-analyzer

  Evaluates each architectural decision through a business and user-impact lens. Use in Phase 2 review.

• phase3-contradiction-resolver

  Finds and resolves contradictions between the PRD and the technical specification. Use in Phase 3a consolidation.

• phase3-coverage-verifier

  Forensic check that 100% of PRD requirements are covered by the consolidated spec. Use at the Phase 3a gate.

• phase3-epic-story-mapper

  Breaks a consolidated spec into an Epic/Story hierarchy suitable for agile delivery. Use in Phase 3b breakdown.

• phase3-spec-consolidator

  Merges the PRD and tech spec into a single unified reference document. Use in Phase 3a consolidation.

• phase4-intent-validator

  Reads implemented code and validates it fulfills the business intent in the user stories and acceptance criteria. Use in Phase 4 review.

• phase4-scope-guardian

  Compares implemented code against the PRD's in-scope baseline to catch scope creep and silent omissions. Use in Phase 4 review.

• phase4-sprint-planner

  Turns a prioritized backlog into a realistic, capacity-based sprint plan. Use in Phase 4 planning.

• phase4-sprint-reviewer

  Objective sprint review: planned vs delivered, measured on empirical data such as velocity. Use at the end of a Phase 4 sprint.

• phase5-acceptance-validator

  Validates every PRD acceptance criterion against actual test results and UAT evidence, producing a definitive verdict. Use in Phase 5.

• phase5-release-certifier

  Makes the final GO/NO-GO release certification from acceptance results and release-readiness checks. Use at the Phase 5 gate.

• phase5-release-retrospective

  Post-release retrospective: what the PRD promised versus what actually shipped, across the full development trace. Use after release.

• phase5-uat-coordinator

  Designs a UAT test plan from the end-user's perspective, translating user stories and the original problem statement. Use in Phase 5.

• prd-research-aggregator

  Reads all Phase 0 research and produces a structured Research Brief a PRD writer can work from. Use at the start of Phase 1.

• prd-validator

  Independently evaluates a draft PRD against quality criteria and verifies traceability to research. Use at the Phase 1 gate.

• prd-writer

  Drafts a complete PRD from a structured research brief, following the AID template. Use in Phase 1.

• qa-validator-agent

  Validates that completed work meets its acceptance criteria in .aid/qa/<task-id>.yaml and returns a PASS/FAIL verdict. Use when the QA gate blocks task completion in Phase 4, or whenever a task claims to be done.

• reflection-agent

  Independent quality evaluation of an output - scores WHY alignment, phase compliance, correctness, security and completeness for the Quality Check box. Also runs end-of-session review. Use for the automatic Quality Check, or when an output needs scoring by someone who did not produce it.

• test-engineer

  Writes real, runnable test files (TDD) for code the developer just produced - not a test strategy document. Use in Phase 4 right after implementation.

• test-review-agent

  Independent review of test quality - coverage, over-mocking, weak assertions, test independence. Use for the pipeline TEST_REVIEW step, or when tests pass but you need to know whether they actually prove anything.

• visual-qa-agent

  Independently reviews a RUNNING application's visual quality and interaction in a real browser, then grades it. Use when UI work needs verifying in the browser rather than from code or tests alone.

Hooks (6)

• SessionStart

  node

• PreToolUse

  node

• PreToolUse

  node

• PostToolUse

  node

• Stop

  node

• Stop

  node

Similar plugins