mattwynne/memba

kaizen-investigate

Investigate delivery-workflow friction or a docs/kaizen note, creating the observation first when no matching note exists; establish evidence-backed causes and options without implementing a fix.

technical-iteration-planning

Plan a technical or refactoring iteration that preserves observable behaviour, with explicit capability, constraints, architecture decisions, proof, and publication.

kaizen-fix

Implement and validate a countermeasure for an investigated docs/kaizen note, then document its resolution. Use when asked to fix or resolve a kaizen note, not for investigation-only requests.

kaizen-note

Offer to capture and, when accepted, write a docs/kaizen observation when we notice friction, imperfections, waste, opacity, brittleness, or failure in the pipeline/factory/workflows/tooling used to create the product. Use for workflow/tooling problems, not…

kaizen

Carry a delivery-workflow problem end to end: capture or amend a kaizen note, investigate its cause, and apply and validate a fix. Use when asked to kaizen a problem or take a workflow/tooling observation through resolution; use the stage-specific skills for…

bdd-automation

Design trustworthy, maintainable acceptance-test automation across domain, service, and UI boundaries in any technology stack.

behaviour-iteration-planning

Plan a behaviour-changing iteration through adversarial example mapping, Gherkin, collaborative domain modelling, Matt-approved ADRs, plan assembly, and publication.

writing-adrs

Use when creating or editing Architecture Decision Records - guides thinking through decisions with stakeholders before documenting the outcome

agent-collaboration

Maintain a small team of persistent agent perspectives alongside an evolving human conversation, using BB threads when available and Pi subagents as a fallback.

bdd-discovery

Use before formulating Gherkin scenarios when exploring a story's behaviour, rules, examples, questions, scope, or readiness with stakeholders

bdd-formulation

Write or review Gherkin scenarios after discovery, using Memba's agreed problem-domain vocabulary and concrete examples of business rules.

domain-modelling

Collaboratively model agreed behaviour or a technical capability with Matt before implementation, covering concepts, invariants, commands, events, lifecycle, ownership, and responsibility boundaries.

domain-vocabulary

Consult and maintain Memba's canonical problem-domain vocabulary when naming behaviour, scenarios, commands, events, invariants, or domain concepts.

iteration-delivery

Present a published ready or validated iteration plan for explicit approval, then use Fabro deliver to validate if needed and implement.

iteration-planning

Start planning a product or engineering iteration, classify it as behaviour-changing or technical/refactoring, and route into the appropriate specialist planning skill.

ensemble-review

Run a generic read-only review by up to three independent model families using a caller-supplied artifact, focus, rubric, questions, and constraints.

record-architectural-decisions

Collaborate with Matt to identify, draft, independently review, accept, and publish one or more consequential architectural decisions.

ux-design

Decide, locate, create, and review UX design coverage for visible behaviour before implementation, using Memba's design sources and Matt's decisions.

interview-me

Conduct a thorough, adaptive interview about any topic. Use when the user asks to be interviewed, questioned, grilled, or helped to clarify their thinking through dialogue.

kaizen-deep-retrospective

Conduct a comprehensive, evidence-led review of Memba's software-delivery factory across many deliveries, selecting one systemic improvement for approval. Use for periodic or explicitly requested deep factory reviews, not ordinary retrospectives, incident…

kaizen-experiment-review

Evaluate an active software-delivery factory experiment against its predeclared metric and guardrails, then recommend Adopt, Iterate, or Revert. Use for a named active kaizen experiment or when its ledger review date is due—not for launching experiments,…

incident-review

Record and investigate production incidents using a blameless timeline, evidence-backed Five Whys, and corrective, detection, and prevention actions. Use when a production failure, outage, data incident, serious customer-facing degradation, or request for an…

pi-subagent-gpt55

Delegate self-contained research, review, planning, debugging, or implementation subtasks to a Pi subagent running the openai-codex/gpt-5.5 model. Use when the user asks for Pi, GPT-5.5, a subagent, independent analysis, parallel investigation, or a second…

resend

Read, audit, and safely manipulate Resend email configuration and message data through the Resend API. Use when inspecting domains, API keys, audiences, contacts, broadcasts, emails, webhooks, or making explicit Resend changes with an API key from the…

postmark

Read, audit, and safely manipulate Postmark configuration and message data through the Postmark API. Use when inspecting servers, streams, senders, domains, templates, messages, webhooks, suppressions, or making explicit Postmark changes with API tokens from…

dnsimple

Read, audit, and safely manipulate DNSimple DNS configuration through the DNSimple API. Use when inspecting domains, zones, DNS records, or making explicit DNS changes with a DNSimple API token from the environment.