Product Engineering

Plugin product-engineering from marketplace agent-ready-repo in eugenelim/agent-ready-repo. Commands read from the repo's manifest — today.

Skills (12)

• align-value-stream

  Use at business-unit scale to stand up and keep current a value-stream meta-repo — a coordinating repo with no app code that holds the cross-component artifacts a polyrepo has nowhere else to put (the federated Backstage catalog, the shared-contract authority, the C4/bounded-context architecture, an

• discovery-loop

  Use to turn a raw product idea into a ratified, build-ready decision brief — the upstream discovery loop run by the discovery-lead agent. Triggers on "scaffold the product vision for X", "run a discovery for X", "diverge on the product shape then converge to a brief", "take this idea to a decision b

• diverge-solutions

  Use to lay out comparable solution options for an initiative-sized opportunity, each with trade-offs, plus a recommendation, in solution-options.md. Triggers on "compare solution options", "options with trade-offs". For loose product-shape ideas use `explore-options`; to commit to one use `place-bet

• explore-options

  Use to diverge on the product shape — sketch several distinct shapes, each with its riskiest assumption, before converging. Triggers on "give me candidate product shapes", "explore alternatives", "don't converge yet". For initiative options use `diverge-solutions`; not to break down a chosen shape (

• frame-domain

  Use to frame the domain — how the real-world activity is actually done, its best practice, and how naive versions fail — and to draw the MVP scope boundary before design starts. Triggers on "how is this really done", "what's in the MVP", "is this scope creep". Not for shaping the intent (use `intent

• frame-situation

  Use when a signal needs sorting out before anyone shapes work — a market shift, a metric drop, a competitor move, a recurring user pain. Classifies the signal, rates capability maturity on a Wardley map, and names the shaping step to start from. Not for a single feature (use `intent frame`).

• identify-opportunities

  Use to find and rank the unmet jobs behind a problem area — what users are trying to get done, functional, emotional, and social — scored by importance and satisfaction into an opportunity assessment. Triggers on "map the jobs", "what do users need", "score the opportunity". Not once a solution is c

• intent

  Use when shaping a piece of product work before it becomes a spec. Three modes: `frame` turns a rough idea, request, or strategy into a level-tagged intent: the problem, who has it, the outcome, and the opportunity behind it; `de-risk` finds the assumption that would sink an intent if it were wrong

• lean-canvas

  Use to fill in a lean canvas for an initiative and write it up as a one-page initiative brief — problem, customer segments, value proposition, solution, key metrics. Triggers on "lean canvas", "initiative brief", "canvas this initiative". Not for a single feature (use `intent frame`).

• map-capabilities

  Use after a bet is committed to list the capabilities it needs, decide build, buy, partner, or adopt for each, and suggest a build order, in a capability map. Triggers on "what do we need to build", "build or buy", "map our capabilities". Not for a single feature (use `intent frame`).

• place-bet

  Use to make the call between solution options and record the bet in bet.md — the choice, why, confidence, appetite (the time it is worth), risks accepted, and what would reverse it. Triggers on "pick an option", "commit to a direction", "place the bet". To generate options first use `diverge-solutio

• plan-validation

  Use to plan the validation of the assumptions a product rests on — what would confirm or kill each one — and to scaffold an interview guide or usability-test plan for a human to run. Triggers on "plan the validation", "how do we validate these assumptions", "what would confirm this". To test one bet

Subagents (3)

• discovery-lead

  The upstream discovery supervisor — runs the discovery-loop skill to turn a raw product idea into a ratified, build-ready decision brief. Holds the discovery-workspace (the typed sidecar) in one reasoning context, diverges across candidate product shapes, drives the lens roster to convergence, pause

• discovery-reliability-reviewer

  Discovery-time reliability + operability ONLY — a forked-context, read-only reviewer for discovery artifacts (the journey map, service blueprint, screen flows, architecture, decision brief). Required at the discovery loop's G2 reconcile. A DISTINCT agent from work-loop's code quality-engineer — it r

• discovery-threat-reviewer

  Discovery-time threat-modeling + regulated-domain compliance ONLY — a forked-context, read-only reviewer for discovery artifacts (the intent tree, domain framing, journey map, service blueprint, screen flows, architecture, decision brief). Required at the discovery loop's G2 reconcile. A DISTINCT ag

Hooks (1)

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/scripts/install-marker.py" --install-route claude-plugins

Similar plugins