ShapeUp SDLC Plugin

Chạy full harness unattended

Use this skill whenever a user provides a product requirement, pitch, or feature description and wants it broken down into structured, executable development tasks. Triggers on: "analyze this pitch", "break this into tasks", "generate tasks from requirement", "act as BA", "create spec from PRD", "turn this into dev tasks", or any request to decompose a feature into DDD-structured documents and implementation tasks for Claude Code CLI execution. Also triggers when user mentions Shape Up, bounded context, domain model, or use cases. Output is a linked document tree (pitch → domain model → use cases → tasks). Emits BDD scenarios + integration flow in task AC, a UC System Flow tracing UI→API→UC→DB, a derived UC Test Surface, and per-phase gates (summary + max 2 questions, never assumes).

Use this skill for Shape Up step 7 (Orient) — the builder-led reconnaissance pass that runs AFTER kick-off and BEFORE any task board exists. Triggers on: "orient on this feature", "scout the codebase for this pitch", "where does this pitch touch the code", "do an orient pass", "recon before we plan", "spike the riskiest part before mapping scopes". The tech-lead orchestrator invokes it at step 7 before delegating to ba-pitch-analyzer (Map Scopes, step 8). Use it even when the user describes "read the code first and surface the unknowns" without naming Orient. The Scout is a PURE worker: it reads code, spikes the single riskiest area, and emits four artifacts (code-surface map, spike findings, discovered-task seed, hill signal). It writes NO production code, builds NO scope board, keeps NO run-state, and renders NO progress report — those belong to ba (planner) and tech-lead (orchestrator) respectively.

Use this skill for the post-PASS exploratory QA pass — Shape Up's "QA is for the edges", made explicit for the harness. Triggers on: "hunt edge cases", "QA pass on this feature", "exploratory test the running app", "edge hunt before ship", "run qa-edge-hunter", "the evaluator passed — what did it miss?". tech-lead invokes it after the run's FIRST PASS at GATE L3, before SHIP; it also runs standalone given a spec folder, a PASS EVAL report, and a running app. The Hunter is a PURE worker: it charters edges OUTSIDE what the evaluator probed (EVAL-*.md = negative-space input), hunts them on the running app through six fixed lenses; findings → discovery/ledger.md, always `~`. NO verdict, NO score, NO gate; never fixes code, never promotes its own findings, never blocks ship — triage is PO/TL's at SHIP S.0/GATE L4. NOT for checking AC (spec-evaluator), deriving test cases (ba), or fixing bugs (task-executor).

Use this skill for any Shape Up workflow before writing code. Triggers on: "shape this feature", "frame this problem", "breadboard this", "map affordances", "write a framing doc", "write a kickoff doc", "turn this transcript into a framing document", "turn this transcript into a kickoff document", "what should we build", "explore solutions", "is this shaped enough to build", "slice this into scopes", "fit check", "wiring diagram". Also triggers when user says "before we build...", "I want to think through...", "let's shape this", or provides a raw transcript and wants it structured. DEFAULT: if no sub-command given, run /shapeup full — ask clarifying questions at each gate, keep solutions as simple as possible, never touch parts that already work. Sub-commands: /shapeup full | /shapeup shaping | /shapeup spike | /shapeup breadboarding | /shapeup framing-doc | /shapeup kickoff-doc | /shapeup breadboard-reflection

Use this skill whenever the user wants to evaluate, QA, or verify that an implemented task actually matches its spec and acceptance criteria — the judge in a planner→generator→evaluator harness, pairing with task-executor. Trigger on: "evaluate task TASK-NNN", "QA TASK-NNN", "verify against spec", "check acceptance criteria", "does this match the spec", "grade this build", "run evaluator", "verify TDD", "run integration tests", "check test coverage". Use it even when the user just points at a built task plus a spec folder and asks if it is correct. Three always-on dimensions: spec-conformance (AC + Done-when + contract shapes + non-go), tdd-surface (test suite green + companion test files), and integration (full-stack integration test + auth boundary + RLS-JWT pattern). Security and performance ship as disabled, injectable stubs. Skeptical by default — absence of evidence is a FAIL, probes the running app and test suite, files file:line bugs, never marks a task done.

1 hook across 1 event