davidlee

The claude arm of `/dispatch` — spawn a worker via the `Agent` tool using the dispatch-worker subagent type with worktree isolation. Base is explicit — `dispatch arm-spawn --base B` writes the base file, then cd into the spawn dir before the Agent spawn so the WorktreeCreate hook forks at B. Worker self-commits via the gated `worker_commit` MCP tool; the orchestrator lands via `dispatch_import` → `dispatch_conclude_phase` → `dispatch_reap`. Reached only from the `/dispatch` router on a claude↔env-marker agreement; do not invoke directly.

Use at the very start of ANY substantive work in a Doctrine repo — before inspecting files, running commands, or writing code. The mandatory gate that chooses the governing skill. Skip it only when the user has explicitly told you to.

Use when a named subsystem, capability, or code surface needs governance coverage assessed before authoring a spec — deciding what is already governed by an existing PRD / tech spec / ADR, what is dark, and where new spec boundaries should fall by product altitude and C4 level. Use before creating or scoping a product or technical spec for an unfamiliar or partially-governed surface. Use when a request asks to "assess coverage", "find governance gaps", "what's already specified", "where should this spec's boundary sit", "one spec or several", "what needs a PRD vs a tech spec", or "is this subsystem properly documented". Produces a reviewable coverage-map artifact that feeds `/spec-product` and `/spec-tech`. Do not use when the target spec and its boundary are already known and unambiguous — go straight to `/spec-product` or `/spec-tech`. Do not confuse with `doctrine coverage` — unrelated CLI verb for requirement verification.

Use the moment you hit an unanticipated obstacle, a decision with competing tradeoffs, or emergent complexity mid-task — before adapting planned scope, adding a dependency, taking a shortcut, or making any impactful concession on your own.

Use when a slice needs architectural shaping before implementation — decision triage, critical analysis of tradeoffs and solutions, and section-by-section validation of design.md until the decisions lock. Routed to from /route once a slice exists.

Use when work surfaces something epistemic worth keeping — "we're assuming / proceeding as if X", "we decided X over Y", "open question worth outliving this session", "we're bound by X", "evidence for/against X", "testable hypothesis", or a stable concept worth naming — and when settling, relating, or surveying such records. Routes capture, settle, and survey intent to the correct `doctrine knowledge` verb.

Use after routing has chosen this path, when the next step is bounded up-front research to understand a substantive task, surface unknowns and tensions, and assess readiness — without drifting into implementation or open-ended exploration.

Use to formally close a slice once its phases are complete, audited, and reconciled — confirm the rollup, verify spec-coherence, harvest durable findings, reconcile lifecycle status, and land a clean final commit. Routed to from /reconcile.

Canonical reconciliation runsheet for AUD artefacts. Create or update the audit, disposition every finding, reconcile specs/contracts, and hand off to closure only when audit state supports it.

Close a delta safely - satisfy coverage gates, complete the delta command, and verify owning-record lifecycle updates.

Orchestrate parallel implementation via sub-agents. Drives an entire delta to completion across all phases — planning, dispatching, merging, and continuing automatically. Batches tasks by token budget, routes to appropriate models (sonnet/opus), and dispatches workers in isolated worktrees. Use instead of /execute-phase when a phase has parallelizable work.

Mandatory execution skill for any delta/IP implementation phase. Use it before code changes, move the owning delta to in-progress, keep notes current, reconcile structured execution docs, and surface blockers early.

Whenever you complete a task or phase - record implementation notes.

Reconcile DE/IP/phase/DR execution artefacts during delta work. Use this when implementation changes structured execution state, not just notes.

Mandatory onboarding. Every agent MUST execute this on startup, or as soon as becoming aware of it.

Invoke this skill whenever any of the following occurs during work: (1) you discover or confirm a durable fact, constraint, invariant, or “how we do X here” pattern; (2) you create a new workflow/checklist that will be reused; (3) you resolve a recurring confusion (“where is the source of truth?”); (4) you make a decision that is not an ADR/SPEC but would prevent rework; (5) you detect a sharp edge, footgun, or non-obvious dependency that future agents will hit. Do NOT rely on conversational context to persist. When the information would save ≥10 minutes for a future agent, write a memory record immediately.

Mandatory onboarding. Every agent MUST execute this on startup, or as soon as becoming aware of it.

Execute an active implementation phase against DR/IP intent, keep notes current, and surface blockers early. You MUST use this skill when implementing a delta / IP.

Before starting anything new, understand task, intent, and context.

Understand project governance to avoid spreading heresy. you

Scope intentional change as a delta. Define applies-to specs/requirements, risks, and closure targets before implementation.

Shape a spec revision when requirements/responsibilities move. Use this before delta scoping when policy/doctrine requires revision-first flow.

Perform verification/audit pass after implementation (or as discovery/backfill), reconcile against specs/contracts, and route findings into closure or follow-up change.

Invoke this skill whenever any of the following occurs during work: (1) you discover or confirm a durable fact, constraint, invariant, or “how we do X here” pattern; (2) you create a new workflow/checklist that will be reused; (3) you resolve a recurring confusion (“where is the source of truth?”); (4) you make a decision that is not an ADR/SPEC but would prevent rework; (5) you detect a sharp edge, footgun, or non-obvious dependency that future agents will hit. Do NOT rely on conversational context to persist. When the information would save ≥10 minutes for a future agent, write a memory record immediately.

Audit completed work against the design; harvest durable findings into audit.md.

MUST USE whenever reviewing or auditing code for quality & correctness

Author and adversarially review a slice's design.md until the decisions lock.

Execute a planned phase — fill the sheet, TDD red/green/refactor, end green, commit.

Create a context packet and continuation prompt to continue with the next phase in a slice (or audit & close). Use whenever a phase is completed and a fresh agent would more efficiently continue.

Expand a single plan phase into its runtime phase sheet, just before execution.

Author plan.toml + plan.md — the phased implementation plan against the existing surface.

Pre-execution gate — plan approved, tree clean, EN/EX/VT criteria readable.