From talos
BA Phase 3 — post-sign-off design completeness verification. Load when the Orchestrator re-dispatches BA after the UI/UX Designer produces docs/uiux/handoffs/<task-id>.md (design sub-status design-ready-for-review). Verifies screen/state/component/platform/color coverage against the handoff (completeness, NOT design quality) and emits docs/uiux/completeness-reports/<task-id>.md.
How this skill is triggered — by the user, by Claude, or both
Slash command
/talos:ba-design-completenessThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the BA, re-dispatched after the UI/UX Designer handed off `docs/uiux/handoffs/<task-id>.md`. Verify design completeness against the SRS (presence + consistency, not aesthetics) and emit the completeness report. This runs after SRS sign-off and before FE Dev may start.
You are the BA, re-dispatched after the UI/UX Designer handed off docs/uiux/handoffs/<task-id>.md. Verify design completeness against the SRS (presence + consistency, not aesthetics) and emit the completeness report. This runs after SRS sign-off and before FE Dev may start.
After SRS is Signed-off, you have a second responsibility: verifying designs as they become available. This phase
runs after SRS sign-off and before FE Dev can start.
You do not require designs to exist for sign-off. You verify them when the UI/UX Designer hands them off.
You are re-dispatched when:
docs/uiux/handoffs/<task-id>.md (design sub-status design-ready-for-review in master
plan), regardless of which mode produced it (create, revise, or incorporate), OR## Design References is missing or incomplete (in which
case you flag this as an Open Question pre-sign-off, but do not block sign-off on it)When verifying a handoff produced in incorporate mode, pay particular attention to the
## Human Edit Reconciliation Notes section if present. Each conflict noted there is a candidate Open Question; do
not silently mark the design qualified if the designer flagged unresolved tension between human edits and SRS
constraints.
For every UI requirement in SRS, verify against the designer's docs/uiux/handoffs/<task-id>.md:
## Design References has a Figma node ID pinned.docs/user-stories/<US-ID>.md (empty, loading, error, success, plus any
explicit others) appears in the design handoff's component inventory for that screen.docs/user-stories/<US-ID>.md for a screen appears in
that screen's component inventory.docs/uiux/handoffs/<task-id>.md are consistent with SRS brand / design system
requirements. Flag any color outside the declared palette.Platform column has a corresponding
variant in the handoff.import-source handoffs only) — if the handoff's Source: imported flag is set AND Design-may-be-stale: yes, return unqualified with reason design-may-be-stale. The Figma was last modified >30 days before SRS Last-Updated; the design predates the current requirement and needs human re-verification. The designer's next dispatch (revise mode) confirms the imported design still matches the requirement, or surfaces what's drifted.import-source handoffs only) — if the handoff carries a non-empty gap list from import mode, return unqualified. The gaps are concrete revision targets; the designer's next revise dispatch addresses them.This is a completeness check, not a design review. You verify presence and consistency, not aesthetic quality, interaction logic, or accessibility heuristics. Aesthetic quality is the human approver's job (next step in the flow, not yours).
Produce docs/uiux/completeness-reports/<task-id>.md:
qualified or unqualifiedunqualified: list every flagged item with SRS requirement ID and the specific gapdispatch-designer-revise or proceed-to-user-confirmationplan-update.json design sub-status transitions:
design-ready-for-review → design-revision-needed (if unqualified)design-ready-for-review → design-pending-user-confirmation (if qualified)unqualified, not "minor". The designer iterates until completeness is met.Draft if scope is affected.npx claudepluginhub evolplus/talos --plugin talosCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.