System Design Session Skill
[!IMPORTANT]
Run an interactive system design session that turns a product goal into a scoped, evidence-qualified architecture and handoff.
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
Instructions
When the user asks to perform this workflow, execute the following steps:
System Design Workflow
Goal
Goal: Produce an evidence-qualified system design and handoff to design-solution, holding unresolved material decisions and distinguishing design readiness from implementation or operations.
Steps
- Load context. Read the product goal and relevant architecture. Review-existing mode uses current traffic/incident evidence when available. Load
system-design-methodology and only relevant siblings: system-design-data-architecture for consequential flows, system-design-mobile-client for client/SDK concerns, and common-architecture-diagramming only for a selected view.
- Classify independently. State mode (new design | review existing | interview practice), depth (quick | full), and surface (backend | mobile/client | SDK/library | full stack; mixed may name multiple). Quick uses labeled assumptions; full confirms consequential gates. Escalate quick for hard constraints or irreversible choices. Interview practice follows
system-design-interview-coaching; the candidate designs, then receives the practice loop and six-criterion debrief.
- Intake and estimate. Follow
system-design-methodology/references/four-phase-process.md exit predicates. Bound intake to journeys, scope, inputs/outputs, trust/ownership boundaries, quality scenarios (trigger, environment, response, measure, owner), and assumptions. Ask at most 3 blocking questions per turn. Estimate only decision-relevant quantities; label target/estimated/measured and provenance. Confirm material scope and shaping estimates before physical choices in full sessions.
- Trace before binding. Describe each consequential journey logically: source/sink, payload/purpose, transformations, authoritative owner/derived copies, invariant, user-visible outcomes, verification. Use
system-design-data-architecture/references/flow-contracts.md; do not duplicate C1. Bind accepted decisions to physical components/stores/contracts afterward. Link applicable FLOW-* design records through REQ-* -> HLD-* -> CMP-* -> LLD-* -> VER-*; FLOW-* is not an outcome field.
- Select views and deep dives conditionally. Choose zero or more from the named question, risk, surface, and time. Dataflow explains movement/authority; sequence ordering/acknowledgment; state lifecycle; ERD relationships; deployment placement. Prose/table is sufficient. No component, queue, store, specialist, or diagram quota. Practice uses commitment -> adverse timeline -> mechanism revision -> changed constraint -> evidence-based debrief.
- Hold material decisions. Full sessions do not commit affected design or claim readiness while a material owner/invariant, compliance/residency, or topology-changing budget decision remains unresolved. Record it in
decision_needed; preserve other gaps in missing_evidence. Quick sketches may proceed with explicit assumptions, never false readiness.
- Score and hand off. Run the declared-profile, scope-aware nine-axis
system-design-review scorecard and independent system-design-review/references/semantic-evaluation.md. Use applicable denominators and justified N/A. Semantic soundness requires >=85%, no applicable zero, and no hard failure; any failed material gate blocks readiness regardless of aggregate. The six-criterion interview rubric is separate. Preserve existing outcome fields/statuses; design evidence does not prove implementation or operations.
- Prepare warranted delivery slices. Only when independent post-decision docs/diagram slices are warranted, define exact files, AC, evidence, checks, and integrator before execution. Use configured project/account/data-eligible routing; lead retains decisions/final review. Allow one focused correction, then configured eligible fallback or
BLOCKED. Disclose executor/model/settings, correction/fallback, and actual usage/cost or unavailable. This gate grants no model/provider execution authorization, including premium execution; workers must not change policy/profile settings, invoke unapproved model execution, or claim unrun checks.
Runtime Contract
- Required input: product goal or existing system, plus scale parameters or explicit permission to use labeled assumptions.
- Never select physical components before relevant requirements/estimates exist or are explicitly assumed. Do not claim readiness with unresolved material gates or failed semantic evaluation.
- Return
BLOCKED for unresolved material ownership, invariant, compliance/residency, or topology-changing budget decisions that prevent a safe design commitment.
Handoff Payload
Include slug, operator_profile, design document path, mode/depth/surface, requirement and FLOW-* trace, relevant estimates/provenance, assumptions, physical component/ownership decisions, selected view paths, ADRs, scorecard and independent semantic findings, risk register, next workflow, completed_evidence, missing_evidence, and decision_needed.
Blocking Questions
Ask at most 3 at a time; provide a recommended default and 2–3 options. Quick sketches may proceed with labeled assumptions.
Output Template
# System Design: [Name]
## Mode, Depth, And Surface
## Requirements, Quality Scenarios, And Scope
## Assumptions And Evidence Provenance
## Decision-Relevant Estimates
## Logical Critical Flows (`FLOW-*`)
## Physical HLD / Ownership / Contracts
## Selected Views And Deep Dives (if any)
## Adverse Timeline, Recovery, And Verification
## Trade-offs, ADRs, And Staged Plan
## Nine-Axis Design Scorecard And Independent Semantic Review
## Interview Scorecard (interview practice only)
## Risks, Missing Evidence, And Decisions Needed
Quick assumptions or unresolved material gates cannot be reported as design-ready. `completed_evidence` records exercised evidence only; planned checks belong in `missing_evidence` until run.
## Outcome Report
schema_version: 1
run_id: "[run-id]"
slug: "[slug]"
workflow: system-design-session
feature_status: "[not_started | requirements_ready | design_ready | partially_implemented | implemented | blocked]"
started_at: "[timestamp]"
completed_at: "[timestamp]"
requirement_trace: { brd_objectives: [], requirements: [], acceptance_criteria: [], srs: [] }
completed_evidence: []
missing_evidence: []
decision_needed: []
recommended_next_workflow: design-solution
cost: { source: unavailable }
agent: { identity: "[agent-identity]", model: "[model]" }
Next Workflow
design-solution when the design is ready for contract work; otherwise resolve decision_needed or missing design evidence first.
Cost Report
Call get_session_cost(workflow="system-design-session") before final handoff. Report actual usage/cost when available; otherwise unavailable.
1---2name: system-design-session-23description: "Run an interactive system design session that turns a product goal into a scoped, evidence-qualified architecture and handoff."4metadata:5 source: https://skillmd.com/skills/hoangnguyen0403/system-design-session-26 internal: true7 triggers:8 keywords:9 - system design session10 - workflow11---1213# System Design Session Skill1415> [!IMPORTANT]16> Run an interactive system design session that turns a product goal into a scoped, evidence-qualified architecture and handoff.1718Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.1920## Instructions2122When the user asks to perform this workflow, execute the following steps:232425# System Design Workflow2627## Goal2829Goal: Produce an evidence-qualified system design and handoff to `design-solution`, holding unresolved material decisions and distinguishing design readiness from implementation or operations.30## Steps31321. **Load context.** Read the product goal and relevant architecture. Review-existing mode uses current traffic/incident evidence when available. Load `system-design-methodology` and only relevant siblings: `system-design-data-architecture` for consequential flows, `system-design-mobile-client` for client/SDK concerns, and `common-architecture-diagramming` only for a selected view.332. **Classify independently.** State mode (new design | review existing | interview practice), depth (quick | full), and surface (backend | mobile/client | SDK/library | full stack; mixed may name multiple). Quick uses labeled assumptions; full confirms consequential gates. Escalate quick for hard constraints or irreversible choices. Interview practice follows `system-design-interview-coaching`; the candidate designs, then receives the practice loop and six-criterion debrief.343. **Intake and estimate.** Follow `system-design-methodology/references/four-phase-process.md` exit predicates. Bound intake to journeys, scope, inputs/outputs, trust/ownership boundaries, quality scenarios (trigger, environment, response, measure, owner), and assumptions. Ask at most 3 blocking questions per turn. Estimate only decision-relevant quantities; label target/estimated/measured and provenance. Confirm material scope and shaping estimates before physical choices in full sessions.354. **Trace before binding.** Describe each consequential journey logically: source/sink, payload/purpose, transformations, authoritative owner/derived copies, invariant, user-visible outcomes, verification. Use `system-design-data-architecture/references/flow-contracts.md`; do not duplicate C1. Bind accepted decisions to physical components/stores/contracts afterward. Link applicable `FLOW-*` design records through `REQ-* -> HLD-* -> CMP-* -> LLD-* -> VER-*`; `FLOW-*` is not an outcome field.365. **Select views and deep dives conditionally.** Choose zero or more from the named question, risk, surface, and time. Dataflow explains movement/authority; sequence ordering/acknowledgment; state lifecycle; ERD relationships; deployment placement. Prose/table is sufficient. No component, queue, store, specialist, or diagram quota. Practice uses commitment -> adverse timeline -> mechanism revision -> changed constraint -> evidence-based debrief.376. **Hold material decisions.** Full sessions do not commit affected design or claim readiness while a material owner/invariant, compliance/residency, or topology-changing budget decision remains unresolved. Record it in `decision_needed`; preserve other gaps in `missing_evidence`. Quick sketches may proceed with explicit assumptions, never false readiness.387. **Score and hand off.** Run the declared-profile, scope-aware nine-axis `system-design-review` scorecard and independent `system-design-review/references/semantic-evaluation.md`. Use applicable denominators and justified `N/A`. Semantic soundness requires >=85%, no applicable zero, and no hard failure; any failed material gate blocks readiness regardless of aggregate. The six-criterion interview rubric is separate. Preserve existing outcome fields/statuses; design evidence does not prove implementation or operations.398. **Prepare warranted delivery slices.** Only when independent post-decision docs/diagram slices are warranted, define exact files, AC, evidence, checks, and integrator before execution. Use configured project/account/data-eligible routing; lead retains decisions/final review. Allow one focused correction, then configured eligible fallback or `BLOCKED`. Disclose executor/model/settings, correction/fallback, and actual usage/cost or `unavailable`. This gate grants no model/provider execution authorization, including premium execution; workers must not change policy/profile settings, invoke unapproved model execution, or claim unrun checks.4041## Runtime Contract4243- Required input: product goal or existing system, plus scale parameters or explicit permission to use labeled assumptions.44- Never select physical components before relevant requirements/estimates exist or are explicitly assumed. Do not claim readiness with unresolved material gates or failed semantic evaluation.45- Return `BLOCKED` for unresolved material ownership, invariant, compliance/residency, or topology-changing budget decisions that prevent a safe design commitment.4647## Handoff Payload4849Include `slug`, `operator_profile`, design document path, mode/depth/surface, requirement and `FLOW-*` trace, relevant estimates/provenance, assumptions, physical component/ownership decisions, selected view paths, ADRs, scorecard and independent semantic findings, risk register, next workflow, `completed_evidence`, `missing_evidence`, and `decision_needed`.5051## Blocking Questions5253Ask at most 3 at a time; provide a recommended default and 2–3 options. Quick sketches may proceed with labeled assumptions.5455## Output Template5657```md58# System Design: [Name]59## Mode, Depth, And Surface60## Requirements, Quality Scenarios, And Scope61## Assumptions And Evidence Provenance62## Decision-Relevant Estimates63## Logical Critical Flows (`FLOW-*`)64## Physical HLD / Ownership / Contracts65## Selected Views And Deep Dives (if any)66## Adverse Timeline, Recovery, And Verification67## Trade-offs, ADRs, And Staged Plan68## Nine-Axis Design Scorecard And Independent Semantic Review69## Interview Scorecard (interview practice only)70## Risks, Missing Evidence, And Decisions Needed7172Quick assumptions or unresolved material gates cannot be reported as design-ready. `completed_evidence` records exercised evidence only; planned checks belong in `missing_evidence` until run.7374## Outcome Report75schema_version: 176run_id: "[run-id]"77slug: "[slug]"78workflow: system-design-session79feature_status: "[not_started | requirements_ready | design_ready | partially_implemented | implemented | blocked]"80started_at: "[timestamp]"81completed_at: "[timestamp]"82requirement_trace: { brd_objectives: [], requirements: [], acceptance_criteria: [], srs: [] }83completed_evidence: []84missing_evidence: []85decision_needed: []86recommended_next_workflow: design-solution87cost: { source: unavailable }88agent: { identity: "[agent-identity]", model: "[model]" }89```9091## Next Workflow9293`design-solution` when the design is ready for contract work; otherwise resolve `decision_needed` or missing design evidence first.9495## Cost Report9697Call `get_session_cost(workflow="system-design-session")` before final handoff. Report actual usage/cost when available; otherwise `unavailable`.98