Design Orchestration
Enforce brainstorm → risk-based review → execution gates so risky feature ideas do not skip design validation.
Overview
Design Orchestration is an agent skill most often used in Validate (also Build PM, Ship review) that enforces brainstorm → risk assessment → validated design before any implementation skill may run.
Install
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill design-orchestrationWhat is this skill?
- Meta-skill that routes work—it does not generate designs itself
- Step 1 mandates `brainstorming` with Understanding Lock, Initial Design, and Decision Log
- Step 2 classifies designs as low, moderate, or high risk before escalation
- Coordinates `multi-agent-brainstorming` for validation on higher-risk paths
- Hard gate: execution and downstream planning skills only after validated design
- 3 risk classes: low, moderate, high
- 3 mandatory brainstorming artifacts: Understanding Lock, Initial Design, Decision Log started
Adoption & trust: 455 installs on skills.sh; 40.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want the agent to jump straight into code for a risky feature and you have no enforced design artifacts or review step.
Who is it for?
New features, system changes, or design decisions where misunderstanding is expensive and you already use brainstorming skills in the same repo.
Skip if: Trivial typo fixes, approved specs with a finished Decision Log, or workflows that lack `brainstorming` and optional `multi-agent-brainstorming`.
When should I use this skill?
A user proposes a new feature, system, or change; a design decision carries meaningful risk; correctness matters more than speed.
What do I get? / Deliverables
A classified risk level, required brainstorming outputs, and an explicit go/no-go before downstream implementation or planning skills are invoked.
- Risk classification
- Enforced skill invocation order
- Execution permission decision
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Validate → scope because the skill blocks implementation until design artifacts exist—first meaningful stop in the journey is scoping and locking understanding before build. Scope fits routing and enforcement of what gets built, not generating UI or shipping code.
Where it fits
User asks for a new billing module—the orchestrator forces brainstorming and risk tier before any build skill runs.
Mid-build pivot on auth model triggers re-entry to assess moderate vs high risk and whether multi-agent review is required.
Large refactor proposal is treated as a design change and blocked from merge until Decision Log artifacts exist.
Early system sketch is routed through brainstorming instead of immediate prototype generation.
How it compares
Use instead of ad-hoc ‘just implement it’ agent chats when you need a enforced skill chain.
Common Questions / FAQ
Who is design-orchestration for?
Solo and indie builders orchestrating Antigravity-style skill stacks who want mandatory design steps before implementation agents run.
When should I use design-orchestration?
At Validate when scoping a risky feature; at Build PM when a change needs re-validation; at Ship review when correctness must trump speed—always before coding without artifacts.
Is design-orchestration safe to install?
Check the Security Audits panel on this Prism page and review the community skill source before enabling orchestration that invokes other local skills.
Workflow Chain
Then invoke: brainstorming
SKILL.md
READMESKILL.md - Design Orchestration
# Design Orchestration (Meta-Skill) ## Purpose Ensure that **ideas become designs**, **designs are reviewed**, and **only validated designs reach implementation**. This skill does not generate designs. It **controls the flow between other skills**. --- ## Operating Model This is a **routing and enforcement skill**, not a creative one. It decides: - which skill must run next - whether escalation is required - whether execution is permitted --- ## Controlled Skills This meta-skill coordinates the following: - `brainstorming` — design generation - `multi-agent-brainstorming` — design validation - downstream implementation or planning skills --- ## Entry Conditions Invoke this skill when: - a user proposes a new feature, system, or change - a design decision carries meaningful risk - correctness matters more than speed --- ## Routing Logic ### Step 1 — Brainstorming (Mandatory) If no validated design exists: - Invoke `brainstorming` - Require: - Understanding Lock - Initial Design - Decision Log started You may NOT proceed without these artifacts. --- ### Step 2 — Risk Assessment After brainstorming completes, classify the design as: - **Low risk** - **Moderate risk** - **High risk** Use factors such as: - user impact - irreversibility - operational cost - complexity - uncertainty - novelty --- ### Step 3 — Conditional Escalation - **Low risk** → Proceed to implementation planning - **Moderate risk** → Recommend `multi-agent-brainstorming` - **High risk** → REQUIRE `multi-agent-brainstorming` Skipping escalation when required is prohibited. --- ### Step 4 — Multi-Agent Review (If Invoked) If `multi-agent-brainstorming` is run: Require: - completed Understanding Lock - current Design - Decision Log Do NOT allow: - new ideation - scope expansion - reopening problem definition Only critique, revision, and decision resolution are allowed. --- ### Step 5 — Execution Readiness Check Before allowing implementation: Confirm: - design is approved (single-agent or multi-agent) - Decision Log is complete - major assumptions are documented - known risks are acknowledged If any condition fails: - block execution - return to the appropriate skill --- ## Enforcement Rules - Do NOT allow implementation without a validated design - Do NOT allow skipping required review - Do NOT allow silent escalation or de-escalation - Do NOT merge design and implementation phases --- ## Exit Conditions This meta-skill exits ONLY when: - the next step is explicitly identified, AND - all required prior steps are complete Possible exits: - “Proceed to implementation planning” - “Run multi-agent-brainstorming” - “Return to brainstorming for clarification” - "If a reviewed design reports a final disposition of APPROVED, REVISE, or REJECT, you MUST route the workflow accordingly and state the chosen next step explicitly." --- ## Design Philosophy This skill exists to: - slow down the right decisions - speed up the right execution - prevent costly mistakes Good systems fail early. Bad systems fail in production. This meta-skill exists to enforce the former. ## When to Use This skill is applicable to execute the workflow or actions described in the overview. ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.