agentsclimarketplace

Dev architecture playbook

Skill majiayu000/spellbook/skills/dev-architecture-playbook

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

Install
npx -y skills add majiayu000/spellbook --skill dev-architecture-playbook

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Route full software-development architecture work from product intent through design, implementation, testing, release, and operations. Use when the user asks for a complete development architecture, wants to know which Spellbook skills to combine, needs an execution path across PRD/spec/API/data/security/performance/release/SRE, or asks to turn an idea or repo into a production-ready engineering plan.

SKILL.md

3.3 KB, 650 tokens by cl100k_base, as published. Nobody here has run it

Dev Architecture Playbook

Purpose

Use this as the lifecycle router before starting broad product or architecture work. It chooses the minimum useful skill chain, defines gates, and prevents starting implementation before the required contracts exist.

Route

Classify the request first:

RequestPrimary SkillsOutput
Idea, product direction, or market/user problemproduct-discovery, prd-masterProduct brief, user stories, success metrics
Architecture or module boundariesarchitecture-foundation, technical-spec, elegant-architectureArchitecture spec, boundaries, rejected alternatives
API, auth, data, or schema contractapi-design, auth-security, database-patterns, data-contract-migrationsVersioned contracts and migration plan
UI/product surfacefrontend-design, ui-ux-pro-max, ui-design-system, playwright-automationUX flow, component plan, visual checks
Implementation workflowflowguard, threads, systematic-debugging, comprehensive-testingBounded execution, ownership, root-cause debugging, and verification
Quality and regression riskcomprehensive-testing, codebase-audit, vibeguard, project-health-auditorTest matrix and risk list
Release and operationsrelease-engineering, config-secrets-environments, performance-capacity, incident-slo-runbook, observability-sre, devops-excellenceRollout, config, capacity, SLO, runbook

Required Gates

Do not treat the architecture as complete until these gates are explicit:

  1. Goal and non-goals.
  2. Domain model and ownership boundaries.
  3. External API, data, and config contracts.
  4. Security and permission model.
  5. Test strategy with command-level verification.
  6. Release, rollback, and migration gates.
  7. Observability, SLO, and incident response.

If a gate is irrelevant, state why. Do not silently skip data, security, or rollback gates for production systems.

Execution Pattern

Use this sequence for greenfield or major refactors:

  1. Product: write the product brief or PRD.
  2. Architecture: define modules, runtime boundaries, and tradeoffs.
  3. Contracts: define API, data, config, and security contracts.
  4. Plan: split work into independently verifiable steps.
  5. Implement: use one workflow skill per step, not every skill at once.
  6. Verify: run build, typecheck, tests, and focused behavioral checks.
  7. Release: define rollout, migration, rollback, monitoring, and support owner.

For existing repos, start with repo-agent-context-audit or codebase-audit before proposing new structure.

Output Shape

Return a compact plan:

goal:
context:
selected_skill_chain:
architecture_gates:
implementation_steps:
verification_commands:
release_and_ops_gates:
open_risks:

Prefer the smallest chain that covers the risk. Too many skills at once usually means the scope needs to be split.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.