Agent skill
cobuilder
This skill should be used when the user asks to "brainstorm a feature", "create a PRD", "write a solution design", "plan a new initiative", "start a new project", "ideate on a feature", "brainstorm and build", "go from idea to implementation", "generate a TDD pipeline", or when System 3/Guardian needs to drive the complete ideation → PRD → SD → worktree → autonomous TDD pipeline. Parent skill for CoBuilder orchestration-level workflows. For worker-level powers (TDD, debugging, verification), see the separate worker-superpowers skill.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/cobuilder
SKILL.md
CoBuilder Orchestration Workflows
High-level workflows for the CoBuilder multi-agent pipeline, inspired by superpowers. These sub-skills are used by System 3, Guardian, and Orchestrators — not by workers directly.
For worker-level powers (TDD, debugging, verification, brainstorming), see Skill("worker-superpowers").
Sub-Skills
| Sub-Skill | Invoke As | Purpose |
|---|---|---|
| ideation-to-execution | Skill("cobuilder:ideation-to-execution") |
Brainstorm → PRD → SD → Worktree → TDD Pilot |
| tdd-pipeline | Skill("cobuilder:tdd-pipeline") |
Generate and configure TDD pipeline DOT files |
Quick Start
Full Initiative (System 3 / Guardian)
Skill("cobuilder:ideation-to-execution") # 5-phase workflow: brainstorm → PRD → SD → worktree → pilot
Generate Pipeline Only
Skill("cobuilder:tdd-pipeline") # Instantiate tdd-validated template from SD
Brief Workers on Powers
When creating worker task assignments, include:
"Load Skill('worker-superpowers') for TDD workflow, systematic debugging, and verification."
Core Principles
- Never jump to code — Discover → Design → Plan → Execute
- Test first — Every feature starts with a failing test (via worker-superpowers)
- Blind acceptance tests — Write tests from PRD before any implementation
- Isolated execution — Workers run in worktrees with scoped file access
- Pipeline-driven — DOT graph defines execution order, not ad-hoc delegation
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?