skills.rest
lenlla
lenllaCOMMUNITY
Explore all skills by this author →
GitHub

build-step

Coordinate epic build steps by dispatching developer and reviewer sub-agents.

Updated Aug 23, 2026
Search Tags:#automation#tdd#agents#orchestration#code-review#circuit-breaker#build-system
One-click install
npx skills add https://github.com/lenlla/one_shot_build --skill build-step
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: build-step
Source: https://github.com/lenlla/one_shot_build/tree/main/skills/build-step
Command: npx skills add https://github.com/lenlla/one_shot_build --skill build-step

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinate the implementation, test-driven validation, and peer review of individual epic steps so agentic teams can make reliable, auditable progress without human micromanagement.

Core Features & Use Cases

  • Per-step orchestration: Parse an implementation plan, initialize step state, and iterate through pending tasks for a single epic.
  • Agentized dev + review loop: Spawn fresh developer and reviewer sub-agents via the Task tool for each step to maintain clean contexts and enforce review gates.
  • Robust safety and recovery: Enforce test immutability via TDD baselines, track circuit-breaker signals, and optionally escalate to automated replanning to correct or justify failing tests.
  • Use Case: Use from an execute-plan orchestrator to implement an epic by iteratively running development attempts, automated tests, reviews, and controlled replanning until completion.

Quick Start

Run the build-step skill from the execute-plan orchestrator with epic_name, build_dir, plan_path, epic_spec_path, tdd_baseline_tag, and mode to process the next epic step-by-step.

Frequently Asked Questions about build-step

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate epic step development and code review with sub-agents?▼

Automate epic step development by dispatching developer and reviewer sub-agents to implement and verify each step, coordinating the build and review loop for a single epic. The build-step skill parses an implementation plan and iterates through pending tasks via the Task tool.

How does TDD baseline enforcement work for agentized build loops?▼

TDD baseline enforcement works by requiring a baseline tag to maintain test immutability during agentized build loops. The build-step skill tracks circuit-breaker signals and optionally escalates to automated replanning to correct or justify failing tests.

What do I need to set up before orchestrating per-step epic development?▼

To set up per-step epic development orchestration, you need an epic plan and spec files, a build directory execution state, a TDD baseline tag, and a Task tool capable of spawning sub-agents. Run the build-step skill from an execute-plan orchestrator with these parameters.

Can I use automated replanning when a developer sub-agent fails TDD tests?▼

Yes, you can use automated replanning when a developer sub-agent fails TDD tests. The build-step skill applies circuit-breaker policies and optionally escalates failing tests to automated replanning to correct or justify the failure.

Why spawn fresh developer and reviewer sub-agents for each build step?▼

Spawning fresh developer and reviewer sub-agents for each build step maintains clean contexts and enforces review gates. This per-step orchestration ensures agentic teams make reliable, auditable progress through the epic implementation plan without human micromanagement.

What are the limitations of using circuit-breaker policies in TDD build orchestration?▼

Circuit-breaker policies in TDD build orchestration are limited to enforcing test immutability and tracking failure signals for a single epic. The build-step skill requires access to the epic plan and spec files, and cannot operate without a Task tool capable of spawning sub-agents.

Related Skills

Explore More Software Engineering Skills→
alexanderguyalexanderguy
4

dispatch

Orchestrate parallel agent tasks across a dependency graph with quality gates.

Community
Advanced
lemeblemeb

go-on

Assess workflow state, execute one step, and emit a status signal.

Community
Intermediate
aws-samplesaws-samples
18

agent-harness

Coordinate planner, worker, and evaluator subagents in a plan-execute-evaluate loop.

Official
Advanced
samjhechtsamjhecht
4

implement

Implement tasks from specs, plans, or issues using subagents with TDD and code review.

Community
Advanced