spec-execution

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

509 stars

Best use case

spec-execution is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

Teams using spec-execution should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/spec-execution/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/claudekit/skills/spec-execution/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/spec-execution/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How spec-execution Compares

Feature / Agentspec-executionStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Spec Execution

## Overview

Executes a feature specification through 6 iterative phases with quality-gated convergence. Each phase builds on the previous, with improvement cycles triggered when quality falls below threshold.

## Six Phases

### Phase 1: Implementation
- Read specification for requirements and architecture
- Implement each requirement following project conventions
- Add type definitions and JSDoc documentation
- Implement error handling for all failure modes

### Phase 2: Test Writing
- Write unit tests for each module/function
- Write integration tests for API boundaries
- Cover all acceptance criteria from the specification
- Test edge cases and error paths

### Phase 3: Code Review
- Verify all requirements are implemented
- Check acceptance criteria are tested
- Review architecture adherence
- Assess code quality

### Phase 4: Iterative Improvement
- Address review findings
- Fix failing tests
- Resolve architecture deviations
- Re-verify quality (convergence loop, max 3 cycles)

### Phase 5: Atomic Commit
- Group changes into logical atomic commits
- Descriptive messages following project conventions
- Separate production, test, and config changes
- Include specification reference

### Phase 6: Progress Tracking
- Requirement completion percentage
- Test coverage summary
- Quality score report
- Remaining work identification

## Quality Gate

Quality threshold defaults to 80. If not met after max improvement cycles, a human breakpoint is triggered for review.

## When to Use

- `/spec:execute [file]` slash command
- After spec creation when ready to implement

## Processes Used By

- `claudekit-spec-workflow` (execute mode)