spec-code-pipeline
Runs a strict Spec-to-Code pipeline for specific modules with automated quality gate scoring.
Install
mkdir -p .claude/skills/spec-code-pipeline && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12902" && unzip -o skill.zip -d .claude/skills/spec-code-pipeline && rm skill.zipInstalls to .claude/skills/spec-code-pipeline
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Run the repo-local Spec -> Matrix -> Tasks -> Plan -> Prompt -> Code workflow for one module, with stage gates and agent routing.Key capabilities
- →Run a complete development workflow for one module
- →Enforce stage-gate scoring at every step
- →Generate traceability, tasks, implementation plan, task prompt, and code
- →Route failures back to the current stage executor for repair
- →Escalate failures to upstream stages if repeated
How it works
This skill executes a sequential workflow (Spec -> Matrix -> Tasks -> Plan -> Prompt -> Code) for a single module, where each stage is followed by a gate that requires a composite score of 98 or higher from multiple AI models and a rules engine.
Inputs & outputs
When to use spec-code-pipeline
- →Implementing a new module based on a spec
- →Running an end-to-end development pipeline
- →Ensuring consistent code quality through automated gating
About spec-code-pipeline
Executes a defined workflow from module specification to code implementation. It enforces rigorous stage-gate scoring at every step, using multiple AI models and rules engines to ensure quality before moving to the next phase.
Run the repo-local Spec -> Matrix -> Tasks -> Plan -> Prompt -> Code workflow for one module, with stage gates and agent routing.
When not to use it
- →When working on multiple modules simultaneously
- →When the user wants to code from a Draft spec
- →When the user wants to bypass scoring gates manually
Limitations
- →Works on one module at a time
- →Requires a `composite_score` of at least 98 for each stage to advance
- →Has bounded repair loops: `max_stage_attempts = 3`, `max_total_gate_failures = 18`
How it compares
This skill enforces a rigorous, automated stage-gate process with multiple AI scorers and a rules engine for quality assurance, which is more structured and less prone to manual errors than a typical development workflow.
Compared to similar skills
spec-code-pipeline side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| spec-code-pipeline (this skill) | 0 | 3mo | Review | Advanced |
| agent-factory | 8 | 11mo | Review | Advanced |
| subagent-driven-development | 14 | 9mo | No flags | Advanced |
| continuous-learning-v2 | 10 | 3mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
continuous-learning-v2
affaan-m
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
agent-skill-creator
FrancyJGLisboa
This enhanced skill should be used when the user asks to create an agent, automate a repetitive workflow, create a custom skill, or needs advanced agent creation capabilities. Activates with phrases like every day, daily I have to, I need to repeat, create agent for, automate workflow, create skill for, need to automate, turn process into agent. Supports single agents, multi-agent suites, transcript processing, template-based creation, and interactive configuration. Claude will use the enhanced protocol to research APIs, define analyses, structure everything, implement functional code, and create complete skills autonomously with optional user guidance.
vibe-build
KhazP
Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".
swarm-coordination
joelhooks
Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination.