component-pipeline

Orchestrates a six-stage pipeline for adding new language components to Semorphe.

9|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/timcsy/semorphe --skill component-pipeline-timcsy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: component-pipeline
Source: https://github.com/timcsy/semorphe/tree/main/knowledge/skills/component-pipeline
Command: npx skills add https://github.com/timcsy/semorphe --skill component-pipeline-timcsy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Adding support for a new language feature (e.g., C++ <algorithm>, Python list comprehensions) to Semorphe requires coordinating discovery, code generation, round-trip testing, fuzzing, integration, and browser verification. This Skill automates that entire end-to-end workflow with a single command, enforcing mandatory gates between stages so no step is silently skipped. ## Core Features & Use Cases - Six-Stage Orchestration: Sequentially invokes component-discover, component-generate, component-roundtrip, component-fuzz, component-integrate, and verify-in-browser via the Skill tool, with pass/fail gates after each stage. - Mandatory Browser Verification: The final stage visually checks blocks in the browser, catching UI defects (missing toolbox entries, wrong colors, misplaced mutation buttons) that green test suites cannot detect. - Flexible Flags: Supports --dry-run, --skip-fuzz, --components=X,Y,Z, and --fuzz-count=N to control scope and depth. - Use Case: Run the pipeline on "cpp <algorithm>" to research, generate, round-trip test, fuzz, integrate, and visually verify all new C++ algorithm blocks, then commit them on an auto-numbered feature branch with an optional PR. ## Quick Start Ask the AI to run the component pipeline for a target such as "cpp <algorithm>" or "python list comprehension" to add and fully verify new language components end to end.

Frequently Asked Questions about component-pipeline

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

FAQPage Schema
How do I add support for a new C++ or Python feature in Semorphe?

Run the component pipeline with a language and target, such as "cpp <algorithm>" or "python list comprehension". It automatically discovers concepts, generates block components, runs round-trip and fuzz tests, integrates them, and verifies the result in a browser.

What stages does the component pipeline run?

It runs six stages in order: discover, generate, round-trip, fuzz, integrate, and verify-in-browser. Each stage invokes a dedicated sub-skill through the Skill tool and must pass a gate before the next stage begins.

Can I skip fuzz testing or other pipeline stages?

Yes, the --dry-run flag skips stages 3 through 5, and --skip-fuzz skips only fuzz testing. The browser verification stage has no skip flag because it catches UI defects that test suites miss.

Why does the pipeline require browser verification after all tests pass?

Browser verification catches visual defects like missing toolbox entries, wrong block colors, and misplaced mutation buttons that no API or test suite can detect. It previously found five such defects while over 4900 tests were green.

What happens when the component pipeline fails at a stage?

The pipeline stops and reports which gate failed so you can fix the issue. All intermediate artifacts are preserved, and you can resume from any stage by invoking the individual sub-skills directly.

When should I use component-refactor instead of component-pipeline?

Use component-pipeline for adding brand-new concepts from scratch. Use component-refactor to repair existing components with incomplete paths, audit issues, or migrate hand-written lifters to JSON patterns.