using-singularity

Coordinate Claude Code skill evolution by detecting capability gaps and initiating creation, evaluation, repair, or hardening.

27|2|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/Shmayro/singularity-claude --skill using-singularity
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-singularity
Source: https://github.com/Shmayro/singularity-claude/tree/main/skills/using-singularity
Command: npx skills add https://github.com/Shmayro/singularity-claude --skill using-singularity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps coordinate the life cycle of Claude Code skills by detecting capability gaps and guiding creation, evaluation, repair, and hardening through recursive improvement loops.

Core Features & Use Cases

  • Gap detection and automated skill creation via /singularity-create
  • Scoring and telemetry with /singularity-score and /singularity-review
  • Repair and crystallize workflows to improve and lock skill versions
  • Guidance for maturation through draft, tested, hardened, and crystallized stages

Quick Start

Detect a capability gap and trigger the singularity workflow to create or improve a skill.

Frequently Asked Questions about using-singularity

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

FAQPage Schema
How do I automate Claude Code skill creation when capability gaps are detected?

Automate Claude Code skill creation by triggering recursive improvement loops that detect capability gaps and initiate /singularity-create workflows to generate new skills automatically.

What is the best way to evaluate and score Claude Code skills using telemetry?

Evaluate and score Claude Code skills by applying /singularity-score and /singularity-review commands to collect telemetry data, measuring skill maturity and detecting performance gaps across recurring tasks.

How does recursive skill improvement work for maturing Claude Code capabilities?

Recursive skill improvement works by guiding Claude Code capabilities through draft, tested, hardened, and crystallized stages using repair and hardening loops to continuously refine skill versions.

Can I repair and lock specific versions of Claude Code skills after evaluation?

Yes, you can repair and lock specific Claude Code skill versions by initiating /singularity-repair to fix issues and /singularity-crystallize to harden and lock the evaluated skill versions.

Do I need internal commands and registry access to coordinate skill evolution across multiple skills?

Yes, coordinating skill evolution across multiple skills requires access to internal commands like /singularity-create and /singularity-score, plus telemetry and registry locations defined in the data model.

When should I initiate a skill hardening workflow instead of creating a new skill?

Initiate a skill hardening workflow instead of creating a new skill when existing capabilities show recurring task failures or telemetry gaps, indicating the current skill needs repair and maturation rather than replacement.