Skip to main content
skill CX Codex

skill-creation — Claude Code skill: what it does, how to install

skill-creation converts past session breakthroughs into reusable agent skills inside SKILL.md files. Helps extract repeatable patterns and refine existing instructions.

no license 142 installs ★ 129 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Factory-AI/factory-plugins --skill skill-creation -a claude-code
Open on GitHub

What skill-creation does

The skill captures successful problem-solving paths from agent sessions and turns them into standalone SKILL.md documents. Each file starts with YAML metadata containing its name and trigger criteria. A precise description is critical here because the agent relies on it when picking which skill to trigger for an incoming prompt.

Skills are organized on two levels. Shared project playbooks go into .factory/skills/ and get checked into version control. User-specific workflows stay in ~/.factory/skills/. The skill prompts you to include verification steps and explicit failure boundaries. Without automated verification checks, an agent cannot validate its own output.

To spot recurring bottlenecks, you can inspect JSONL session archives with rg. Breaking changes to inputs or outputs warrant a major version increment.

What it helps with

  • extract solved session problems into reusable SKILL.md guides
  • locate recurring errors across JSONL session logs with rg
  • establish project-wide conventions inside .factory/skills/
  • revise outdated agent instructions with new version tags

Example prompts for the agent

  • Extract the debugging steps from this session into a fresh skill
  • Update the deployment skill with verification steps and common edge cases
  • Inspect recent session logs to find repeated failures and improve the skill

How to install skill-creation

1Skills CLI (Vercel)

npx skills add Factory-AI/factory-plugins --skill skill-creation -a claude-code

2Manually: put the files in place

~/.claude/skills/skill-creation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-creation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-creation

How do I install skill-creation in Claude Code?

Run npx skills add Factory-AI/factory-plugins --skill skill-creation -a claude-code in your terminal.

What does the skill-creation skill do?

It guides you in turning ad-hoc session fixes into structured SKILL.md files with clear triggers, failure notes, and verification routines.

Where are skills stored?

Project skills live in .factory/skills/ so teammates can track them in git. Personal skills reside in ~/.factory/skills/ for cross-project use.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set17

The whole set →
visual-design visual-design is a Claude Code skill that uses nanobanana CLI to create or edit project visuals and Slidev to build presentations. It covers asset, diagram, photo-editing, and slide-deck requests. CX Codex +1 167installs threat-model-generation threat-model-generation — a skill for Claude Code, Codex, Cursor, and other agents that builds a STRIDE threat model from a repository's codebase. CX Codex +1 151installs ban-type-assertions ban-type-assertions is a Claude Code skill that blocks TypeScript as assertions and guides their replacement with compiler-checked code. It runs when a package adopts the ban or needs existing lint violations fixed. CX Codex +1 151installs fix-knip-unused-exports fix-knip-unused-exports resolves knip “Unused exports” violations by removing or relocating exports that have no production consumers. Use when npm run knip reports unused code. CX Codex +1 147installs autoresearch The autoresearch skill runs repeated code experiments against a measurable target. Use it for tuning tests, builds, bundle size, or ML training results. CX Codex +1 137installs vulnerability-validation vulnerability-validation is a Claude Code skill that tests whether security scan findings can be exploited and filters false alarms. It runs after commit-security-scan, before findings become issues or block a PR. CX Codex +1 135installs commit-security-scan The commit-security-scan skill reviews Git changes for security flaws using threat-model context. Use it for pull requests, staged files, or branch diffs. CX Codex +1 126installs http-toolkit-intercept http-toolkit-intercept captures HTTP requests and responses from any script or service — including LLM API calls, backend requests, and auth flows. Use it when you need to see what's actually sent over the wire and what comes back. CX Codex +1 124installs

Project sponsors

Companies that keep this analytics open