improve-creating-new-skills
Sub-skill of improve: Creating New Skills (+3).
Best use case
improve-creating-new-skills is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of improve: Creating New Skills (+3).
Teams using improve-creating-new-skills 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/creating-new-skills/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How improve-creating-new-skills Compares
| Feature / Agent | improve-creating-new-skills | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sub-skill of improve: Creating New Skills (+3).
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.
SKILL.md Source
# Creating New Skills (+3) ## Creating New Skills 1. Search `.Codex/skills/**/*.md` for existing coverage 2. If no match, create at `.Codex/skills/<category>/<subcategory>/<name>/SKILL.md` 3. Follow existing SKILL.md template (YAML frontmatter + markdown sections) 4. Mark as `auto_generated: true` in frontmatter 5. Log in changelog with source pattern evidence ## Enhancing Existing Skills 1. Read current SKILL.md 2. Identify section to update (Quick Reference, examples, error handling) 3. Apply surgical edit (append examples, fix instructions) 4. Bump patch version in frontmatter 5. Log enhancement in changelog ## Deprecating Skills 1. Verify: no usage in last 90 days (check session logs, git history) 2. Verify: superseded by another skill (identify replacement) 3. Add to frontmatter: `deprecated: true`, `deprecated_date`, `replacement_skill` 4. Do NOT delete — archive in next pass ## Archiving Skills 1. Move from `.Codex/skills/<category>/` to `.Codex/skills/_archive/<category>/` 2. Add archive metadata: `archive_date`, `reason`, `original_path` 3. Update any cross-references in other skills
Related Skills
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
extract-skills-from-hermes-sessions
Automatically analyze Codex session transcripts to identify and extract reusable skills using LLM analysis via OpenRouter
extract-skills-from-Codex-sessions
Automatically extract reusable skills from Codex session transcripts using LLM analysis and wire them into a Stop hook
improve-trigger-conditions
Sub-skill of improve: Trigger Conditions.
improve-scope
Sub-skill of improve: Scope.
improve-related-commands
Sub-skill of improve: Related Commands.
improve-phase-1-collect-gather-session-signals
Sub-skill of improve: Phase 1: COLLECT — Gather Session Signals (+6).
improve-manual-vs-automatic-invocation
Sub-skill of improve: Manual vs Automatic Invocation.
improve-integration
Sub-skill of improve: Integration.
improve-decision-logic-scoring
Sub-skill of improve: Decision Logic (Scoring).
scientific-problem-selection-the-9-skills-overview
Sub-skill of scientific-problem-selection: The 9 Skills Overview.
solver-benchmark-creating-benchmark-specs
Sub-skill of solver-benchmark: Creating Benchmark Specs.