RegEx Pattern Optimizer skill for Claude and Codex
Rewrites a slow or backtracking-prone regex into an equivalent that runs in predictable time on your engine, with the changes explained and a residual risk…
Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.
Download the skill (.zip) · View SKILL.md
When it is used
Use when a regex times out, pins the CPU, or risks catastrophic backtracking on long inputs and needs a faster equivalent for a specific engine. Do not use for writing a new regex from a description, or commenting a pattern for readability. Related topics: coding, regex.
What it will ask you for
- Target engine (choose one: PCRE, JavaScript, Python, Go, Rust)
- Pattern (longer free text)
- Sample input (longer free text)
- Typical input length (characters) (number from 1 to 1000000)
- Primary goal (choose any: Speed, Readability, Memory, Compatibility)
- Allow lookarounds (choose one: Yes, No)
How it works
- Locate every backtracking hazard in the pattern: nested quantifiers, overlapping alternations, greedy dot-star, and groups that can match empty.
- Rewrite each hazard with the engine's tools (atomic groups, possessive quantifiers, exclusive classes, anchors) without changing the match set.
- For Go and Rust, remove backreferences and lookarounds since the engines reject them, and note any behaviour that cannot be preserved.
- Verify the new pattern on the sample input and on an adversarial string of the stated length, and score the residual risk from 1 to 10.
- Package the result as the three-key JSON object with a three-sentence explanation.
What you get
A JSON object with the keys optimized_pattern, explanation (three sentences), and risk_score (integer 1 to 10), and nothing outside the JSON.
What it watches out for
- Replacing a greedy dot-star with a lazy one, which still backtracks on failure and only moves the cost around.
- Quietly dropping a lookaround for Go compatibility so the pattern now matches strings the original rejected.
- Scoring risk from the sample input alone when the hazard only appears on long inputs that nearly match.
How to install
Claude.ai and the Claude desktop app
- Download the skill .zip.
- Open Settings, then Capabilities, and find Skills.
- Choose Upload skill and select the .zip.
- Ask Claude for help with the task. It loads the skill when your request matches.
Claude Code
- Download the skill .zip.
- Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
- Start a new session. Claude Code loads the skill when your request matches.
Codex
- Download the skill .zip.
- Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
- Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.
Cursor
- Download the Cursor rule (.mdc).
- Save it in .cursor/rules/ inside your project.
- Cursor's agent applies the rule when your request matches its description.
AGENTS.md (Codex, Cursor, and other coding agents)
- Copy the AGENTS.md section.
- Paste it into AGENTS.md at the root of your repository, creating the file if needed.
- Coding agents that read AGENTS.md follow it when your request fits.