Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Debug regex patterns with visual breakdowns, plain English explanations, test case generation, and flavor conversion. Use when user needs help with regular expressions or pattern matching.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Interactive regex testing, explanation, and debugging tool.
Activate when the user:
Analyze the Regex Pattern
Provide Plain English Explanation
Visual Breakdown
Test Against Examples
Identify Common Issues
Generate Test Cases
Suggest Improvements
Convert Between Flavors
# Regex Analysis: `pattern`
## Plain English Explanation
This pattern matches [description]:
- `^` - Start of string
- `[A-Z]` - One uppercase letter
- `\d{3}` - Exactly 3 digits
- `$` - End of string
**Overall**: Matches strings like "A123", "Z999"
## Visual Structure
^ - Start anchor [A-Z] - Character class (uppercase letters) \d{3} - Digit, exactly 3 times $ - End anchor
## Test Results
### Matches
- `A123` -> Full match
- `Z999` -> Full match
### No Match
- `a123` -> Lowercase 'a' doesn't match [A-Z]
- `A12` -> Only 2 digits (needs 3)
- `A1234` -> Too many digits
## Capture Groups
1. Group 1: `[captured text]`
2. Group 2: `[captured text]`
## Issues Found
**Issue 1**: Pattern is too restrictive
- **Problem**: Doesn't handle lowercase letters
- **Fix**: Use `[A-Za-z]` instead of `[A-Z]`
## Suggested Improvements
```regex
# More flexible version
^[A-Za-z]\d{3,5}$
Changes:
{3} to {3,5} for 3-5 digitsA123
Z999
B456
1ABC (starts with digit)
ABCD (no digits)
A12 (too few digits)
JavaScript: [any JS-specific notes] Python: [any Python-specific notes]
const pattern = /^[A-Z]\d{3}$/;
const match = str.match(pattern);
import re
pattern = r'^[A-Z]\d{3}$'
match = re.match(pattern, string)
(?:...) for better performance
## Examples
**User**: "Why doesn't this regex match emails: `\w+@\w+\.\w+`?"
**Response**: Analyze pattern → Explain it matches simple emails only → Show test cases (fails on "user+tag@domain.co.uk") → Identify issues (doesn't handle special chars, multiple TLDs) → Provide improved pattern → Generate comprehensive test cases
**User**: "Explain this regex: `^(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$`"
**Response**: Break down pattern (IP address matcher) → Explain each component → Show it matches valid IPs (0-255 per octet) → Provide test cases → Visualize structure
**User**: "Convert this Python regex to JavaScript: `(?P<name>\w+)`"
**Response**: Identify named capture group (Python feature) → Convert to JS equivalent → Explain differences → Show both versions with usage examples
## Best Practices
- Always test regex with edge cases
- Explain in plain English first
- Show concrete examples (not just theory)
- Highlight common pitfalls for each pattern
- Provide both positive and negative test cases
- Consider performance implications
- Note flavor-specific features
- Suggest simpler alternatives when possible
- Use non-capturing groups for performance
- Escape special characters properly
- Be explicit about case sensitivity
- Test with Unicode characters if relevant
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.
日本語の概要は準備中です。原文の説明を表示しています。
Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.
日本語の概要は準備中です。原文の説明を表示しています。
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
日本語の概要は準備中です。原文の説明を表示しています。
Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.
日本語の概要は準備中です。原文の説明を表示しています。
Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.
日本語の概要は準備中です。原文の説明を表示しています。