# Send Regex to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "regex",
    "name": "Regex",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/regex",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/regex",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/regex",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=regex",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "regex",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-08T02:01:42.446Z",
      "expiresAt": "2026-05-15T02:01:42.446Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=regex",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=regex",
        "contentDisposition": "attachment; filename=\"regex-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "regex"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/regex"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/regex",
    "downloadUrl": "https://openagent3.xyz/downloads/regex",
    "agentUrl": "https://openagent3.xyz/skills/regex/agent",
    "manifestUrl": "https://openagent3.xyz/skills/regex/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/regex/agent.md"
  }
}
```
## Documentation

### Greedy vs Lazy

.* is greedy—matches as much as possible; .*? is lazy—matches minimum
Greedy often overshoots: <.*> on <a>b</a> matches entire string, not <a>
Default quantifiers + * {n,} are greedy—add ? for lazy: +? *? {n,}?

### Escaping

Metacharacters need escape: \\. \\* \\+ \\? \\[ \\] \\( \\) \\{ \\} \\| \\\\ \\^ \\$
Inside character class []: only ], \\, ^, - need escape (and ^ only at start, - only mid)
Literal backslash: \\\\ in regex, but in strings often need \\\\\\\\ (double escape)

### Anchors

^ start, $ end—but behavior changes with multiline flag
Multiline mode: ^ $ match line starts/ends; without, only string start/end
\\A always string start, \\Z always string end (not all engines)
Word boundary \\b matches position, not character—\\bword\\b for whole words

### Character Classes

[abc] matches one of a, b, c; [^abc] matches anything except a, b, c
Ranges: [a-z] [0-9]—but [a-Z] is invalid (ASCII order matters)
Shorthand: \\d digit, \\w word char, \\s whitespace; uppercase negates: \\D \\W \\S
. matches any char except newline—use [\\s\\S] for truly any, or s flag if available

### Groups

Capturing () vs non-capturing (?:)—use (?:) when you don't need backreference
Named groups: (?<name>...) or (?P<name>...) depending on engine
Backreferences: \\1 \\2 refer to captured groups in same pattern
Groups also establish scope for alternation: cat|dog vs ca(t|d)og

### Lookahead & Lookbehind

Positive lookahead (?=...): assert what follows, don't consume
Negative lookahead (?!...): assert what doesn't follow
Positive lookbehind (?<=...): assert what precedes
Negative lookbehind (?<!...): assert what doesn't precede
Lookbehinds must be fixed-width in most engines—no * or + inside

### Flags

i case-insensitive, m multiline (^$ match lines), g global (find all)
s (dotall): . matches newline—not supported everywhere
u unicode: enables \\p{} properties, proper surrogate handling
Flags syntax varies: /pattern/flags (JS), (?flags) inline, or function arg (Python re.I)

### Engine Differences

JavaScript: no lookbehind until ES2018; no \\A \\Z; no possessive quantifiers
Python re: uses (?P<name>) for named groups; no \\p{} without regex module
PCRE (PHP, grep -P): full features; possessive ++ *+; recursive patterns
Go: RE2 engine, no backreferences, no lookahead—guaranteed linear time

### Performance

Catastrophic backtracking: (a+)+ against aaaaaaaaaab is exponential—avoid nested quantifiers
Possessive quantifiers ++ *+ prevent backtracking—use when backtracking pointless
Atomic groups (?>...) don't give back chars—similar to possessive
Anchor patterns when possible—^prefix is O(1), unanchored prefix is O(n)

### Common Mistakes

Email validation: RFC-compliant regex is 6000+ chars—use simple check or library
URL matching: edge cases are endless—use URL parser, regex for quick extraction only
Don't use regex for HTML/XML—use a parser; regex can't handle nesting
Forgetting to escape user input—regex injection is real; use literal escaping functions

### Testing

Test edge cases: empty string, special chars, unicode, very long input
Visualize with tools: regex101.com shows matches and explains
Check which engine documentation you're reading—features vary significantly
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: ivangdavila
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-08T02:01:42.446Z
- Expires at: 2026-05-15T02:01:42.446Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/regex)
- [Send to Agent page](https://openagent3.xyz/skills/regex/agent)
- [JSON manifest](https://openagent3.xyz/skills/regex/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/regex/agent.md)
- [Download page](https://openagent3.xyz/downloads/regex)