notque/vexjoy-agent / skills/meta/toolkit
toolkit
VerifiedToolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.
references/routing-table-updater/extraction-patterns.md
View on GitHub# Trigger Phrase Extraction Patterns
## Explicit Trigger Phrases
**Pattern:** Look for quoted phrases in description
```regex
"([^"]+)"
```
**Example:**
```yaml
description: Use when "lint code", "check style", or "format files"
```
**Extracted:** `["lint code", "check style", "format files"]`
## "Use when" Clauses
**Pattern:** Extract content after "Use when" keyword
```regex
(?:Use when|Trigger on|Invoke for)\s+(.+?)(?:\.|$)
```
**Example:**
```yaml
description: Automate testing. Use when running unit tests or integration tests.
```
**Extracted:** `["running unit tests", "integration tests"]`
## Action Verbs + Domain
**Pattern:** Match action verb + domain noun
```regex
(debug|fix|test|review|analyze|generate|create)\s+(\w+)
```
**Example:**
```yaml
description: Debug Go applications with systematic approach
```
**Extracted:** `["debug Go", "debug applications"]`
## Skill Purpose Keywords
**Common Keywords Map:**
- "lint", "format" → code quality checking
- "test", "TDD" → testing workflows
- "review", "audit" → code review
- "debug", "fix" → troubleshooting
- "refactor", "restructure" → code improvement
- "generate", "create" → code generation
**Example:**
```yaml
description: Lint Python code with ruff and mypy
```
**Extracted:** `["lint", "lint Python", "ruff", "mypy"]`
## Domain Keywords (Agents)
**Pattern:** Extract technology names
```regex
(Go|Python|TypeScript|React|Kubernetes|Docker|PostgreSQL|etc)
```
**Example:**
```yaml
description: Deep expertise in Go development, architecture, debugging
```
**Extracted:** `["Go", "Go development", "Go architecture", "Go debugging"]`
## Complexity Inference
**Simple:** Single action, tool wrapper, formatting
**Medium:** Multi-step, requires configuration, domain-specific
**Complex:** Orchestration, multi-tool, requires planning
**Keywords:**
- Simple: "quick", "simple", "check", "run"
- Medium: "comprehensive", "systematic", "analyze"
- Complex: "orchestrate", "coordinate", "plan"
## Fallback Strategy
If no explicit patterns found:
1. Use first sentence of description
2. Extract noun phrases
3. Default to skill/agent name as pattern
4. Mark complexity as Medium (conservative default)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |