con un clic
am-command-init-rules
Initialize non-obvious modular rules for the codebase
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Initialize non-obvious modular rules for the codebase
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Analyze codebase with repomix, search skillshare for relevant skills, and recommend top 5
Reference codebase for Pi Extensions. Use this skill when you need to understand the structure, implementation patterns, or code details of the Pi Extensions project.
Plan and add as task
Basado en la clasificación ocupacional SOC
| name | am-command-init-rules |
| description | Initialize non-obvious modular rules for the codebase |
| x-agentsmesh-kind | command |
| x-agentsmesh-name | init-rules |
| x-agentsmesh-allowed-tools | ["Read","Grep","Glob","Bash","question"] |
Generate modular, path-scoped rules that are non-obvious, project-specific, and actionable using a 3-phase workflow.
Analyze the repository to identify project-specific conventions, not generic patterns:
package.json, go.mod, etc.) for project-specific dependenciesFor each rule, use the question tool to gather:
globs: for file scoping)targets: array)Create rule files in rules/ with strict guidelines:
---
description: Project-specific API response convention
targets: [claude-code, cursor]
globs: ["src/api/**/*.ts"]
---
- All endpoints must return the project's `ApiEnvelope<T>` type (never raw objects)
- Include `requestId` matching the `traceId` from the project's logger
- Use `handleApiError` wrapper for all catch blocks (no raw error throws)
withTransaction wrapper" not "handle DB errors")frontend/, backend/, testing/)❌ Obvious (reject): "Use strict TypeScript. Never use any."
✅ Non-obvious (accept): "Prefer project's Result<T, E> type over throws for all service layer errors"
After creating rules, suggest running agentsmesh generate to deploy to configured AI tools.