Search skills.../

Stc Narrativa Lotes | Skills Pool

Skill File

Stc Narrativa Lotes

Use when editing /api/dashboard/narrativa-lotes, generarNarrativaLocal, and Gemini prompt so backend narrative keeps matrix parity with dashboard criteria.

CRISTIANESCOBAR-ar0 starsMar 6, 2026

Occupation
Categories: Automation Tools

Skill Content

47:T5bf,

STC Narrativa Lotes

Goal

Maintain a single source of truth for narrative criteria in backend local generation and LLM prompt output.

Use When

User asks to adjust narrative logic for lote audit output.
Endpoint /api/dashboard/narrativa-lotes gives wrong status.
Local fallback and Gemini output diverge.

Primary Files

backend/server.js

Procedure

Find and review:
- generarNarrativaLocal(...)
- MATRIZ_BASE
- Process audit block (AUDITORIA DE APTITUD POR PROCESO)
- Prompt text used before Gemini call.
Keep matrix entries explicit per Ne with and bands.

Related Skills

Quick Install

Stc Narrativa Lotes

npx skills add CRISTIANESCOBAR-ar/analisis-produccion-stc-postgresql

Download Skill Open repository

Author: CRISTIANESCOBAR-ar
stars: 0
Updated: Mar 6, 2026
Occupation

On this page

01STC Narrativa Lotes

ok

w

Use one evaluator for all variables:

ok, warn, crit, and sin-dato handling.

Build process status from severities:

Any crit -> Rechazado
No crit and any warn (or fiber warning) -> Condicional
Else -> Aprobado

Mirror the same rules in prompt text. Never keep binary prompt if local is tri-state.

Add comments only when they help production interpretation and do not contradict matrix logic.

Validation

Run syntax check:
- node --check backend/server.js
Search for stale binary status strings in backend.
Confirm output template explicitly includes Aprobado/Condicional/Rechazado.

Guardrails

Do not silently change thresholds without documenting Ne and variable affected.
Do not mix FLAME and liso criteria.
Prefer deterministic local logic; prompt should explain, not redefine.

02

Goal

04Primary Files

Software Developers

Automation Tools

Coding Agent (bash-first)

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

Automation Tools

Fix

Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.

Automation Tools

Commit

Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'.

microsoft184.0k

Automation Tools

Init

Generate or update chat customization files for AI coding agents

microsoft184.0k

Automation Tools

Github Copilot Upgrader

Use this to update the Github Copilot CLI/SDK

microsoft184.0k

Automation Tools

Rebuilding Flutter Tool

Rebuilds the Flutter tool and CLI. Use when a user asks to compile, update, regenerate, or rebuild the Flutter tool or CLI.

Software Developers