mejorar-tooling

Captures task learnings and edge cases into skill and agent documentation.

Updated Jun 10, 2026
One-click install
npx skills add https://github.com/saulo-fl/armado-en-mexico --skill mejorar-tooling-saulo-fl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mejorar-tooling
Source: https://github.com/saulo-fl/armado-en-mexico/tree/main/.claude/skills/mejorar-tooling
Command: npx skills add https://github.com/saulo-fl/armado-en-mexico --skill mejorar-tooling-saulo-fl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After completing non-trivial work, valuable lessons and edge cases are often lost, forcing the same mistakes to be relearned. This Skill closes that gap by recording each discovery directly into the relevant skill or agent documentation so future runs improve automatically. ## Core Features & Use Cases - Learning Log: Appends dated, actionable entries to a "Bitácora de aprendizajes" section in the appropriate skill or agent file. - Script Extraction: Moves repeated mechanical shell, Node, or Python sequences into deterministic scripts under the skill's scripts directory. - Trigger Tuning: Improves skill descriptions with better synonyms and triggers when a skill fails to activate when it should. - Use Case: After finishing an inventory reconciliation that hit an unexpected PDF parsing edge case, run this Skill to document the gotcha, extract the manual steps into a script, and publish the updated tooling. ## Quick Start Ask the assistant to review and update the skills and agents with the learnings from the task just completed.

Frequently Asked Questions about mejorar-tooling

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I document learnings from a completed task in Claude skills?▼

Identify which skill or agent covers the work you just finished, then add a dated line to its learning log section describing the edge case or decision. Keep entries concrete and actionable so the next execution benefits directly.

When should I update skill or agent documentation?▼

Update documentation after closing a non-trivial task such as an inventory reconciliation, a large UI change, or a deployment incident. Also update when you notice a repeated manual step that belongs in a script or when a skill failed to trigger.

How do I turn repeated manual steps into a reusable script?▼

Move the mechanical shell, Node, or Python sequence into a script inside the skill's scripts directory and reference it from the SKILL.md file. Verify the script runs correctly with python3 or node before committing.

Why did my skill not activate when it should have?▼

A skill fails to trigger when its description lacks the right synonyms or trigger phrases. Improve the description field with broader keywords matching how the task is actually phrased so it self-invokes next time.

What is the difference between a skill and an agent in this tooling?▼

A skill is a repeatable workflow with clear triggers, while an agent is a delegable executor. Prefer deterministic scripts over prose instructions whenever a step is mechanical.