One-click install
npx skills add https://github.com/elbruno/ElBruno.MagenticUI --skill reskill-elbruno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reskill
Source: https://github.com/elbruno/ElBruno.MagenticUI/tree/main/.squad/templates/skills/reskill
Command: npx skills add https://github.com/elbruno/ElBruno.MagenticUI --skill reskill-elbruno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agent charters and history files accumulate duplicated boilerplate and repeated learnings over time, inflating per-agent context consumption. This Skill performs a team-wide optimization pass that audits, extracts, and trims that bloat into shared reusable skills. ## Core Features & Use Cases - Audit: Measures charter and history byte sizes and identifies boilerplate repeated across 3+ charters, shared domain knowledge, and mature learnings appearing 3+ times. - Extract: Creates or updates skills at .squad/skills/{skill-name}/SKILL.md with confidence levels (low, medium, high) based on how many agents share the pattern. - Trim: Reduces charters to a ≤1.5KB minimal template and histories to ≤8KB, then reports a before/after savings table with totals and percentage reduction. - Use Case: When a coordinator hears "team, reskill" or suspects charter bloat, run this pass to consolidate collaboration boilerplate into one skill and shrink every agent's context footprint. ## Quick Start Ask the coordinator to run a team reskill pass to audit all agent charters and histories, extract shared patterns into skills, and report the context savings.

Frequently Asked Questions about reskill

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

FAQPage Schema
How do I reduce context size of AI agent charters?▼

Run a reskill pass that audits all charters for repeated boilerplate, extracts shared patterns into standalone skills, and trims each charter to a minimal template targeting 1.5KB or less. Keep only identity, owned domains, unique work patterns, and boundaries.

When should shared agent knowledge be extracted into a skill?▼

Extraction depends on occurrence count: content in one charter stays put, content in two charters is extracted if overlap exceeds 500 bytes, and content in three or more charters is always extracted to a shared skill.

What parts of an agent charter should never be removed?▼

Never remove the tagline blockquote, unique per-agent identity, domain-specific knowledge, or the Model preference line, since the coordinator needs it for model selection. The decisions file is also off-limits during reskill.

How are agent history files trimmed during optimization?▼

Histories over 12KB get history-hygiene applied, recurring patterns appearing 3+ times are promoted to skills, old entries are summarized into a Core Context section, and session-specific metadata like dates and branch names is removed, targeting 8KB or less.

What confidence levels are assigned to extracted skills?▼

Confidence reflects adoption breadth: low for a first observation, medium when two or more agents share the pattern, and high when the pattern is team-wide.