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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agent charters and histories 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 by removing boilerplate, summarizing old entries, and promoting recurring patterns. - Report: Outputs a savings table showing before/after sizes per agent with totals and percentage reduction. - Use Case: When a coordinator hears "team, reskill" or suspects charter bloat, run this pass to slim every agent's context footprint while preserving unique identity and domain knowledge. ## Quick Start Ask the coordinator to run a team-wide 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 AI agent context size from bloated charters?

Run a reskill pass that audits all charters and histories, extracts patterns shared across 3+ agents into reusable skills, and trims each charter to a minimal template targeting 1.5KB or less. Histories are summarized and capped near 8KB.

When should repeated content be extracted into a shared skill?

Content found in only one charter stays in that charter. Overlap in two charters is extracted if it exceeds 500 bytes, and content appearing in three or more charters is always extracted into a shared skill.

What gets removed from an agent charter during optimization?

The Collaboration and Voice sections are removed, the Model section is trimmed to one line, and boilerplate boundaries text is deleted. Identity, ownership, unique working patterns, domain boundaries, and the tagline blockquote are always preserved.

What are the limitations of automated charter trimming?

The process must not delete unique per-agent identity or domain knowledge, must not create skills for single-agent content, and must not touch decisions.md. It relies on frequency thresholds, so judgment is needed for borderline two-charter overlaps.

How is the result of a reskill pass reported?

The pass outputs a savings table listing each agent's charter and history sizes before and after trimming, along with total bytes saved and the overall percentage reduction.