Summary
A meta-skill that enforces the house format for agentmemory skills so they stay skimmable and maintainable. You'll reach for this when writing a new skill from scratch, reviewing a contribution, or refactoring something that's grown messy. The format is opinionated: frontmatter with a two-sentence description that includes concrete "Use when" triggers, body under 100 lines with a fixed section order, and dense reference material split into separate markdown files. The real discipline is keeping facts generated from source rather than hand-typed, so CI can catch drift. It's designed for teams that treat skills as living documentation, not wiki pages.
Install to Claude Code
npx -y skills add rohitg00/agentmemory --skill write-agentmemory-skill --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
