Skip to content
v1.0.0

Agent Self Improve

Arcantry 1.0.0agent-self-improve

Diagnose recurring communication failures in agent conversations and stage the smallest durable corrections for approval.

Diagnose recurring communication failures in supplied or available agent conversations and stage minimal guidance corrections for approval. Use only when explicitly requested.

arcantry skills link agent-self-improve --scope user

The standard destination is ~/.agents/skills. Codex reads this universal Agent Skills location directly.

arcantry skills link agent-self-improve --scope user --compat claude

This keeps the universal link and adds a Claude alias to the same canonical package.

Prompt

Use the agent-self-improve skill to review this project’s recent tasks. Focus on why the agent kept asking questions the repository already answered.

Expected outcome

A diagnosis tied to conversation evidence and numbered, approval-gated edits for the narrowest guidance layer.

Prompt

Use the agent-self-improve skill on this transcript and explain whether the failure came from execution, a skill, or project instructions.

Expected outcome

A scoped cause analysis that does not blame prompt wording or edit agent configuration without approval.