Agent Self Improve
Diagnose recurring communication failures in agent conversations and stage the smallest durable corrections for approval.
Use when: Diagnose recurring communication failures in supplied or available agent conversations and stage minimal guidance corrections for approval. Use only when explicitly requested.
Install only this skill
Section titled “Install only this skill”arcantry skills link agent-self-improve --scope userThis links only agent-self-improve to the standard user location, ~/.agents/skills. Use --scope repo for one repository, or add --compat claude when that optional alias is needed.
History
Section titled “History”- 2026-08-18 - Coordinate project knowledge and agent workflows with Arcantry: Arcantry provides local-first project configuration, safe repository adoption, a portable catalog of focused agent skills, and one documented workflow for maintaining project intent, release meaning, task intake, verification, and audience-safe content.
- 2026-08-17 - Unified Arcantry capabilities: Arcantry now combines its OpenSpec lifecycle with reusable skills, a complete Codex plugin, a versioned catalog, and one CLI for safe repository adoption and skill management.
Examples
Section titled “Examples”Review a frustrating project task
Section titled “Review a frustrating project task”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.
Evaluate a supplied transcript
Section titled “Evaluate a supplied transcript”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.