The Agent Skills Directory

[SAFE]: The skill establishes a set of markdown-based artifacts to manage project state, coordination rules, and agent handoffs, which is a standard best practice for multi-agent systems.\n- [SAFE]: The instructions focus on maintaining project continuity and visibility through manual updates to documentation, with no evidence of malicious behavior or prompt injection.\n- [SAFE]: Integration with the 'openspec' sub-skill is limited to specialized development tasks like proposal management and validation, following a modular and safe architecture.\n- [SAFE]: No sensitive file access, credential harvesting, or unauthorized network operations were detected in the skill's instructions or its reference documentation.

project-convergence