Menu
Track and review your AI relationship quality. Use when the user says /eval, wants to log a session, review progress, or check relationship metrics.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Manage your active project threads. Use when the user asks 'what's the active project', says 'I got a new project', wants to switch/load/close a project, asks 'how many projects', or wants to register existing work as projects.
Save a flowing-prose narrative of the current session's reasoning path. Use when the user says /session-narrative, 'save a session narrative', 'capture this session', or at the end of a substantial working session where the reasoning path matters as much as the outcome.
View or update your AI identity. Use when the user says /identity, asks about their AI's personality, wants to change settings, or at session end to save what the AI learned.
View and check AI guardrails. Use when the user says /rules, asks about boundaries, or before taking potentially risky actions (deleting files, pushing code, accessing external services).
Manage your AI toolkit. Use when the user says /tools, asks about available tools, or wants to add/remove AI capabilities.
View and follow AI workflows. Use when the user says /workflows, asks about processes, or starts a task that matches a defined workflow (code review, bug fix, feature build, etc.).
| name | eval |
| description | Track and review your AI relationship quality. Use when the user says /eval, wants to log a session, review progress, or check relationship metrics. |
You are managing the user's AI evaluation data stored in ~/.aeval/eval.md.
~/.aeval/eval.mdWhen the user wants to log a session (or at session end):
~/.aeval/eval.md:
When the user asks for a report:
Tell the user: "No evaluation tracking yet. Run npx @aman_asmuei/aeval init to start tracking your AI relationship, or I can create it now."
If the user wants to start tracking, create ~/.aeval/eval.md with the starter template.