Skill

eval

Track and review your AI relationship quality. Use when the user says /eval, wants to log a session, review progress, or check relationship metrics.

npx claudepluginhub amanasmuei/aman-claude-code --plugin aman-claude-code

Tool Access

This skill uses the workspace's default tool permissions.

Preview

You are managing the user's AI evaluation data stored in `~/.aeval/eval.md`.

SKILL.md

Similar Skills

finishing-a-development-branch

174.6k

Verifies tests pass on completed feature branch, presents options to merge locally, create GitHub PR, keep as-is or discard; executes choice and cleans up worktree.

superpowers

systematic-debugging

174.6k

Guides root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.

10 files

superpowers

writing-plans

174.6k

Writes implementation plans from specs for multi-step tasks, mapping files and breaking into TDD bite-sized steps before coding.

1 file

superpowers

Stats

Stars0

Forks0

Last CommitMar 23, 2026

Actions

View Source View Plugin View on GitHub View README

Evaluation Management

You are managing the user's AI evaluation data stored in ~/.aeval/eval.md.

When invoked

Read ~/.aeval/eval.md

Show current metrics: sessions count, trust level, trajectory

Show recent timeline entries if any exist

Ask if the user wants to log this session

Logging a session

When the user wants to log a session (or at session end):

Ask: "How was this session?" (great / good / okay / frustrating)

Ask: "What went well?" (optional)

Ask: "What could improve?" (optional)

Ask: "Trust change?" (increased / same / decreased)

Update ~/.aeval/eval.md:

Increment session count
Add timeline entry with date, rating, notes
Update trust level if changed
Update trajectory based on recent trend

Showing a report

When the user asks for a report:

Show session count, duration, trust trajectory

Show recent sessions with star ratings

Show milestones

Show patterns

If eval.md doesn't exist

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.

Evaluation Management

You are managing the user's AI evaluation data stored in ~/.aeval/eval.md.

When invoked

Read ~/.aeval/eval.md
Show current metrics: sessions count, trust level, trajectory
Show recent timeline entries if any exist
Ask if the user wants to log this session

Logging a session

When the user wants to log a session (or at session end):

Ask: "How was this session?" (great / good / okay / frustrating)
Ask: "What went well?" (optional)
Ask: "What could improve?" (optional)
Ask: "Trust change?" (increased / same / decreased)
Update ~/.aeval/eval.md:
- Increment session count
- Add timeline entry with date, rating, notes
- Update trust level if changed
- Update trajectory based on recent trend

Showing a report

When the user asks for a report:

Show session count, duration, trust trajectory
Show recent sessions with star ratings
Show milestones
Show patterns

If eval.md doesn't exist

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.