Agent skill · operations · alirezarezvani
self-eval
Grade finished work honestly on two axes with a devil's-advocate pass against inflation. Use whenever the user asks how well a task went, to rate the work or for an honest self-review.
Why this skill is useful
Provides a structured evaluation framework that enhances the AI's ability to assess its own work quality and complexity, which is not commonly found in standard practices.
What it needs
About 5k tokens when loaded. Last updated 2026-08-05. 23,939 stars on the source repository.
What this skill does
Self-Eval: Honest Work Evaluation ultrathink Tier: STANDARD Category: Engineering / Quality Dependencies: None (prompt-only, no external tools required) Description Self-eval is a Claude Code skill that produces honest, calibrated work evaluations. It replaces the default AI tendency to rate everything 4/5 with a structured two-axis scoring system, mandatory devil's advocate reasoning, and cross-session anti-inflation detection. The core insight: AI self-assessment converges to "everything is a 4" because a single-axis score conflates task difficulty with execution quality. Self-eval separates these axes, then combines them via a fixed matrix that the model cannot override. Features Two-axis scoring — Independently rates task ambition (Low/Medium/High) and execution quality (Poor/Adequate/Strong), then combines via a lookup matrix Mandatory devil's advocate — Before finalizing, must argue for both higher AND lower scores, then resolve the tension Score persistence — Appends scores to .self-eval-scores.jsonl in the working directory, building history across sessions Anti-inflation detection — Reads past scores and flags clustering (4+ of last 5 identical) Matrix-locked scoring — The composite score comes from the matrix, not from direct selection. Low ambition caps at 2/5 regardless of execution quality Usage After completing work in a Claude Code session: With context about what to evaluate: The skill reviews the conversation history, identifies what was accomplished, scores it on both axes, runs the devil's advocate check, and appends the result to the score history file. Examples Example 1: Feature Implementation Output: Example 2: Bug Fix Output: --- What to Evaluate $ARGUMENTS If no arguments provided, review the full conversation history to identify what was accomplished this session. Summarize the work in one sentence before scoring. How to Score — Two-Axis Model Score on two independent axes, then combine using the matrix. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/self-eval--43a22a