Skip to content
Skills Library
AI & agents · Analysis

evaluate-report

/evaluate-report

View evaluation results and benchmark reports for a skill or plugin. Use when reviewing past eval results, comparing benchmark runs, or tracking quality trends.

Licence
MIT
Last repository change
24.10.2026

Assessment and security

95/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content30 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

View evaluation results and benchmark reports for a skill or plugin. Use when reviewing past eval results, comparing benchmark runs, or tracking quality trends.

Arguments

/evaluate-report git-plugin/git-commit [--latest] | git-plugin [--history]
Original author description

View evaluation results and benchmark reports for a skill or plugin. Use when reviewing past eval results, comparing benchmark runs, or tracking quality trends.

How it works

  1. When to Use This Skill
  2. Parameters
  3. Execution
  4. Agentic Optimizations
  5. Quick Reference
Original SKILL.md headings · 118 lines, 533 words
SKILL.md preview
---
name: evaluate-report
description: View evaluation results and benchmark reports for a skill or plugin. Use when reviewing past eval results, comparing benchmark runs, or tracking quality trends.
args: <plugin/skill-name | plugin-name> [--latest] [--history] [--compare]
allowed-tools: Read, Glob, Grep, Bash(cat *), Bash(jq *), Bash(find *), Bash(ls *), TodoWrite
argument-hint: "git-plugin/git-commit [--latest] | git-plugin [--history]"
created: 2026-03-04
modified: 2026-10-10
compatibility: claude-code
reviewed: 2026-03-04
model: haiku
effort: low
---

# /evaluate:report

View evaluation results and benchmark reports for a skill or plugin.

## When to Use This Skill

| Use this skill when... | Use alternative when... |
|------------------------|------------------------|
| Want to see results from a past evaluation | Need to run new evaluations -> `/evaluate:skill` |
| Comparing benchmark runs over time | Want improvement suggestions -> `/evaluate:improve` |
| Reviewing quality trends for a plugin | Need structural compliance -> `plugin-compliance-check.sh` |

## Parameters

Parse these from `$ARGUMENTS`:

| Parameter | Default | Description |
|-----------|---------|-------------|
| `<target>` | required | `plugin/skill-name` for skill or `plugin-name` for plugin |
| `--latest` | true | Show most recent benchmark only |
| `--history` | false | Show all benchmark iterations |
| `--compare` | false | Compare current vs previous benchmark |

## Execution

### Step 1: Resolve target

Determine if `$ARGUMENTS` refers to a skill or plugin:
- Contains `/`: treat as `plugin-name/skill-name`, look for `<plugin>/skills/<skill>/eval-results/benchmark.json`
- No `/`: treat as `plugin-name`, look for `<plugin>/eval-results/plugin-benchmark.json`

If the target file does not exist, report that no evaluation results are available and suggest running `/evaluate:skill` or `/evaluate:plugin-batch`.

### Step 2: Load results

**Skill-level report** (`--latest` or default):
Read `benchmark.json` and display:

```
## Evaluation Report: <plugin/skill-name>

**Last run**: <timestamp>
**Runs per eval**: N

| Metric | With Skill | Baseline | Delta |
|--------|-----------|----------|-------|
| Pass Rate | 85% | 42% | +43% |
| Duration | 14s | 12s | +2s |

### Per-Eval Results

| Eval ID | Description | Pass Rate | Failures |
|---------|-------------|-----------|----------|
| eval-001 | Basic usage | 100% | — |
| eval-002 | Edge case | 67% | assertion X |
```

**Skill-level history** (`--history`):
Read `history.json` and display improvement iterations:

```
## Evaluation History: <plugin/skill-name>

| Version | Date | Pass Rate | Changes |
|---------|------|-----------|---------|
| v3 (current) | 2026-03-04 | 85% | Improved step 3 instructions |
| v2 | 2026-03-01 | 72% | Added error handling |
| v1 | 2026-02-28 | 55% | Initial evaluation |
```

**Skill-level comparison** (`--compare`):
Read current and previous benchmarks, show delta:

```
## Comparison: <plugin/skill-name>

| Metric | Previous | Current | Delta |
|--------|----------|---------|-------|
| Pass Rate | 72% | 85% | +13% |
| Duration | 16s | 14s | -2s |

Improved evals: eval-002, eval-004
Regressed evals: none
```

**Plugin-level report**:
Read `plugin-benchmark.json` and display:

```
## Plugin Report: <plugin-name>

| Skill | Evals | Pass Rate | Status |
|-------|-------|-----------|--------|
| skill-a | 4 | 100% | PASS |
| skill-b | 3 | 67% | NEEDS WORK |

**Overall**: 82% pass rate
**Skills evaluated**: N / M total
```

## Agentic Optimizations

| Context | Command |
|---------|---------|
| Find skill benchmark | `cat <plugin>/skills/<skill>/eval-results/benchmark.json \| jq .summary` |
| Find plugin benchmark | `cat <plugin>/eval-results/plugin-benchmark.json \| jq .summary` |
| Check for history | `cat <plugin>/skills/<skill>/eval-results/history.json \| jq '.iterations \| length'` |
| List available results | `find <plugin> -name benchmark.json -o -name plugin-benchmark.json` |

## Quick Reference

| Flag | Description |
|------|-------------|
| `--latest` | Most recent benchmark (default) |
| `--history` | Show all iterations |
| `--compare` | Compare current vs previous |

Versions

The database has no other skills named evaluate-report.

Database snapshot: 13.11.2026 · package version 396cb0b90814 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100evaluate-plugin
    Evaluate plugin quality. Use when user says \"evaluate plugin\", \"review plugin quality\", \"score my plugin\", \"check plugin\", \"rate plugin\".
  • 100evaluate-plugin-batch
    Batch evaluate every skill in a plugin and produce a plugin-level report. Use when auditing an entire plugin's quality or validating before a release.
  • 100eval-compare
    Compare evaluation results across multiple models or runs. Takes a directory of eval run artifacts (summary.yaml, run_result.json, HTML reports) and produces a tabbed HTML comparison report with model cards, quality/cost tables, per-case breakdowns, and embedded original…
  • 100bmad-eval-runner
    Run a skill's evals and report results. Use when the user wants to evaluate a skill, run evals, benchmark a skill, validate triggers, optimize a description, or grade skill outputs.
  • 100claude-skills-benchmark
    Evaluate and benchmark Agent Skills quality using static analysis and evaluation methodology. Use when discussing skill quality, benchmarking skills, measuring activation rates, or reviewing skill effectiveness.
  • 100local-evaluate-plugin-cf170bc7
    Evaluate a local Codex plugin in engineer-friendly language. Use when the user says "evaluate this plugin", "audit this plugin", "why did this score that way", "what should I fix first", "help me benchmark this plugin", or asks for a plugin-wide report before comparing versions.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.