Evaluation Framework

What it does

When your agent uses it

• Designing quality gates
• Evaluation systems
• Decision frameworks

Example prompts

• “Use the evaluation-framework skill to provide weighted scoring, rubrics, and decision-threshold patterns”
• “/evaluation-framework”

Requirements

• Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Define Criteria
2. 2Score Each Criterion
3. 3Calculate Weighted Total
4. 4Apply Decision Thresholds

What it can do on your machine

Read from SKILL.md and the folder at commit 9f3eb00. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pytest

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evaluation Framework loads about 1.3k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~42

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 322 words, ~1,251 tokens.

name

evaluation-framework

description

Provides weighted scoring, rubrics, and decision-threshold patterns. Use when designing quality gates, evaluation systems, or decision frameworks.

alwaysApply

false

category

infrastructure

tags

evaluation, scoring, decision-making, metrics, quality

provides.infrastructure

weighted-scoring, threshold-decisions, evaluation-patterns

provides.patterns

criteria-definition, scoring-methodology, decision-logic

usage_patterns

quality-evaluation, scoring-systems, decision-frameworks, rubric-design

complexity

beginner

model_hint

fast

estimated_tokens

550

progressive_loading

true

criteria:
  - name: criterion_name
    weight: 0.30          # 30% of total score
    description: What this measures
    scoring_guide:
      90-100: Exceptional
      70-89: Strong
      50-69: Acceptable
      30-49: Weak
      0-29: Poor

scores = {
    "criterion_1": 85,  # Out of 100
    "criterion_2": 92,
    "criterion_3": 78,
}

total = sum(score * weights[criterion] for criterion, score in scores.items())
# Example: (85 × 0.30) + (92 × 0.40) + (78 × 0.30) = 85.5

thresholds:
  80-100: Accept with priority
  60-79: Accept with conditions
  40-59: Review required
  20-39: Reject with feedback
  0-19: Reject

criteria:
  correctness: {weight: 0.40, description: Does code work as intended?}
  maintainability: {weight: 0.25, description: Is it readable?}
  performance: {weight: 0.20, description: Meets performance needs?}
  testing: {weight: 0.15, description: Tests detailed?}

thresholds:
  85-100: Approve immediately
  70-84: Approve with minor feedback
  50-69: Request changes
  0-49: Reject, major issues

**Verification:** Run the command with `--help` flag to verify availability.
1. Review artifact against each criterion
2. Assign 0-100 score for each criterion
3. Calculate: total = Σ(score × weight)
4. Compare total to thresholds
5. Take action based on threshold range

# In your skill's frontmatter
dependencies: [leyline:evaluation-framework]

© athola, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files in plugins/leyline/skills/evaluation-framework of athola/claude-night-market.

• SKILL.md
• README.md
• modules/decision-thresholds.md
• modules/evaluation-rubric.md
• modules/multi-metric-evaluation-methodology.md
• modules/quality-metrics.md
• modules/scoring-patterns.md

Open the folder on GitHubat commit 9f3eb00