📊
QualityPython

Skill Forge Benchmark

by AgriciDaniel

Skill Forge Benchmark is a Quality skill for Claude Code, published by AgriciDaniel in skill-forge.

169 stars44 forkson AgriciDaniel/skill-forgeAdded 2026/09/08+2% in starsRepository updated 2026/04/10
aiclaude-codeclaude-code-skilldeveloper-toolsopen-source
Install in seconds
Install Skill Forge Benchmark
Copy Skill Forge Benchmark into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/AgriciDaniel/skill-forge/tree/main/skills/skill-forge-benchmark ~/.claude/skills/skill-forge-benchmark

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/AgriciDaniel/skill-forge.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/skill-forge-benchmark/SKILL.md in AgriciDaniel/skill-forge
Installs to
~/.claude/skills/skill-forge-benchmark
Collection
One of 10 skills cataloged from this repository
Category
Quality1897 skills

What Skill Forge Benchmark does

Skill Forge Benchmark measures Claude Code skill performance across multiple trials with pass rate, token usage, duration, and variance analysis. Use it to compare versions, detect regressions, and generate benchmark.json reports.

Skill Forge Benchmark is cataloged under Quality on DirSkills. Skill Forge Benchmark comes from a repository tagged ai, claude-code, claude-code-skill, developer-tools and open-source.

Documentation

README

Skill Benchmarking & Performance Tracking

Measure and compare skill performance across iterations with statistical rigor using multiple trials, variance analysis, and trend tracking.

Process

Step 1: Define Benchmark Configuration

Accept configuration as:

  • Existing eval set: Path to evals/evals.json (from /skill-forge eval)
  • Benchmark config: Custom config with trial count and thresholds

Benchmark config schema:

{
  "skill_name": "my-skill",
  "skill_path": "./my-skill",
  "eval_set_path": "./evals/evals.json",
  "trials_per_eval": 3,
  "baseline_type": "no_skill",
  "previous_benchmark": null,
  "thresholds": {
    "min_pass_rate": 0.8,
    "max_avg_tokens": 100000,
    "max_avg_duration_seconds": 120,
    "min_improvement_ratio": 1.0
  }
}

This is the opening of the README. Read the full README on GitHub.

Commands Skill Forge Benchmark provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /skill-forge

Frequently asked about Skill Forge Benchmark

  • What else does AgriciDaniel publish alongside Skill Forge Benchmark?

    Skill Forge Benchmark is one of 10 skills that DirSkills catalogs from AgriciDaniel/skill-forge, the repository it ships in. Its siblings there include Multi-Skill Orchestrator, Skill Forge and Skill Forge. Each one is a separate skill with its own page in this directory, installs the same way Skill Forge Benchmark does, and is maintained by AgriciDaniel in that same repository. The rest of the collection is listed on the AgriciDaniel/skill-forge page.

  • How does Skill Forge Benchmark compare to other Quality skills?

    Skill Forge Benchmark ranks #1764 by stars among the 1897 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Skill Forge Benchmark against them. Open each page to compare what they document and how they install.

More from AgriciDaniel/skill-forge

Skill Forge Benchmark is one of 10 skills cataloged on DirSkills from AgriciDaniel/skill-forge.

See all 10 skills
🧭
1h ago

Multi-Skill Orchestrator

Multi-Skill Orchestrator provides a template for routing a broad domain into focused sub-skills with shared references and command-based entry points. Use it when one Claude Code skill needs multiple workflows, context detection, and consistent orchestration.
AI Engineering
16944
🛠️
1h ago

Skill Forge

Skill Forge creates, reviews, and evolves Claude Code skills using the Agent Skills open standard and 3-layer architecture. Use it when you need to create a new skill, scaffold a multi-skill system, test, benchmark, or publish a skill.
AI Engineering
16944
🛠️
1h ago

Skill Forge

Skill Forge scaffolds Claude Code skills from a plan or description. Use it to generate SKILL.md files, sub-skills, scripts, references, agents, and templates for the Agent Skills standard.
AI Engineering
16944
🔧
1h ago

Skill Forge Convert

Skill Forge Convert ports Claude Code skills to Codex, Gemini CLI, Antigravity, and Cursor. Use it to analyze compatibility, generate platform-specific files, adapt frontmatter, and convert MCP config.
AI Engineering
16944
🧪
1h ago

Skill Forge Eval

Skill Forge Eval runs evaluation pipelines for Claude Code skills to check triggering accuracy, workflow correctness, and output quality. It creates eval metadata, runs executor and grading agents, and produces benchmark and feedback reports.
Quality
16944
🔧
1h ago

Skill Forge Evolve

Skill Forge Evolve improves existing Claude Code skills using feedback, logs, or test results. Use it to fix triggering problems, refine instructions, add sub-skills, or evolve the skill’s architecture.
AI Engineering
16944