Forge Benchmark — Development skill for Claude Code
Measure validation posture across 5 dimensions with trend tracking.
How to install Forge Benchmark
Installs to ~/.claude/skills/krzemienski-validationforge-forge-benchmark/SKILL.md
mkdir -p ~/.claude/skills/krzemienski-validationforge-forge-benchmark && curl -fsSL https://raw.githubusercontent.com/krzemienski/validationforge/HEAD/commands/forge-benchmark.md -o ~/.claude/skills/krzemienski-validationforge-forge-benchmark/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Forge Benchmark does
name: forge-benchmark description: "Measure validation posture across 5 dimensions with trend tracking" allowed-tools: "Read, Write, Bash, Glob, Grep"
/forge-benchmark
Score your project's validation posture.
Dimensions
| Dimension | Weight | Target |
|---|---|---|
| Coverage | 30% | >80% features validated |
| Detection | 25% | >70% defect detection |
| Evidence Quality | 25% | >90% cited evidence |
| Speed | 10% | <5 min/journey |
| Cost | 10% | Decreasing tr |
Alternatives in Development
- Skill Creator — Create new skills, modify existing skills, and measure skill performance 94.1k ★
- Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
- Evo — turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run 1.4k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Validate Team Dashboard
Aggregate team validation posture into a shared dashboard showing coverage, scores, regressions, and ownership
Forge Team
Multi-agent parallel validation across platforms
Lt Bartini Method
LT method of Bushuev-Bartini-Kuznetsov as an agent skill: resolve contradictions by assigning physical dimensi
Benchmark Rerankers
Measure whether adding a reranker actually improves retrieval, by scoring reranked vs. un-reranked results on
Performance Report
Generate a marketing performance report with KPI tracking, trend analysis, anomaly detection, and recommendati
Pbi Dax
Delegate measure work or a read-only DAX question to pbi-dax: create/optimize measures with validation and sam
Related Agents
Health Checker
Code health dashboard agent - structured 3-phase methodology (detect, measure, prescribe) with weighted 0-10 s
Sub Benchmark Runner
Dept 4 sub. Runs standard benchmark tasks to measure agent and model reliability. Reports only, no product cha
Cto Self Eval
CTO-grade codebase self-evaluation. Measures code health, dead code, debt density, test meaningfulness, and ov