Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Skill Eval Harness
Un framework formal de evaluación para sesiones de Claude Code, implementando principios de desarrollo orientado a evals (EDD).
## Cuándo Activar
- Configurar desarrollo orientado a evals (EDD) para flujos de trabajo asistidos por IA
- Definir criterios de pass/fail para la completitud de tareas en Claude Code
- Medir confiabilidad del agente con métricas pass@k
- Crear suites de pruebas de regresión para cambios de prompts o agentes
- Comparar rendimiento del agente entre versiones de modelos
## Filosofía
El Desarrollo Orientado a Evals trata los evals como las "pruebas unitarias del desarrollo de IA":
- Definir el comportamiento esperado ANTES de la implementación
- Ejecutar evals continuamente durante el desarrollo
- Rastrear regresiones con cada cambio
- Usar métricas pass@k para medición de confiabilidad
## Tipos de Eval
### Evals de Capacidad
Probar si Claude puede hacer algo que antes no podía:
```markdown
[CAPABILITY EVAL: feature-name]
Task: Descripción de lo que Claude debe lograr
Success Criteria:
- [ ] Criterio 1
- [ ] Criterio 2
- [ ] Criterio 3
Expected Output: Descripción del resultado esperado
```
### Evals de Regresión
…
The line at the top of this page pins the label git:20260607.ac0f11c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (6046 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
affaan-m/ecc · 299,696 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ui6cy6y3hd7kgfmu
GET https://markdownregistry.com/api/v1/resolve?ref=affaan-m/ecc/eval-harness
GET https://markdownregistry.com/api/v1/blob/7f94696a0eee7f6d2405ff6a624e1db66ed5f32a8ec5758f398ef922f2b2b256
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
affaan-m/ecc · .agents/skills/agent-sort/SKILL.md · Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras…
affaan-m/ecc · .agents/skills/article-writing/SKILL.md · Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice…
affaan-m/ecc · .agents/skills/backend-patterns/SKILL.md · Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express…
affaan-m/ecc · .agents/skills/benchmark-methodology/SKILL.md · Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine…
affaan-m/ecc · .agents/skills/brand-discovery/SKILL.md · Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers…
affaan-m/ecc · .agents/skills/brand-voice/SKILL.md · Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that…
affaan-m/ecc · .agents/skills/bun-runtime/SKILL.md · Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel…
affaan-m/ecc · .agents/skills/competitive-platform-analysis/SKILL.md · Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any…
affaan-m/ecc · .agents/skills/eval-harness/SKILL.md · Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Use when a…
a5c-ai/babysitter · library/methodologies/everything-claude-code/skills/eval-harness/SKILL.md · Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality…
jikig-ai/soleur · plugins/soleur/skills/eval-harness/SKILL.md · This skill provides a promptfoo eval harness that measures whether a Soleur skill or agent edit actually improves…
miaodx/roboclaws · skills/eval-harness/SKILL.md · Select and run Roboclaws validation, product, eval-suite, and live-agent eval rows from a plan, diff, or explicit…
