- name
SKILL.md
El archivo de la skill permanece en el repositorio del publicador.
Pega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add sickn33/agentic-awesome-skills --skill agent-evaluation -a cursor -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add sickn33/agentic-awesome-skills --skill agent-evaluation -a claude-code -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add sickn33/agentic-awesome-skills --skill agent-evaluation -a codex -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add sickn33/agentic-awesome-skills --skill agent-evaluation -a grok -yEnvía el mensaje copiado en un chat de Grok Bot. El Bot obtiene este SKILL.md de GitHub y lo añade a las skills que comparten todos tus Bots.
Install this skill: https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/agentic-awesome-skills-claude/skills/agent-evaluationDel publicador
Evaluate observable agent behavior against task-specific cases. Modified by AAS maintainers on 2026-09-05 to remove unsupported benchmark claims, correct uncertainty/error reporting and separate optional architecture sketches from the operating procedure.
Use when comparing a changed agent, prompt or tool configuration, reproducing an observed failure, or estimating reliability on a declared task distribution. Do not infer product readiness from a public benchmark percentage or a generic score threshold.
A synthetic agent changes how it chooses a tenant identifier for a read-only lookup. Freeze three cases: an authorized lookup must return the seeded fixture, an unauthorized tenant must be rejected without a tool call, and a simulated tool outage must be classified as infrastructure failure. Supply neither real customer records nor production credentials.
Predeclare five repeats per case with fresh state, the same budget for baseline and candidate, and zero tolerance for an unauthorized tool call. Suppose the candidate returns the expected authorized result in all five runs but makes one unauthorized call in the second case: the candidate fails the permission contract even if its aggregate success rate improves. Retain that run, fix argument authorization, verify the negative case, and rerun the frozen suite. If the outage detector itself crashes, mark that case inconclusive and repair the detector before comparing versions. These are illustrative outcomes, not measured agent results.
Expected output:
contract: case-set revision, rules, repeat plan and budget
versions: baseline, candidate, model, prompt, tool and runtime
runs: one record per attempt, classified outcome and bounded evidence reference
comparison: per-case results, uncertainty, regressions and critical violations
decision: pass | fail | inconclusive; reason; unresolved work
Ten successes in ten independent trials do not demonstrate 100% reliability. This dependency-free helper returns an approximate 95% Wilson interval; for 10/10 it is about [0.7225, 1]. For zero trials it rejects the input.
function wilson95(passes, trials) {
if (!Number.isSafeInteger(passes) || !Number.isSafeInteger(trials)
|| trials <= 0 || passes < 0 || passes > trials) throw new Error('Invalid counts');
const z = 1.959963984540054;
const p = passes / trials;
const denominator = 1 + z * z / trials;
const center = (p + z * z / (2 * trials)) / denominator;
const margin = z * Math.sqrt(p * (1 - p) / trials + z * z / (4 * trials * trials)) / denominator;
return [Math.max(0, center - margin), Math.min(1, center + margin)];
}
Expected checks: 0/10 has a positive upper bound; 10/10 has a lower bound below 1; 0/0 fails. Use case-level or clustered uncertainty when repeated runs share cases or state; pooling correlated runs as independent observations overstates confidence. See NIST interval guidance.
Read the corresponding section in the bundled architecture sketches only when designing a custom harness:
The classes require application-specific adapters and are not copy-and-run implementations. No listed tool, related skill or delegate is a required dependency.
Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.
---name: agent-evaluationdescription: Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt…---# plugins/agentic-awesome-skills-claude/skills/agent-evaluation/SKILL.mdPreguntas frecuentes
Descarga plugins/agentic-awesome-skills-claude/skills/agent-evaluation/SKILL.md desde el publicador, o copia la ruta y abre el repositorio. PlugMCP lista la skill y no aloja el archivo.
El publicador lo mantiene en https://github.com/sickn33/agentic-awesome-skills.
Claude, Cursor, Codex y Grok Build pueden leer un SKILL.md que añadas desde el repositorio del publicador. Grok Bot lo instala cuando envías en un chat el enlace a la carpeta de la skill en GitHub.