Compare two eval runs and report what changed. Reads both runs' events, transcripts, and produced artifacts. Writes a short markdown summary classifying differences as regression, improvement, or neutral.
Idioma del texto original: inglés
Menú
SkillsMP ha recopilado 8 skills de adam-s/agent-spec. Abre una skill para revisar su origen y sus detalles.
Mostrando 8 de 8 skills recopiladas.
Compare two eval runs and report what changed. Reads both runs' events, transcripts, and produced artifacts. Writes a short markdown summary classifying differences as regression, improvement, or neutral.
Idioma del texto original: inglés
Generalized recursive iteration loop. Runs parallel sub-agents against a target, scores deterministically, diagnoses instruction gaps, applies fixes, and recurses until the stop condition is met or max depth is reached.
Idioma del texto original: inglés
Run an evaluation against an eval with a specific config
Idioma del texto original: inglés
Write a handoff document so a new chat can continue the work
Idioma del texto original: inglés
Show evaluation results and comparisons
Idioma del texto original: inglés
Test-driven development of a Hono/Bun WebSocket application. Read requirements, read tests, build server, verify, iterate until all tests pass.
Idioma del texto original: inglés
Scaffold a new evaluation
Idioma del texto original: inglés
Stop all agent-spec processes, clear ports, remove sandboxes, verify clean state.
Idioma del texto original: inglés