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.
Langue du texte source : anglais
Menu
SkillsMP a collecté 8 skills depuis adam-s/agent-spec. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 8 skills collectés sur 8.
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Run an evaluation against an eval with a specific config
Langue du texte source : anglais
Write a handoff document so a new chat can continue the work
Langue du texte source : anglais
Show evaluation results and comparisons
Langue du texte source : anglais
Test-driven development of a Hono/Bun WebSocket application. Read requirements, read tests, build server, verify, iterate until all tests pass.
Langue du texte source : anglais
Scaffold a new evaluation
Langue du texte source : anglais
Stop all agent-spec processes, clear ports, remove sandboxes, verify clean state.
Langue du texte source : anglais