Skip to main content

benchmark-models

benchmark-models

Catalogue généré le 2026-05-11

En une phrase

Cross-model benchmark for gstack skills.

Quand l'utiliser

  • Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

Comment l'invoquer

  • Slash command : /benchmark-models (si exposé dans ton CLI)
  • Voice triggers : « compare models » · « model shootout » · « which model is best »
  • Phrases déclencheurs : voir la description complète ci-dessous
  • Auto-invocation : sur demande explicite

Description complète

Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

Pour aller plus loin

Preamble (run first)

Plan Mode Safe Operations

In plan mode, allowed because they inform the plan: $B, $D, codex exec/codex review, writes to ~/.gstack/, writes to the plan file, and open for generated artifacts.

Skill Invocation During Plan Mode

If the user invokes a skill in plan mode, the skill takes precedence over generic plan mode behavior. Treat the skill file as executable instructions, not reference. Follow it step by step starting from Step 0; the first AskUserQuestion is the workflow entering plan mode, not a violation of it. AskUserQuestion (any variant — mcp__*__AskUserQuestion or native; see "AskUserQuestion Format → Tool resolution") satisfies plan mode's end-of-turn requirement. If no variant is callable, the skill is BLOCKED — stop and report BLOCKED — AskUserQuestion unavailable per the AskUserQuestion Format rule. At a STOP point, stop immediately. Do not continue the workflow or call ExitPlanMode there. Commands marked "PLAN MODE EXCEPTION — ALWAYS RUN" execute. Call ExitPlanMode only after the skill workflow completes, or if the user tells you to cancel the skill or leave plan mode.

(extrait — voir le SKILL.md complet pour la suite)

Source

  • Plugin : gstack
  • Nom interne : benchmark-models
  • Fichier : /home/thymon/.claude/skills/gstack/benchmark-models/SKILL.md
Back to top