Profile live inference traffic into a token/shape distribution artifact that drives profile-matched speculative-decoding draft training -- an analog of Fireworks FireOptimizer's "profile-driven customization" (the documented source of its higher draft hit-rate). Reads an OpenAI-style access JSONL, emits workload-profile.json (input/output length distributions, content-class mix, ISL/OSL bench shapes, and a spec-decode method recommendation), and hands off to inference-spec-decode-train via a hit-rate-matched corpus. The first phase of the adaptive spec-decode loop. Triggers on "profile my workload", "workload profile for spec-decode", "what draft should I train", "match the draft to my traffic", "adaptive speculative decoding", "fireoptimizer equivalent", "profile traffic for a draft model", or any combination of "profile / characterize / sample" with "workload / traffic / requests" and "spec-decode / draft / acceptance / hit-rate".
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryContent & writingStars0
About this skill
Profile live inference traffic into a token/shape distribution artifact that drives profile-matched speculative-decoding draft training -- an analog of Fireworks FireOptimizer's "profile-driven customization" (the documented source of its higher draft hit-rate). Reads an OpenAI-style access JSONL, emits workload-profile.json (input/output length distributions, content-class mix, ISL/OSL bench shapes, and a spec-decode method recommendation), and hands off to inference-spec-decode-train via a hit-rate-matched corpus. The first phase of the adaptive spec-decode loop. Triggers on "profile my workload", "workload profile for spec-decode", "what draft should I train", "match the draft to my traffic", "adaptive speculative decoding", "fireoptimizer equivalent", "profile traffic for a draft model", or any combination of "profile / characterize / sample" with "workload / traffic / requests" and "spec-decode / draft / acceptance / hit-rate".
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Profile live inference traffic into a token/shape distribution artifact that drives profile-matched speculative-decoding draft training -- an analog of Fireworks FireOptimizer's "profile-driven customization" (the documented source of its higher draft hit-rate). Reads an OpenAI-style access JSONL, emits workload-profile.json (input/output length distributions, content-class mix, ISL/OSL bench shapes, and a spec-decode method recommendation), and hands off to inference-spec-decode-train via a hit-rate-matched corpus. The first phase of the adaptive spec-decode loop. Triggers on "profile my workload", "workload profile for spec-decode", "what draft should I train", "match the draft to my traffic", "adaptive speculative decoding", "fireoptimizer equivalent", "profile traffic for a draft model", or any combination of "profile / characterize / sample" with "workload / traffic / requests" and "spec-decode / draft / acceptance / hit-rate".
About this listing
Category
Content & writing
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI