SKILLEMALL.ai
GitHub ↗ RU Sign in

BC speculative-decoding

Train, debug, and validate a speculative decoding draft model (EAGLE3, DFlash, DSpark, Domino) through the ModelOpt launcher pipeline. Use when the user wants to add a new model to a draft-training pipeline, asks why a pipeline run failed, wants experiment logs reviewed, or wants to check whether a run's acceptance rate meets threshold. Triggers on "EAGLE3", "DFlash", "DSpark", "Domino", "draft model", "acceptance rate", "speculative decoding pipeline". Do NOT use for quantizing a model (use ptq) or serving a checkpoint (use deployment).

NVIDIA/Model-Optimizer Agent Skills author: NVIDIA Apache-2.0 12 files body ≈ 1 180 tokens Open the sourcegithub.com↗ analyzed 4 h ago

Train, debug, and validate a speculative decoding draft model (EAGLE3, DFlash, DSpark, Domino) through the ModelOpt launcher pipeline.

As a process C 56/100 · Has gaps — References files that are not bundled: references/algorithms/<algorithm>.md, examples/speculative_decoding/, scripts/{export_hf_checkpoint,ar_validate,quantize_drafter}.py

AnalyzerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
C
56/100
Has gaps
References files that are not bundled: references/algorithms/<algorithm>.md, examples/speculative_decoding/, scripts/{export_hf_checkpoint,ar_validate,quantize_drafter}.py
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/algorithms/<algorithm>.md
  • warning missing-ref reference to a missing file: examples/speculative_decoding/
  • warning missing-ref reference to a missing file: scripts/{export_hf_checkpoint,ar_validate,quantize_drafter}.py
  • note frontmatter-key unknown frontmatter key "user_invocable"

Process rating: all ten parameters 56/100

Will not run. References files that are not bundled: references/algorithms/<algorithm>.md, examples/speculative_decoding/, scripts/{export_hf_checkpoint,ar_validate,quantize_drafter}.py
  • 0Tools and files. 3 referenced file(s) missing: references/algorithms/<algorithm>.md, examples/speculative_decoding/, scripts/{export_hf_checkpoint,ar_validate,quantize_drafter}.py
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Result and completion. Does not say what the result is
  • 55Failures and branches. 1 branches
  • 100Steps. 7 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1180 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +4Description says when NOT to use the skill
  • +3Description length 543: enough signal without eating the budget
  • +4Structure: 6 headings
  • +3Step-by-step instructions: 7 items
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.