AD paper-repro-triage
中文论文复现执行工作流。用于用户上传或提供深度学习、机器学习、LLM、CV、NLP、多模态、数据集、benchmark、prompt 工程或 agent 论文的 PDF、arXiv 链接、论文主页、项目页、标题摘要或源码线索，并要求判断可复现性、搜索官方代码、检查本地源码、追踪数据集论文源码、定位数据处理代码、自动 clone 仓库，或在无线上/本地源码但具备复现条件时生成符合常见 PyTorch 开源项目直觉的复现工程。最终写入 Markdown 报告，聊天只返回极简中文摘要。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, git, python) that frontmatter does not declare
- 100Steps. 72 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2110 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 tags): a typed call is more reliable
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 242: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.
External checks
ClawHub: clean
This skill is a disclosed paper-reproduction helper that clones or inspects research code and writes local reports, with clear limits against installing dependencies, downloading datasets, or running training automatically.
LLM: benign (high) · VirusTotal: · 29 May 2026