Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AkaliKong/PaperClaw --skill paper-relevance-scorergit clone --depth 1 https://github.com/AkaliKong/PaperClawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/akalikong/paperclaw/paper-relevance-scorer)<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-relevance-scorer"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-relevance-scorer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-relevance-scorer"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-relevance-scorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.01343 |
| Opus 5 | $0.00034 | $0.00672 |
| Sonnet 5 | $0.00014 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
paper-relevance-scorer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Relevance Scorer — 三步式相关性打分(Agent 编排模式核心)
概述
本 Skill 是 Agent 编排模式的核心体现。评分流程分为三步:
- 脚本准备上下文 → 生成
skill2_scoring_context.json - Agent LLM 打分 → 逐篇评分,写入
skill2_agent_raw_output.json - 脚本后处理 → 解析、加分、分区,输出
skill2_scored_results.json
⚠️ 关键规则
- 严格 JSON 输出:Agent 打分结果必须为纯 JSON 数组,禁止任何 Markdown 修饰符、寒暄语、解释性文字。
- 逐篇评分:对每篇论文独立评分,输出评分分数、评分理由和语义标签。
- 容错兜底:如果 Agent 输出格式异常,后处理脚本会自动容错提取 JSON 并降级处理。
工作流程
Step 1: 准备打分上下文(脚本)
python $PAPER_AGENT_ROOT/scripts/scorer_utils.py --prepare --run-id {run_id}
脚本将:
- 从
seed_papers.json中选取role: "foundational"的论文(≤3 篇) - 构建 few-shot 正样本(title + abstract + 高分示例)
- 从
profile.yaml读取研究方向描述 - 读取
skill1_search_results.json中的论文列表 - 输出
skill2_scoring_context.json(含 papers 列表、few-shot 示例、完整打分 prompt)
Step 2: Agent 执行打分(你来做)
请读取 pipeline_data/{run_id}/skill2_scoring_context.json 中的打分上下文。
对列表中的每篇论文,根据以下信息进行 0-10 分的相关性评分:
评分维度:
- 与用户研究方向(参见 profile.yaml 中的 research_description)的直接相关度
- 方法论创新性
- 与核心论文(seed_papers.json 中 role 为 foundational 的论文)的技术关联度
- 潜在实验价值(对比基线、技术复用)
评分标准校准(Few-shot 正样本):
以下核心论文应被视为 9-10 分 的标杆。具体示例见 skill2_scoring_context.json 中的 fewshot_examples 字段。
输出格式要求 — 极其重要:
将评分结果写入 pipeline_data/{run_id}/skill2_agent_raw_output.json。
直接输出 JSON 数组。每个元素为一篇论文的打分结果:
[
{
"arxiv_id": "2603.01234",
"relevance_score": 8,
"scoring_rationale": "该论文提出了与用户研究方向高度相关的新方法...",
"tags": ["relevant_method", "novel_approach"]
},
{
"arxiv_id": "2603.05678",
"relevance_score": 3,
"scoring_rationale": "该论文关注传统协同过滤,与生成式推荐方向关联较弱...",
"tags": ["collaborative_filtering"]
}
]
禁止包含任何 Markdown 代码块修饰符(如 ```json)
禁止包含任何解释性文字、过渡句、寒暄语
禁止在 JSON 之前或之后附加任何非 JSON 内容
Step 3: 后处理(脚本)
python $PAPER_AGENT_ROOT/scripts/scorer_utils.py --postprocess --run-id {run_id}
脚本将:
- 使用容错 JSON 提取器解析
skill2_agent_raw_output.json - 对白名单作者论文标注
is_whitelist_author: true并 +1 分 - 对顶会论文标注
is_top_venue: true并 +1 分 - 按评分排序,分为三个区间(高分区 ≥7 / 边缘区 4-6 / 低分区 ≤3)
- 输出
skill2_scored_results.json
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 137 lines · 68 tokens per session scan A 5d8a4800b803
paper-relevance-scorer is a skill published in the GitHub repository AkaliKong/PaperClaw (22 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 1,343 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…