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 tlzmw001/naiyue-skills --skill prior-art-scoutgit clone --depth 1 https://github.com/tlzmw001/naiyue-skillsWrote 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/tlzmw001/naiyue-skills/prior-art-scout)<a href="https://agentmods.dev/skills/tlzmw001/naiyue-skills/prior-art-scout"><img src="https://agentmods.dev/badge/skills/tlzmw001/naiyue-skills/prior-art-scout/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/tlzmw001/naiyue-skills/prior-art-scout"><img src="https://agentmods.dev/badge/skills/tlzmw001/naiyue-skills/prior-art-scout.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 | $0.00238 | $0.04153 |
| Opus 5 | $0.00119 | $0.02076 |
| Sonnet 5 | $0.00048 | $0.00831 |
| Haiku 4.5 | $0.00024 | $0.00415 |
Grade A, and why
prior-art-scout 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prior-Art Scout:开工前技术方案调研
回答:别人试图解决什么问题,用什么工具、流程和技术解决;我能否直接使用或借鉴;前人踩过什么坑;多个方案共同还有什么没有解决;基于证据应如何决策?
这是技术方案调研,不是产品热度排行。star、用户量和活跃度只能作为参考信号。
必读契约
执行 Phase 1、3、4、5 时读取 references/research-design.md。其中定义:
- 先搜完整问题,再按流程环节拆分查询。
- 用户提供明确方向时,先搜该方向并提高其候选优先级;覆盖其他候选时必须说明原因。
- 候选发现覆盖不同供应形态;GitHub 同时执行全文和 topic 搜索。
- 每个来源最多 5 个候选进入深度分析。
- 前三类选择依据必须先通过可采用性门槛;路线差异和失败证据候选单独标识。
- 报告先回答决策问题,候选全集放附录。
铁律
- 尽力证明“有人做过”。 发现高度重叠的成熟方案是成功,不得为了支持开工而弱化重叠。
- 存疑候选不得无记录丢弃。 全部进入卡片;超出深验预算时标为 relevant_not_deep_verified,明确“相关但未深验”,不得伪装成已验证结论。
- 每源深验不超过 5 个。 总上限 = 启用来源数 × 5;不足不补,禁止突破上限。Phase 4 前必须运行 scripts/validate_workspace.py。
- 淘汰必留痕。 different_domain 写入 rejected.json,必须说明“它解决 X,我的问题是 Y”。
- 每个判断挂证据。 成熟性、核心机制、失败路线、可借鉴点和建议必须引用 raw/、cards/ 或 clones/ 中的具体路径。
- 判路线不可行必须有死因证据。 需要弃坑声明、Issue 失败讨论或明确技术瓶颈;项目停更不等于路线不可行。
- 成熟/借鉴结论必须深验。 mature_reference 和 partial_borrow 只能授予 selection.json 中已入选且 deep_verified=true 的候选;GitHub 候选必须 clone 并读核心代码,不能只转述 README。
- 两个确认点必须真正停下。 用户明确确认前禁止继续下一阶段。
- 区分“已踩坑”与“尚未解决”。 已踩坑必须有具体发生记录;共性未解问题必须至少由两个深验候选的证据共同支持。只能写“本轮深验方案中尚未解决”,不得从有限样本推导“行业无法解决”。
- 用户方向优先但不免证。 方向查询先执行;方向候选相关性或证据不足时可以降级,但必须留下
priority_override_reason,不得因用户提到就直接判成熟。 - 广搜不等于多读。 初搜只抓轻量元数据;GitHub 不在发现阶段批量读取 README/commit/Issue。只有每源最多 5 个入选候选进入 clone 或一手材料深验。
- 区分客户端与后端。 开源 SDK 连接闭源服务时标为
open_client_closed_backend,不得写成开源抓取实现。 - 前三类先证明能用。 用户方向、完整方案、流程补位候选必须在入选前证明当前有可用产物、使用文档详细且接入复杂度不是 extreme/unknown;否则不能靠这三类理由占用深验名额。
- Web 优先使用宿主原生搜索。 读取 adapters/web.md;
source=web,实际后端写入 provider,MCP 只作为 transport。宿主无搜索时不得假装执行,也不得自动安装 MCP、索要新 key 或静默切换 provider。 - X 默认走 TikHub 但仍是弱证据。 读取 adapters/x.md;TikHub 负责可复现抓取,不把帖子自述升级为事实。线上 OpenAPI、真实响应和一手落地链接优先于 SDK 宣称。
工作区
research/<项目名>/
├── queries.json # 锚点、任务环节、分来源查询;确认点 1
├── raw/<源>/ # 适配器原始结果
├── candidates.json # 全量归一化候选
├── cards/ # 每候选一张卡
├── selection.json # 每源最多 5 个深验候选及选择理由
├── rejected.json # 问题域不同的候选
├── clones/ # GitHub 深验 clone
└── report.md # 聚焦决策的最终报告;确认点 2
What ships with it
28 files 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.
- adapters/github.md 4.0 KB
- adapters/web.md 6.3 KB
- adapters/x.md 6.3 KB
- references/research-design.md 16 KB
- schemas/candidate.json 4.3 KB
- schemas/query-plan.json 7.3 KB
- schemas/scheme-card.json 7.2 KB
- schemas/selection.json 5.2 KB
- schemas/web-capture.json 2.9 KB
- scripts/gh_fetch.sh 2.8 KB runs code
- scripts/prior_art_validation/__init__.py 276 B runs code
- scripts/prior_art_validation/cards.py 3.2 KB runs code
- scripts/prior_art_validation/common.py 1.3 KB runs code
- scripts/prior_art_validation/queries.py 13 KB runs code
- scripts/prior_art_validation/selection.py 14 KB runs code
- scripts/tikhub_x_fetch.py 12 KB runs code
- scripts/tikhub_x_normalize.py 14 KB runs code
- scripts/tikhub_x_run.py 6.1 KB runs code
- scripts/validate_workspace.py 2.4 KB runs code
- templates/report.md 6.6 KB
- tests/test_gh_fetch.py 3.1 KB runs code
- tests/test_query_contract.py 4.3 KB runs code
- tests/test_selection_adoption.py 2.6 KB runs code
- tests/test_tikhub_x_fetch.py 8.7 KB runs code
- tests/test_tikhub_x_normalize.py 6.8 KB runs code
- tests/test_tikhub_x_run.py 6.1 KB runs code
- tests/test_validate_workspace.py 18 KB runs code
- tests/test_web_adapter_contract.py 2.7 KB runs code
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 · 190 lines · 238 tokens per session scan A 33a5b5314642
prior-art-scout is a skill published in the GitHub repository tlzmw001/naiyue-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 238 tokens to every session and 4,153 once invoked, about $0.0012 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 2026-08-31.
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…