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 jeffy-Peng/jeffy-skills --skill 3d-deep-researchgit clone --depth 1 https://github.com/jeffy-Peng/jeffy-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/jeffy-peng/jeffy-skills/3d-deep-research)<a href="https://agentmods.dev/skills/jeffy-peng/jeffy-skills/3d-deep-research"><img src="https://agentmods.dev/badge/skills/jeffy-peng/jeffy-skills/3d-deep-research/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/jeffy-peng/jeffy-skills/3d-deep-research"><img src="https://agentmods.dev/badge/skills/jeffy-peng/jeffy-skills/3d-deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.02923 |
| Opus 5 | $0.00060 | $0.01461 |
| Sonnet 5 | $0.00024 | $0.00585 |
| Haiku 4.5 | $0.00012 | $0.00292 |
Grade A, and why
3d-deep-research 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 today.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Deep Research
先建立研究底图，确认研究对象的边界、运转方式和当前状态；再用 X/Y/Z 逐层解释：X 识别显性与非显性的关键变化及其后续影响，Y 沿具体变化切开并比较成因，Z 拆开尚不清楚的作用连接。分析结果持续返回发展路径和研究底图，用证据校正解释并检查重要遗漏。
本 Skill 为主研究流程时，默认交付完整的 Markdown、HTML 和 PDF 三份报告；用户明确缩小交付范围时按其要求减少。用户点名其他研究 Skill 或选择其他工作模式时，以其作为主流程；仅在需要本方法时辅助使用，不叠加独立默认产物。不要仅因通用的 deep research 字样同时运行两套流程，也不要把普通问答扩写成长报告。
必读资源
执行完整研究时：
- 读取 references/evidence-protocol.md，建立来源与 Claim 账本并执行事实审计。
- 读取 references/xyz-method.md，建立研究底图并执行 X/Y/Z、路径校正和覆盖复核。
- 根据研究对象读取 references/object-adapters.md 的对应部分。
- 读取 references/visual-guidelines.md，用于分析阶段的视觉规划、HTML/PDF 渲染和图表检查。
- 写作时复制 assets/report-template.md，保留元数据与证据附录；正文可按问题重组。
报告措辞
- 先直接回答研究问题，再解释事实、原因、限制和行动含义。
- 使用自然、具体的语言。尽量说明“谁做了什么、为什么、造成什么结果”，避免名词堆叠和抽象套话。
- 每段只推进一个判断。删除不提供事实、解释或决策价值的句子。
- 明确区分事实、解释和预测。证据只能支持“可能”时，不写成“证明”或“必然”。
- 不把 Claim 类型、证据门槛、X/Y/Z 等内部方法术语写进正文；它们只用于组织研究和附录说明。
- 数字首次出现时说明时间、单位、统计口径和比较对象。
- 不使用宣传式形容词、无依据的最高级，以及“值得注意的是”“不容忽视”等空洞过渡语。
- 只在不确定性会影响结论时说明限制，并紧邻相关判断书写。
执行流程
0. 明确研究设定
记录研究对象、对象类型、用户要做的决策、特别关注点、时间基准、范围边界和交付要求。无法从上下文解决且会显著改变目标或正确性的问题才追问；其余情况直接开始。根据对象适配器建立研究底图，先确认主体边界、价值或作用结构、关键参与者及当前状态，再选择解释主线。
复杂或持续时间较长的任务可以把上述设定记录为工作笔记；不要为简单任务强制创建独立过程文件。
研究范围由用户问题和证据决定，不追求来源数、Claim 数、字数或图表数量。每个进入 A2 的关键判断和数字都必须通过适用的证据门槛并完成审计；资料不足时缩小可确认结论的范围，保留未解决问题，不静默改变用户的研究目标。
涉及“最新、现在、最近”时联网核实，并记录发布日期和访问日期。输出到用户指定位置；未指定时使用当前项目的 output/。
1. 规划检索
先列出：
- 建立研究底图必须确认的事实和口径；
- 关键变化及其前后状态；
- 需要比较的成因和需要打开的作用连接；
- 需要主动寻找的反向证据、替代解释和失败案例。
检索过程中根据证据调整问题。每个影响结论的问题最终都要有来源支持，或在 A2/A3 明确标为未解决。复杂任务可以维护检索笔记，但不强制生成独立表格。来源选择遵循 evidence protocol，优先使用适合该对象的原始材料、官方记录和独立来源。
2. 维护证据账本
在 report.md 附录 A1 和 A2 分别维护来源与 Claim 账本。来源使用稳定 ID（S01、S02），关键判断使用 Claim ID（C01、C02）。把“来源出处”和“证据作用”分开记录。
研究过程中持续更新账本。每条关键判断的支持证据、替代解释、反向材料、独立性、置信度、资料缺口和修订条件，按 references/evidence-protocol.md 记录和判断；因果和机制判断分别记录过程证据与归因边界。过程已发生不等于它足以解释总体结果。
What ships with it
15 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.
- agents/openai.yaml 275 B
- assets/report-template.md 3.3 KB
- assets/report.css 4.5 KB
- references/evidence-protocol.md 6.4 KB
- references/object-adapters.md 4.0 KB
- references/visual-guidelines.md 4.1 KB
- references/xyz-method.md 11 KB
- scripts/linkify_sources.py 3.0 KB runs code
- scripts/render_report.py 12 KB runs code
- scripts/report_artifacts.py 3.7 KB runs code
- scripts/validate_report.py 25 KB runs code
- tests/test_evidence_contract.py 8.6 KB runs code
- tests/test_linkify_sources.py 2.1 KB runs code
- tests/test_render_report.py 3.0 KB runs code
- tests/test_validate_report.py 13 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.
- today Changed · +9 lines 5c9a577b3f37
- 5d ago Changed · +2 lines 21cf0304aeb2
- 6d ago Changed · +6 lines c2faa769d31b
- 12d ago First seen · 114 lines · 121 tokens per session scan A bbaa4f5ca823
3d-deep-research is a skill published in the GitHub repository jeffy-Peng/jeffy-skills (20 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 2,923 once invoked, about $0.0006 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
research-ops
Use when someone hands you an open question whose answer must survive scrutiny — a tech choice, a regulation, a what-is-actually-true-about-X — with every non-obvious claim dated and sourced, source disagreements surfaced rather than averaged away, and a cited memo as the deliverable. Also for refreshing a stale…
idea-bib-review
A writing workflow for drafting a literature review from a research idea and BibTeX files, which are structured records of academic sources. It preserves citation keys and checks whether claims are supported by the supplied evidence.
link-evidence
Prevents fabricated URLs. Only use links that appear in the sources pool or are provided by the user.
mk:research
Use when a decision needs deep multi-source technical research with cited evidence — technology evaluation, ecosystem comparison, standards/spec fact-finding, "how do others solve X". Triggers on "research X", "deep dive on X", "evaluate X vs Y", "find best practices for X". NOT for library/API doc lookup (see…
net-deep-research
Perform deep multi-source internet research for complex web truth-finding tasks. Prefer explicit /net-deep-research invocation. Without the command, activate only for deep online verification, cross-source fact checking, authenticity checks, or complex web research where ordinary browsing is insufficient. Do not use…
benchmark-audit
Systematic quality assessment using BetterBench 46-criterion framework — 5 benchmarks, 30 papers, 40 web searches.