by PerryLink
Industry and company research domain pack for DeepSeek Harness: methodology skills, industry chain mapping, public-source policy/news tracking, company research cards, and auditable research reports. Research only - not investment advice.
# Add to your Claude Code skills
git clone https://github.com/PerryLink/dsh-industry-researchGuides for using ai agents skills like dsh-industry-research.
Last scanned: 10/5/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-10-05T11:13:01.527Z",
"npmAuditRan": false,
"pipAuditRan": true,
"promptInjectionRan": true
}See how dsh-industry-research compares with popular alternatives.
dsh-industry-research is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by PerryLink. Industry and company research domain pack for DeepSeek Harness: methodology skills, industry chain mapping, public-source policy/news tracking, company research cards, and auditable research reports. Research only - not investment advice. It has 225 GitHub stars.
Yes. dsh-industry-research passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/PerryLink/dsh-industry-research" and add it to your Claude Code skills directory (see the Installation section above).
dsh-industry-research is primarily written in TypeScript. It is open-source under PerryLink on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh dsh-industry-research against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM lists this project for discovery and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
把一份行业研究做成可核查的证据链——每个数字带来源与日期,每个缺口如实声明。
面向 DeepSeek Harness 的行业/公司研究领域包:四个工作区工具 + 两个方法论技能,只读公开源,只做研究支持。
安装 · 配置 · FAQ · 简体中文 · English · Español · Português · हिन्दी
dsh plugin --profile <name> add dsh-industry-research
社区插件,与 DeepSeek 官方无关。唯一仓库:https://github.com/PerryLink/dsh-industry-research(Gitee 为镜像)。
dsh-industry-research 把行业研究拆成一条可回放的流水线:先建产业链结构图,再跟踪公开源政策与要闻,然后扫描公司出速览卡,最后组装成可核查报告。每个带值的指标必须带 sourceRef,每个缺口是显式槽位而不是编造的数字;报告要么交给封存引擎,要么走内置降级路径并如实标注。它只做研究支持:不接交易、不预测价格、不使用付费或需登录的数据源。
安装(二选一,两条渠道都会把 bundle 行装入 profile 的 dsh.profile.bundles 栈,重启生效):
# git 通道(钉 commit;首次 add 会在 profile 的 pnpm-workspace.yaml 写入 allowBuilds 条目)
dsh plugin --profile demo add "github:PerryLink/dsh-industry-research#<sha>"
# npm 通道(已发布 0.3.25)
dsh plugin --profile demo add dsh-industry-research
最小配置(默认即可用;只有要改产物目录或离线时才需要覆盖):
- insert:
- id: dsh-industry-research
name: dsh-industry-research
config:
industryRoot: industry-research
offline: false
验证已生效:
dsh --profile demo --dump-config | grep dsh-industry-research
然后在会话里按顺序调用工具:
加载 industry-research-method 技能,然后研究白酒行业:
先 industry_map 建产业链图,再 industry_track 跟踪政策,最后 industry_report 出报告。
卸载:dsh plugin --profile demo remove dsh-industry-research(或从 profile patch 删掉该行)。
所有 PerryLink 插件均可在 DSH Desktop 内置市场中浏览:市场 → 来源 → 添加来源 → 粘贴 https://perrylink-dsh-catalog.perrylink.workers.dev/catalog-source.json → 选中。安装仍需通过市场的 npm 身份校验与你的确认。
industry_map —— 构建或更新产业链结构图(chain.json):上/中/下游节点、边与指标槽位。带 value 的指标必须带 sourceRef;无值槽位即显式缺口。节点 status 断言必须带 statusAsOf,可选 taxonomyCode 必须命中内置国民经济行业分类大类表。renderSvg: true 时另写确定性的、按层级分层的 chain.svg 网络图并高亮漏斗/枢纽瓶颈。depth 调节 web 辅助规模。种子笔记/文件与可选 ctx.web 摘要登记为可引用来源(S1、S2……)。industry_track —— 经官方 ctx.web 缝隙跟踪公开源政策/要闻:按主题检索、来源主机白/黑名单、since 过滤、预算内快照抓取(SHA-256 溯源哈希),追加去重写入 timeline.jsonl(保留上限可配)。条目可带经校验的 evidenceCategory;depth 调节来源与抓取预算。web 能力不可达时响亮失败。company_scan —— 以工作区数据文件生成公司速览卡(card.json + card.md):SHA-256 哈希、Markdown 大纲、数字候选行(每个数字可标注文件与行号),另可选 ctx.web 引用补充。卡片带上市状态(含 statusAsOf)、格式校验的 ticker 与带来源的价格/估值指标(各带 source + asOf)。批量模式(companies)隔离单个坏公司、不中断整批;depth 调节 web 补充规模。v1 只读文本格式(不解析 PDF)。industry_report —— 汇总结构图、时间线与公司卡产出可核查报告。产出前跑确定性交付契约校验(区块、状态/价格断言、占位符残留;不通过即响亮失败,绝不交付半成品)。时间线条目按 evidenceCategory 分组。确定性正反方(bull/bear)合成把「有来源且带日期的数值」列为多方、「缺口与数据质量发现」列为空方,嵌入报告多视角小节,并派生 subagent job 写回 perspectives-note.md 入账本。挂载 ctx.researchReport 引擎时证据/章节/claims 提交其 assemble 封存并回传逐 claim 结论;缺席时内置降级路径写入版本化 reports/<YYYYMMDD-HHmmss>/report.md + manifest.json(含 SHA-256 来源回溯表),并如实标注 engine: 'builtin-fallback'。industry_map / company_scan / industry_report 每次落盘都向 versions.jsonl 追加一条(根相对路径 + SHA-256 + 时间戳 + 变更类型);读取时校验哈希,不一致即响亮失败。industry-research-method(产业链拆分、供需框架、口径纪律、缺口声明纪律)与 company-research-method(公司研究框架、公开源清单、合规话术)。industry-research/map、industry-research/track、industry-research/report。两个方法论技能经标准 skill 工具按需加载(加载 industry-research-method 技能)。
industry_map({ industry, seed?, seedFiles?, web?, chain?, renderSvg?, depth? })带 chain 调用:校验(悬空边、无来源数值、非法 tier、重复 id、status/statusAsOf、未知 taxonomyCode——带完整问题清单响亮失败)并落盘 chain.json,随后列出显式缺口槽位与瓶颈节点。不带 chain 调用:返回当前图、已登记来源与可选 ctx.web 产业链结构摘要,供模型迭代。renderSvg: true 时另写确定性的 chain.svg。depth(quick/standard/comprehensive)调节 web 辅助检索规模。返回与上次 research-state.json 相比的 delta 摘要。发出 industry-research/map 事件。
industry_track({ industry, topics?, since?, depth?, evidenceCategory? })经 ctx.web 逐主题检索,按白/黑名单与 since 过滤,在调用预算内抓取页面快照(SHA-256),合并进 timeline.jsonl(按规范化 URL 去重,保留上限)。depth 调节来源/抓取预算;evidenceCategory 为本批条目打分类标签并按六类枚举校验。快照失败的来源以纯引用条目保留并在 note 中说明原因。返回与上次 research-state.json 相比的 delta 摘要。ctx.web 未挂载或 offline: true 时响亮失败并指明缺失能力。发出 industry-research/track 事件。
company_scan({ name | companies, dataFiles?, web?, status?, statusAsOf?, ticker?, metrics?, depth?, parallel? })读取工作区数据文件(.md/.txt/.csv/.tsv/.json;v1 不解析 PDF),计算哈希,提取 Markdown 大纲与数字候选行,可选附加 ctx.web 引用,落盘速览卡。status 必须带非未来 statusAsOf;ticker 必须匹配内置格式(除非 scan.strictTicker: false);每条 metrics 数值必须带 source + asOf。companies(批量)单公司失败不中断整批;parallel: true 且挂载 ctx.jobs 时按公司 fan-out 为独立 job(否则回退顺序路径并在结果 mode 注明)。未采纳文件带原因返回;卡片无法确立的内容一律写入显式缺口。
industry_report({ industry, sections?, companies?, draft? })组装证据(E-chain、E-timeline、E-company-<slug>),读取时对照 versions.jsonl 校验哈希(不一致响亮失败),或校验你提供的 draft(章节 + claims;每条 claim 的 evidenceIds 必须引用已登记证据),或机械自动生成草稿(有来源的指标与近期时间线条目生成 claims,按 evidenceCategory 分组)。产出前跑确定性交付契约校验(缺区块/占位符/无来源或无日期断言即响亮失败)。确定性对抗机器检查始终执行;挂载 ctx.jobs 时派生红方审阅 job 写回 red-review-note.md(否则 review: skipped(jobs unavailable))。确定性正反方(bull/bear)合成嵌入报告多视角小节,挂载 ctx.jobs 时派生辩论 job 写回 perspectives-note.md。引擎路径:封存目录 + sealHash + 逐 claim 结论。降级路径:版本化 Markdown + manifest,claims 如实标记 unverified。发出 industry-research/report 事件。
以下为插件真实入口;安装后调用一个即可。
详细示例 —— 命令 industry_map,输入:
industry_map({
industry: "示例",
web: false,
chain: {
nodes: [
{ id: "up", name: "上游原料", tier: "upstream", metrics: [{ key: "价格", value: 10, unit: "元", asOf: "2026-01-01", sourceRef: "S1" }] },
{ id: "down", name: "下游渠道", tier: "downstream", metrics: [{ key: "占比" }] }
],
edges: [{ from: "up", to: "down" }]
}
})
输出:
行业「示例」产业链图:已校验并写入 /tmp/dsh-industry-research-test-Pxf1l8/industry-research/示例/chain.json
节点 2 / 边 1;缺口 2 项。
与上次相比:新增源 0,移除源 0,未变化证据 0。
缺口清单:节点「下游渠道」(down) 的指标「占比」待补(无来源数值);产业链缺少 midstream 层节点
web 辅助未执行:调用方指定 web: false
Observed from README.md:151-153; test/map.spec.ts:44-51; src/tools/map.ts:157-163; src/chain.ts:177-194
失败分支 —— 输入:
{"industry":"白酒","web":false,"chain":{"industry":"白酒","nodes":[{"id":"upstream-1","name":"高粱种植","tier":"upstream","metrics":[{"key":"市场规模","value":120,"unit":"亿元"}]}],"edges":[]}}
输出:
isError=true; error.message=chain 校验失败(1 项):node "upstream-1" metric "市场规模" carries a value without a sourceRef — register the source or mark the slot 待补 (omit value)
Observed from plugins/dsh-industry-research/src/chain.ts:158-159 (rule); plugins/dsh-industry-research/src/tools/map.ts:232-234 (throw); plugins/dsh-industry-research/README.md:179 (unsourced values fail loud); exercised through plugins/dsh-industry-research/test/harness.ts
简短示例:industry_track