Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zxpmail/ReqForgenpx agentmods add skills/zxpmail/reqforge/domain-mapperWrote 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/zxpmail/reqforge/domain-mapper)<a href="https://agentmods.dev/skills/zxpmail/reqforge/domain-mapper"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/domain-mapper/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/zxpmail/reqforge/domain-mapper"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/domain-mapper.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 | $0.00000 | $0.01286 |
| Opus 5.5 | $0.00000 | $0.00514 |
| Sonnet 5.5 | $0.00000 | $0.00257 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
domain-mapper 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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: domain-mapper description: Used when the user wants to research a domain, industry, market, technology, codebase, or competitor — turning scattered/unstructured information into a structured Markdown database (domain-map.md). Triggers on phrases like "帮我研究一下", "分析一下这个", "我不太熟悉这个领域", "拆一下这个行业/代码库". version: 1.0.0 updated: 2026-06-08 requires: []
[Task] Transform unstructured/sprawling domain knowledge into a structured Markdown database, independent of any product spec flow.
**Core pipeline**: Scope definition → Domain Snapshot (domain-map.md) → optional Deep-Dive (competitor-analysis.md) → optional Social/Media Analysis (social-analysis.md) → Synthesis (update domain-map.md).
**Depth levels**:
- L1 Snapshot: 30-min pass, only domain-map.md output
- L2 Standard: 1-2h, domain-map.md + competitor-analysis.md
- L3 Deep: Half-day, full 5-step pipeline
The output is a living document: timestamped, source-attributed, and designed to be revisited when the domain evolves.
[Not For] - Writing product requirements -> use /product-spec-builder instead - Fixing bugs -> use /bug-fixer instead - Code review -> use /code-review instead - General web search without structure -> use direct WebSearch or /deep-research instead
[Dependency Check] No required prerequisite files. This skill can always run from a blank project.
- If domain-map.md already exists for the same domain, warn about staleness (check timestamp in file header) and ask whether to regenerate or append.
- If Product-Spec.md exists, read it for context but do not modify it.
[First Principles]
→ references/first-principles.md
[Shared Discipline]
Karpathy 四原则 → ../_shared/karpathy-discipline.md
Source attribution required on every claim → see workflow.md §源标注
[HARD-GATE]
Until domain-map.md is saved and the user confirms the snapshot:
- MUST NOT proceed to Step 3 (Deep-Dive) or Step 4 (Social/Media)
- MUST NOT modify Product-Spec.md, DEV-PLAN.md, or source code
- MUST NOT treat "looks good in chat" as confirmation — user must confirm the saved file
[Output Style] → 每个输出文件头部包含生成时间戳 → 每一条关键信息附来源 URL（不可溯源标注 ⚠️） → 每步完成输出一个文件，不把所有信息挤在同一份报告里
[Output Artifacts] - domain-map.md — 结构化领域数据库（所有深度级别） - competitor-analysis.md — 对比表 + 叙事差异分析（L2/L3） - social-analysis.md — 社媒内容分析 + 核心矛盾提取（L3 only）
[File Structure]
domain-mapper/ ├── SKILL.md # 入口（本文件） ├── references/ │ ├── first-principles.md # 核心理念 + HBM 示例锚点 │ └── workflow.md # 完整 5 步工作流 + 失败模式 └── templates/ └── domain-map-template.md # 通用输出模板 ../_shared/
[Gotchas] 域过宽陷阱: "帮我研究科技行业" → 必须强制收窄（芯片 > 封装 > 设备，你关心哪一层？） 源不可靠: WebSearch 未返回实质内容时，必须在输出的对应条目旁标注 ⚠️（来源不足，需人工补充） 老化地图: domain-map.md 头部有生成时间戳，后续引用时若超过 30 天需提醒用户 竞品敏感数据: 某些行业核心信息不在公开网页，技能必须在输出末尾列出"已知盲区"
[Triggers] The following phrases should route to this skill: - "帮我研究一下 X" / "帮我看看 X 行业" - "分析一下 X 这个赛道/领域/市场" - "我不太熟悉 X，帮我了解一下" - "拆一下 X 的竞争格局" / "X 有哪些玩家" - "研究一下 X 这个技术/产品/代码库" - "画一张 X 的行业地图"
[Workflow]
1. Run [Dependency Check]
2. Read references/first-principles.md
3. Read references/workflow.md — 前置深度选择 → 5 步工作流 → 失败模式
4. 每步完成后暂停，让用户决定继续/转向/停止
What ships with it
5 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.
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.
- 1mo ago First seen · 120 lines · 0 tokens per session scan A 5d7a071c411b
domain-mapper is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,286 tokens. 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
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
oma-hwp
Convert Hangul HWP, HWPX, or HWPML documents to Markdown with kordoc. Use for text, table, and image extraction from these formats.