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 Haochenhust/ch-skills --skill company-analyzergit clone --depth 1 https://github.com/Haochenhust/ch-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/haochenhust/ch-skills/company-analyzer)<a href="https://agentmods.dev/skills/haochenhust/ch-skills/company-analyzer"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/company-analyzer/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/haochenhust/ch-skills/company-analyzer"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/company-analyzer.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 | $0.00123 | $0.02410 |
| Opus 5 | $0.00062 | $0.01205 |
| Sonnet 5 | $0.00025 | $0.00482 |
| Haiku 4.5 | $0.00012 | $0.00241 |
Grade A, and why
company-analyzer 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Analyzer
Produces a company analysis organized as Story × Logic × Judgment — a deliberate departure from SWOT-style templated reports. The three layers map to how humans actually understand a business: the narrative arc makes it memorable, the economic logic makes it rigorous, and the forced judgment makes it useful.
The benchmark for style and depth is 《晚点 LatePost》-class industry writing (see references/style-benchmark.md for an annotated example). If the output reads like a translated McKinsey slide with English jargon sprinkled in, it failed — even if all the facts are correct.
When to use
- "分析一下 XX 公司" / "深度研究 XX" / "我想搞懂 XX 这家公司"
- Weighing an investment, job, or partnership with a specific company
- Wants to understand the company as a thesis, not a data dump
When NOT to use
- Quick factual lookup (founding year, headcount) — answer directly
- Real-time prices, intraday earnings reactions — route to a market data tool
- Comparing ≥5 companies at once — depth-first, not breadth-first
- Pure concepts/technologies (Transformer, RAG) — not a company
Writing style (非协商)
This is the hardest part to get right and the easiest to fail. Before writing any section, hold the following rules in memory.
- 母语化中文,不要自造中英夹杂术语。"护城河"说护城河,不要说 "moat";"资本配置"说资本配置,不要说 "capital allocation";"工艺 know-how" 最多保留 "know-how" 这样已被中文业界吸收的词。行业通用英文缩写(CAGR、PE、TIER 1、ROE、FCF)可保留;自造英译概念(process power、moat type、unit economics 当小标题用)不要。
- 小标题必须是带动词的一句完整论断,不是名词短语。
- 好:「过往的路径依赖,让公司错失了新能源车的增长红利」
- 差:「历史沿革」「业务模式」「护城河分析」
- 每段话都要自我解释因果。不写"它有规模优势",写"它在 X 细分市场占 Y% 份额,这让它能摊薄 Z 这条固定成本——但同一份额在 W 市场并不成立"。
- 因果链至少 3 层深。事件 → 为什么发生 → 业务影响 → 投资含义。停在任何中间层都是懒惰。
- 段间用中文连接词过渡,不要靠 markdown 视觉结构硬拼(无 emoji、无表格作为论证主体——表格只用于展示分段数字)。
- 数字要带解释。不要"营收 147 亿元,同比 +4.83%",要"营收 147 亿元,同比只 +4.83%,而扣非反而 -4.39%——意味着这 4.83% 增速里一多半是卖资产,不是主业。"
Workflow
Phase 0 — Scope alignment (可跳过)
Default: use AskUserQuestion to confirm three things before any web search:
What ships with it
17 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.
- company-analyzer-workspace/iteration-1/eval-han-laser/judgment.md 8.6 KB
- company-analyzer-workspace/iteration-1/eval-han-laser/logic.md 12 KB
- company-analyzer-workspace/iteration-1/eval-han-laser/report.md 20 KB
- company-analyzer-workspace/iteration-1/eval-han-laser/story.md 9.7 KB
- company-analyzer-workspace/iteration-1/reference-wolong-latepost.md 21 KB
- company-analyzer-workspace/iteration-2/eval-han-laser/judgment.md 9.9 KB
- company-analyzer-workspace/iteration-2/eval-han-laser/logic.md 21 KB
- company-analyzer-workspace/iteration-2/eval-han-laser/report.md 30 KB
- company-analyzer-workspace/iteration-2/eval-han-laser/story.md 9.5 KB
- references/anti-patterns.md 7.7 KB
- references/business-logic.md 4.6 KB
- references/financial-analysis.md 3.8 KB
- references/industry-structure.md 5.7 KB
- references/moat-types.md 5.7 KB
- references/story-patterns.md 4.2 KB
- references/style-benchmark.md 7.1 KB
- templates/report-template.md 4.3 KB
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 · 110 lines · 123 tokens per session scan A 640ab3f655aa
company-analyzer is a skill published in the GitHub repository Haochenhust/ch-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 2,410 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 2026-08-31.
Other skills, from other repositories
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
dep-auditor
A read-only audit of a project’s third-party packages for known security issues, version health, and license facts. It uses the versions actually selected by lockfiles, which record the exact packages installed, rather than relying only on version ranges.
github-actions-gen
A guide for creating or updating GitHub Actions workflows, which are automated jobs that test, build, release, or deploy code. It first examines the real project before choosing commands, runtimes, caches, and permissions.
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.