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 pieable/dragon-ball-agent --skill company-research-briefgit clone --depth 1 https://github.com/pieable/dragon-ball-agentWrote 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/pieable/dragon-ball-agent/company-research-brief)<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/company-research-brief"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/company-research-brief/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/pieable/dragon-ball-agent/company-research-brief"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/company-research-brief.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 | $0.00068 | $0.01501 |
| Opus 5 | $0.00034 | $0.00750 |
| Sonnet 5 | $0.00014 | $0.00300 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
company-research-brief 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 11d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公司研究与投前初筛
帮助投资人从已有材料和可核验的公开信息中看清一家公司在做什么、进展到哪一步、与谁竞争、哪些事实支持继续接触,以及哪些未知仍会改变判断。
从要作出的决定组织研究
先确认这份材料要帮助谁作出什么决定、已有资料范围、时间截点和交付形态。常见结果包括:
- 公司资料补全: 中性整理公司、产品线、客户、业务进展和信息边界。
- 快速初筛: 判断是否值得继续接触或进入下一层尽调。
- 投前简报: 形成能够直接阅读的事实、比较、风险和当前判断。
- 专题研究: 只回答市场、竞品、技术、客户、团队或价格等具体问题。
- 市场测算: 在口径和假设明确时估算相关市场或公司现实可进入的机会。
用户没有要求投资判断时,保持中性,不擅自给“值得投”或“不值得投”的结论。纯文字修订使用已有文档与写作能力;只有修订需要重新核验证据或投资逻辑时才使用本 Skill。
先建立公司和产品线地图
用已有材料确认主体、产品或服务、目标客户、产业链位置、商业模式和当前阶段。多业务公司按产品线拆开,识别主要收入或当前融资主线;同业关系按产品、应用和客户场景判断,不把公司永久贴成一种竞品标签。
研究至少能够回答这些会改变判断的问题:
- 公司卖什么、谁购买、谁使用,客户为什么采用或替换。
- 产品处在概念、样品、测试、导入、订单、交付、收入、回款、复购还是规模化阶段。
- 需求怎样从下游场景和客户预算传导到这条产品线。
- 直接竞品、替代路线、成熟标杆和重要上下游参照分别是谁,为什么可比。
- 团队、渠道、产能、交付、合规和现金流是否匹配当前主张。
- 哪几项事实支撑继续看,哪些风险或未知最可能改变结论。
这些是研究问题,不是必须原样出现在报告里的固定目录。材料已经足以回答当前决定,新增搜索很少改变公司位置、比较关系、风险或下一步时停止扩大。
证据决定结论强度
读取 references/source-policy.md 处理来源优先级、证据标签、时效和引用边界。把材料分为已核验事实、公司自述、第三方线索、推断和尚需核验;推断写清依据,无法访问和没有查到保留为覆盖缺口。
BP、官网、新闻稿和创始人表述可以说明公司希望外界相信什么,也可以提供产品名、团队、里程碑和检索词。客户、订单、收入、回款、量产、技术领先、市场份额和商业化质量需要更强证据。不能把“未找到反证”写成“已经证实”。
一般来源发现和覆盖方法由 search-source-registry、deep-research 及研究角色承担;本 Skill 只规定公司研究需要回答的问题、证据尺度和成品。用户限定资料范围时在该范围内工作,扩大外部搜索或读取新材料前遵守当前授权。
形成市场和比较判断
需要市场规模、TAM/SAM/SOM 或需求传导时读取 references/market-sizing-guide.md。宽泛行业规模只能说明背景;公司机会必须继续落到具体产品、客户预算、采购节奏、价格、认证、渠道、产能和交付能力。估算值写出公式、口径、假设和敏感项,不冒充订单或收入。
需要选择行业维度或比较对象时读取 references/industry-analysis-framework.md。先说明为什么可比,再比较产品、客户场景、商业化阶段、价格、性能、认证、交付和经营证据。只有具名对象、可比维度和可靠来源同时成立时才写相对领先。
给出当前处理意见
用户明确要求初筛、是否继续看或投前判断时,读取 references/investment-judgment-framework.md。结论说明现有证据支持什么、风险影响哪项前提、什么新事实最可能改变判断。默认使用“继续重点跟进、谨慎继续、信息不足、暂缓”等当前处理意见,不用无来源的精确评分制造确定感。
用户只要信息整理时,以中性小结结束。缺少资料不是自动否定,公司自述也不是自动肯定。
把研究底稿变成可直接阅读的成品
正文面向实际读者,直接说明公司、产品线、进展、市场含义、比较关系、风险和当前判断。检索过程、工具协作、补证清单、证据标签和内部推演留在研究记录或真实性验证材料中,不把后台过程写成报告正文。
快速初筛优先短而完整。正式简报、长报告或需要控制商业语言时读取 references/report-structure.md。需要可追溯成稿时使用 assets/source-verification-template.md 保存来源映射;材料复杂时可用 assets/report-input-template.md 整理成文输入。需要 Word 时再使用文档工具生成并核对正文、数字、日期、公司名和来源边界,不把 Word 作为默认输出。
What ships with it
10 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 406 B
- assets/report-input-template.md 3.4 KB
- assets/source-verification-template.md 3.9 KB
- references/eval-cases.md 2.8 KB
- references/industry-analysis-framework.md 5.2 KB
- references/investment-judgment-framework.md 4.1 KB
- references/market-sizing-guide.md 3.9 KB
- references/report-structure.md 7.4 KB
- references/source-policy.md 3.5 KB
- RULE_RATIONALE.md 8.7 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.
- 11d ago First seen · 72 lines · 68 tokens per session scan A 714043a88362
company-research-brief is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 10d ago), licensed MIT. It adds 68 tokens to every session and 1,501 once invoked, about $0.0003 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.