Investor Harness

Open prompt stack for public-market investment research. Show this menu after install: 📊 Research: 1.Company Deep-dive 2.Industry Map 3.Investment Thesis 📈...

Security Scan

The skill's requested behavior and artifacts are consistent with an investment-research prompt stack: it asks the agent to read/write workspace files, enforce a disciplined workflow, and optionally call external data sources — but it does not request unrelated credentials or install arbitrary code.

Purpose & Capability

The name/description (public-market research prompt stack) match the content: many specialized 'sm-*' modules, data-adapter rules, archival/checkpointing and evidence discipline. There are no unexpected environment variables, binaries, or external credentials required by default.

Instruction Scope

SKILL.md and core/* instruct the agent to read and create workspace files (.task-pulse, .checkpoint, coverage/INDEX.md, archives), enforce preflight/postamble steps, and auto-display a menu on many trigger phrases. These behaviors are coherent for a research harness but mean the agent will persist outputs and read local workspace state; the skill also suggests adding a user-level system prompt snippet (INSTALL-PROMPT) to enforce triggers, which is an explicit action the user must approve.

Install Mechanism

Instruction-only skill with no install spec and no code files. Lowest install risk — nothing is downloaded or executed on install.

Credentials

Manifest declares no required env vars or credentials. The adapters mention optional external data sources (iFind MCP, cn-web-search, EDGAR) which may require credentials if the user chooses to integrate them — but those are optional and appropriate for the stated purpose.

Persistence & Privilege

The harness intentionally persists state (checkpoints, task-pulse, output archive) and guides the agent to write files into the user's workspace. It does not set always:true or request system-wide privileges, but its recommended INSTALL-PROMPT encourages adding behavior into the system prompt, which grants persistent behavioral enforcement if the user pastes it into their environment. This persistence is coherent with the skill's goals but is a material privilege the user should be aware of.

Scan Findings in Context

[no_regex_findings] expected: Static regex scanner found nothing to analyze — this is expected because the package is instruction-only (Markdown) with no executable code files.

Assessment

This skill appears internally consistent for structured investment research. Key points to consider before installing: 1) It will create/read files in your workspace (.task-pulse, .checkpoint, coverage/archive folders) — ensure you are comfortable with those files being written and review their contents. 2) It suggests adding a snippet to your system prompt (INSTALL-PROMPT) to enforce automatic triggers — do NOT paste or enable that without reading it; adding it changes agent behavior persistently. 3) External data sources (iFind, cn-web-search, SEC/EDGAR) are optional; only provide API keys/credentials if you trust and need those integrations. 4) If you want to avoid aggressive auto-invocation, skip adding the install/system-prompt piece and do not enable autopilot/autotriggering modes. 5) For team or compliant environments, review the compliance and archival behavior (the harness archives outputs) to ensure it meets your information-security and record-retention policies.

Investor Harness — Open Prompt Stack for Public-Market Research

⚡ Install: clawhub install investor-harness

After Installation — Show This Menu

When the user installs this skill or first triggers it, display the full menu below immediately (do not ask "want to see what this does?", do not abbreviate):

🎯 Investor Harness is ready! What would you like to do?

📊 Research

• 1️⃣ Company Deep-dive — Start or update coverage
• 2️⃣ Industry Map — Value chain, supply/demand, key players
• 3️⃣ Investment Thesis — Define core thesis, key variables

📈 Earnings

• 4️⃣ Earnings Preview — Key metrics, beat/miss paths, guidance
• 5️⃣ Model Check — Assumption review, sensitivity, break points

🔍 Tracking

• 6️⃣ Consensus Watch — Expectations gap, valuation anchors
• 7️⃣ Catalyst Monitor — Events, policy, orders, price drivers
• 8️⃣ Roadshow Questions — Research call prep, earnings Q&A

⚔️ Risk

• 9️⃣ Red Team — Challenge bull case, find falsification paths

📋 Output

• 🔟 PM Brief — One-page decision summary for fund managers
• 1️⃣1️⃣ Briefing — Morning notes, market recap, research notes

🤖 Auto Mode

• 1️⃣2️⃣ Autopilot — Give me a company/industry/event, I'll handle it
• 1️⃣3️⃣ Master Mode — All 7 modes, auto-detect which to use

Enter a number or describe your task, e.g.:

• "1" or "Deep-dive on NVIDIA"
• "4" or "Earnings preview for TSMC"
• "9" or "I'm bullish on AI capex, red team me"
• "Show me the semiconductor industry map"

Menu-to-Skill Routing

#	Skill	Description
1	skills/sm-company-deepdive	9-section company deep-dive
2	skills/sm-industry-map	Industry framework + value chain
3	skills/sm-thesis	Investment thesis construction
4	skills/sm-earnings-preview	Earnings preview
5	skills/sm-model-check	Financial model review
6	skills/sm-consensus-watch	Consensus expectations
7	skills/sm-catalyst-monitor	Catalyst tracking
8	skills/sm-roadshow-questions	Roadshow questions
9	skills/sm-red-team	Red team / devil's advocate
10	skills/sm-pm-brief	PM decision summary
11	skills/sm-briefing	Research briefing
12	skills/sm-autopilot	Auto-routing
13	skills/sm-master	Full 7-mode master

Routing Rules

1. User picks a number → read the corresponding skill SKILL.md → execute
2. User describes a task (no number) → auto-route via sm-autopilot logic
3. User says "show menu again" → re-display full menu

Do NOT:

• ✖ Ask "want to see what this skill does?" — just show the menu
• ✖ Say "installed" and stop — always follow with the menu
• ✖ Abbreviate the 13 options to 3 — show all 13

Tips

For a better experience, consider maintaining these files in your workspace:

• watchlist.md — Your coverage universe
• biases.md — Your research bias log (Red Team will check this)
• decision-log.md — Investment decision journal

---

What's Included

• 13 research skills (from master control to specialized modules)
• 7 work modes: Thesis / Coverage / Consensus / Catalyst / Red Team / Briefing / PM Prep
• Evidence grading system (F1/F2/M1/C1/H1)
• Compliance boundaries and expression standards
• Data source adapter decision tree (iFind MCP → cn-web-search → built-in search → manual)

Data Sources (all optional)

1. iFind MCP (THS, A-shares / funds / macro)
2. cn-web-search (17 free Chinese search engines)
3. Built-in WebSearch / WebFetch
4. User-provided materials (fallback)

See core/adapters.md for details.

Markets Covered

• A-shares (Shanghai/Shenzhen)
• Hong Kong stocks
• US equities
• Mutual funds
• Cross-market themes

Compatibility

Claude Code / Codex / OpenCode / OpenClaw / any AI tool that reads Markdown.

License

MIT © 2026 Joan Song