AgentStack
SKILL verified MIT Self-run

Valuation Investment Strategy

skill-spikehongg-china-stock-research-skills-valuation-investment-strategy · by spikeHongg

Convert a source-backed A-share research view into valuation scenarios and an investment plan. Use this skill after strategy, business, financial, industry, and risk work is complete. Choose methods that fit the business model and explain assumptions with accessible source links.

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-spikehongg-china-stock-research-skills-valuation-investment-strategy

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Valuation Investment Strategy? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Valuation Investment Strategy

Build scenario-based valuation only after the factual base is complete.

Non-Negotiable Rules

  • Do not invent inputs when public evidence is missing.
  • Tie every key assumption to a public source or a clearly labeled analytical assumption.
  • Use scenario analysis instead of false precision.
  • Keep facts separate from judgment and trading plan.
  • Default every intermediate and final output to Simplified Chinese unless the user explicitly requests another language.

Read First

  • skills/shared/references/citation-standard.md
  • skills/shared/references/research-output-template.md
  • skills/shared/references/analysis-pattern-selector.md
  • skills/shared/references/language-output-standard.md
  • skills/shared/templates/valuation-scenario-table.md
  • skills/valuation-investment-strategy/references/method-selection.md
  • If the company is in a business-model transition or asset-heavy ramp, also load the matching shared overlay.
  • If the company is an IDC or AI-compute transition case, skills/shared/references/idc-heavy-asset-transition-overlay.md and skills/valuation-investment-strategy/references/idc-valuation-overlays.md are optional example overlays.

When to Use

  • A full company view already exists and now needs a valuation frame.
  • The company is in transition and simple PE is not enough.
  • The report needs bear, base, and bull cases with explicit assumptions.

Workflow

  1. Pull outputs from the previous five skills.
  2. Select the right method: peer multiple, SOTP, EV/EBITDA, PB, DCF, or asset-based.
  3. Define a scenario table with revenue, margin, capex, utilization, and balance-sheet assumptions.
  4. Link every assumption to the supporting source or mark it as an analytical estimate.
  5. Produce a value range, thesis checkpoints, and invalidation triggers.

Required Output

  • 事实: valuation-relevant facts, peer set, asset base, financing constraints
  • 解读: which method is most suitable and why
  • 待验证问题: missing occupancy, margin, capex, or disposal assumptions
  • Scenario Table: bear, base, bull with linked assumptions
  • Investment Plan: build condition, stop condition, and thesis-confirmation milestones

Boundaries

  • Do not rebuild the raw company fact base from scratch.
  • Do not present unsupported precision such as exact fair value without ranges.
  • Do not ignore risk and balance-sheet constraints.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.