Juglar Cycle Stock Stage logo

Juglar Cycle Stock Stage

Community
haskaomni
juglar-cycle-stock-stage

Classify a listed company and its core industry into Juglar fixed-asset investment cycle stages with probabilities, evidence, counter-evidence, migration signals, and investment implications. Use when the user provides a ticker/company or asks about 朱格拉周期, Juglar cycle, capex cycle, fixed-asset investment cycle, industry cycle phase, recovery, expansion, overheating, downturn, clearing, inventory cycle, capacity cycle, ASP, or supply-demand cycle positioning.

Overview

Publisherhaskaomni
Repositoryserenity-skill
Skill namejuglar-cycle-stock-stage
Stars
633
Forks
97
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by haskaomni on GitHub. Read the source before you install it.

Installation

Install the Juglar Cycle Stock Stage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/haskaomni/serenity-skill/tree/main/skills/juglar-cycle-stock-stage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/haskaomni/serenity-skill.git /tmp/serenity-skill
mkdir -p .claude/skills
cp -r /tmp/serenity-skill/skills/juglar-cycle-stock-stage .claude/skills/juglar-cycle-stock-stage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Juglar Cycle Stock Stage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Juglar Cycle Stock Stage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Juglar Cycle Stock Stage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Juglar Cycle Stock Stage

Core Principle

Judge the company's Juglar cycle position from the industry fixed-asset investment cycle first, then the company's own operating phase second. Do not classify from share price, PE, or narrative alone.

Use the framework to answer:

text
Where are the company and its core industry in the fixed-asset investment cycle, and what evidence would move the judgment to the next phase?

Treat outputs as research analysis, not personalized investment advice. For latest/current scoring, verify market price, filings, earnings, guidance, industry supply-demand, capex plans, inventory, ASP, backlog, and estimate revisions from current sources before making time-sensitive claims.

Required Inputs

Required input: a ticker or clearly identifiable listed company.

Optional user inputs:

  • market: US, HK, A股, 台股, 日股, 韩股, etc.
  • horizon: 6 months, 12 months, 24 months, or 3-5 years
  • cost basis or position size for risk framing only; do not let it affect cycle classification

If the ticker is ambiguous, identify the most likely listed company and state the assumption. Ask only when multiple candidates are genuinely plausible and the wrong choice would change the analysis.

Required Evidence

Collect and separate industry-cycle evidence from company-specific evidence:

  • demand: orders, shipments, backlog, book-to-bill, utilization, customer capex, downstream demand
  • price / ASP: product pricing, contract prices, commodity prices, discounting, pricing power
  • profitability: gross margin, operating margin, EPS, loss/profit inflection, operating leverage
  • capex: company capex, peer capex, industry capacity announcements, fab/plant/vessel/equipment orders
  • inventory: company inventory, channel inventory, customer inventory, days inventory, destocking/restocking
  • capacity pressure: new capacity timing, utilization, supply bottlenecks, lead times, future overcapacity risk
  • customer behavior: rush orders, long-term agreements, replenishment, order deferrals, price pressure, cancellations
  • capital-market reaction: price trend, valuation, estimate revisions, sentiment, whether stock pricing is ahead of cycle evidence

For U.S.-listed companies, SEC filings can anchor reported revenue, margins, capex, inventory, backlog/order language, capacity plans, customer concentration, and risk factors. Use current market and industry sources for ASP, consensus estimates, stock trend, and competitive capex.

Five Stages

StagePhaseTypical Signal
Stage 1复苏期Demand improves, prices stop falling, inventory declines, margins repair, capex has not yet surged.
Stage 2扩张期Orders are strong, revenue/profit accelerate, utilization rises, capex starts increasing.
Stage 3过热期Prices and margins are high, optimism is broad, companies expand aggressively, future supply risk accumulates.
Stage 4衰退期Demand growth slows, prices soften, inventory rises, margins fall, capex begins to be cut.
Stage 5出清期Industry losses or weak profits force capex cuts, destocking, shutdowns, consolidation, layoffs, or restructuring.

Always distinguish:

  • industry cycle stage
  • company competitive/operating stage
  • stock valuation or market-pricing stage

These can diverge. Example: industry Stage 3, company Stage 2, stock already priced as Stage 3.

Eight-Dimension Scoring

Score each dimension from -2 to +2 and explain the evidence.

Dimension+2+10-1-2
Demand cycledemand surgedemand improvingstableslowingsharply declining
Price / ASP cyclesustained price risesprices bottoming/reboundingstablebeginning to fallrapid decline
Margin cyclemargins expanding fastmargins repairingstablepressuredsharply worse or loss-making
Capex cyclebroad aggressive expansioncapex revised up / expansion startsstableslowingsharply cut
Inventory cycleextremely low / tight supplydecliningnormalrisinghigh / channel clogged
Capacity-release pressurelittle new supply / bottleneckmanageable new supplybalancedclear new supply in 6-18 monthsconcentrated supply release / overcapacity risk
Customer behaviorrush orders, LTAs, accepts price hikesrestockingnormal purchasingdelays or price pressureorder cuts or cancellations
Capital-market reactionestimates rising and trend healthyvaluation repairdividedprice weakens ahead of fundamentalsderating and estimate cuts

Do not mechanically map the total score to a stage. Use the four core variables first: margin, capex, inventory, and price.

Stage Mapping Rules

Use these patterns as anchors:

StagePattern
Stage 1 复苏期demand +1, price +1, margin +1, capex 0/+1, inventory +1, market starts repairing
Stage 2 扩张期demand +2, price +1/+2, margin +2, capex +1, inventory +1/+2, estimates rising
Stage 3 过热期demand +2, price +2, margin +2, capex +2, inventory still low, future supply pressure rising, valuation/story very optimistic
Stage 4 衰退期demand -1/-2, price -1/-2, margin -1/-2, inventory -1/-2, capex rolls over, customers pressure prices or cut orders
Stage 5 出清期demand weak, prices low, margins poor or loss-making, inventory begins falling, capex -2, industry consolidation or shutdowns appear

Output stage probabilities across all five stages. The probabilities must sum to roughly 100%, and the most likely stage should include a confidence level.

Mermaid Visualizations

For a full report, include 2-4 Mermaid diagrams when they materially improve comprehension. A short answer or data-limited analysis may use fewer. Do not create a diagram merely to meet a quota.

Prioritize these views:

  1. A five-stage flowchart showing the Juglar cycle and visibly highlighting the current industry stage; annotate a different company stage only when it diverges.
  2. A pie chart of Stage 1-5 probabilities after confirming they match the probability list and sum to roughly 100%.
  3. An xychart-beta of the eight dimension scores on the common -2 to +2 scale, with the scoring table retained.
  4. A compact flowchart of the signals required to enter the next stage and the evidence that would invalidate the current classification.

Apply these rules to every diagram:

  • Use fenced mermaid blocks, match the report language, keep node IDs in simple ASCII, and keep labels short.
  • Prefer broadly supported flowchart, pie, and stateDiagram syntax. Use xychart-beta, quadrantChart, or timeline only as progressive enhancement and retain the adjacent Markdown table as the fallback.
  • Use only evidence and values already stated in the report. Keep stage names, probabilities, score scales, and horizons consistent with the surrounding tables; never fill missing data for visual completeness.
  • Place each diagram beside the analysis it explains and follow it with a one-sentence takeaway. Keep citations, URLs, dates, and detailed caveats outside the diagram.
  • Keep a diagram focused: normally no more than 12 nodes or 8 plotted values. Diagrams supplement rather than replace scoring evidence, counter-evidence, migration conditions, and source trails.

Output Format

Use Chinese by default unless the user requests another language.

markdown
# TICKER:朱格拉周期阶段判断

【结论】
股票代码:
公司:
核心行业:
行业朱格拉周期阶段:
公司自身阶段:
股票定价阶段:
置信度:
未来 6-12 个月方向:

【阶段概率】
Stage 1 复苏期:xx%
Stage 2 扩张期:xx%
Stage 3 过热期:xx%
Stage 4 衰退期:xx%
Stage 5 出清期:xx%

紧接概率列表加入 Stage 1-5 Mermaid pie;数值必须与列表一致。

【周期位置图】
加入五阶段 Mermaid flowchart,并高亮当前行业阶段;公司阶段不同则单独标注。

【一句话判断】
...

【8维评分表】
| 维度 | 分数 | 证据 | 解释 |
| --- | ---: | --- | --- |
| 需求周期 | | | |
| 价格周期 / ASP | | | |
| 利润率周期 | | | |
| 资本开支周期 | | | |
| 库存周期 | | | |
| 产能释放压力 | | | |
| 客户行为 | | | |
| 资本市场反应 | | | |

如八维数据完整,在表后加入 -2 到 +2 同量纲的 Mermaid xychart,并保留评分表。

【核心证据】
1.
2.
3.

【反证与风险】
1.
2.
3.

【阶段迁移信号】
- 进入下一阶段需要看到:
- 当前判断被推翻需要看到:

加入 Mermaid flowchart 展示迁移条件与证伪分支。

【投资含义】
1. 短期交易含义:
2. 中期持仓含义:
3. 最大风险:

【最终评级】
周期位置:
风险收益比:
适合策略:左侧买入 / 右侧持有 / 趋势加仓 / 逢高减仓 / 等待出清 / 只观察

Detailed Reference

Read references/original-framework.md when a task needs the full Chinese source framework, exact stage definitions, complete scoring tables, or the original prompt wording.

When the reference format differs, preserve its analytical intent but follow this SKILL.md's current output and visualization rules.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Juglar Cycle Stock Stage AI skill do?

Classify a listed company and its core industry into Juglar fixed-asset investment cycle stages with probabilities, evidence, counter-evidence, migration signals, and investment implications. Use when the user provides a ticker/company or asks about 朱格拉周期, Juglar cycle, capex cycle, fixed-asset investment cycle, industry cycle phase, recovery, expansion, overheating, downturn, clearing, inventory cycle, capacity cycle, ASP, or supply-demand cycle positioning.

Why use Juglar Cycle Stock Stage on TypingMind?

Because you install it once and use it with any model. Juglar Cycle Stock Stage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Juglar Cycle Stock Stage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/haskaomni/serenity-skill/tree/main/skills/juglar-cycle-stock-stage. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Juglar Cycle Stock Stage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Juglar Cycle Stock Stage?

As many as you like. As long as a model supports skills, you can use Juglar Cycle Stock Stage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Juglar Cycle Stock Stage AI skill free?

Yes. It is published on GitHub by haskaomni under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇