Leading Indicators logo

Leading Indicators

Community
agentii-ai
leading-indicators

Leading economic indicators analysis, ISM PMI, yield curve, consumer sentiment UMCSI, jobless claims, building permits, economic turning point detection, recession signal analysis

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill nameleading-indicators
Stars
207
Forks
16
Bundled files
4
LicenseApache-2.0
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.

  • 4 bundled files

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

  • Open source

    Published by agentii-ai on GitHub. Read the source before you install it.

Installation

Install the Leading Indicators 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/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/macro-strategy/skills/agentii/leading-indicators
  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/agentii-ai/agentii-investment-intelligence.git /tmp/agentii-investment-intelligence
mkdir -p .claude/skills
cp -r /tmp/agentii-investment-intelligence/plugins/vertical-plugins/macro-strategy/skills/agentii/leading-indicators .claude/skills/leading-indicators
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Leading Indicators 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 Leading Indicators 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 Leading Indicators 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.

Methodology inspired by publicly taught trading frameworks; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
lookback_quarters4Standard window for leading-indicators
gdp_forecast_lag6 monthsS&P 500 leads GDP with maximum statistical significance at the 6-month horizon (10-year rolling correlation avg: 0.56, 1960–2020)
indicator_frequencyweeklyMoney-market and survey indicators are tracked weekly; GDP is quarterly
portfolio_biaslong / neutral / shortMacro view resolves to one of three biases governing portfolio construction

Preflight

Run canonical pre-flight per contracts/preflight.md. Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md — carry the _run_id from your first tool result and name yourself (and your parent, if you were spawned).

Data Source Priority

  1. Leading indicators framework — references/leading-indicators-framework.md (bundled methodology)
  2. Knowledge entries — query search_knowledge_entries for supplementary L1 frameworks
  3. Historical analogues — query search_by_analogue(market_regime, event_type)
  4. Real-time data — FRED (real rates, yield curve, money supply, credit spreads), ISM PMI, UMCSI, jobless claims, building permits, commodity prices, DXY

Methodology

Retrieval Scope

structured_only

Retrieval Strategy

This skill follows Branch (d) Simple Lookup from contracts/retrieval.md: query knowledge entries for L1 macro and leading-indicator frameworks; query search_by_analogue for historical regime analogues resolved from the indicator panel. No unstructured document retrieval.

Temporal Scope

See frontmatter temporal_scope block.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

The Pro-Trader Systematic macroeconomic framework: predict GDP → predict stock-market returns. S&P 500 leads GDP by 6 months (10-year rolling correlation avg 0.56). Two analytical axes: Growth drives earnings (E); Liquidity drives price (P). Detailed indicator methodology, thresholds, and decision rules are in references/leading-indicators-framework.md.

  1. GDP Baseline: Quadrinomial method (S&P 500 quarterly returns 6-month lagged vs real GDP). Four outcomes: 0-0 (both down, 8.2%), 1-1 (both up, 60.9%), 0-1 (profit-taking, 25.6%), 1-0 (unpredictable, 5.3%). 10-year rolling correlation check. Apply to EuroStoxx 600 vs Eurozone GDP. Skip China Shenzhen (unreliable correlation ~0.05).

  2. Money Market Indicators (earliest and most reliable):

    • Real interest rates: Nominal rate − CPI. Classify accommodative (< 0.5%), neutral (0.5–2%), restrictive (> 2%). Direction: falling = bullish; rising = bearish.
    • Yield curve (2s10s): Normal/steep = expansionary. Flattening = transition. Inverted = recession (6–18 month lead). Steepening from inversion = recovery. Monitor TED spread (3m LIBOR vs 3m Treasury) for global dollar stress.
    • Credit spreads: Hierarchy AA (ICE BofA, FRED) → BBB → CCC (junk moves first). Widening = contractionary → sell. Tightening = expansionary → buy. CCC blowout 400+ bps with AA calm = stress concentration.
    • M2 Money Supply: Accessory only. Accelerating + falling real rates = confirm expansion. Decelerating + rising real rates = confirm contraction. Divergence = flag regime ambiguity.
  3. Survey Indicators:

    • ISM Manufacturing PMI: > 50 expansion, < 50 contraction. Prioritize New Orders sub-component. PMI < 45 = strong contraction.
    • UMCSI Consumer Sentiment: < 70 recession warning, > 90 confident. Sharp MoM drops > 5 points often precede equity corrections.
  4. Commodity Prices: Copper (pervasive industrial demand proxy — compare LME vs Shanghai). Brent crude (rising with copper = demand-driven, bullish; rising without copper = supply shock, bearish).

  5. Market & Forex: S&P 500 as ultimate daily leading indicator. DXY strengthening = tightening global conditions; weakening = loosening. Cross-reference DXY direction against credit spread direction.

  6. Coincident & Lagging Cross-Check: CPI, PPI, NFP (coincident); GDP, earnings, unemployment (lagging). Never trade on lagging indicators alone.

  7. International: European ESI, China PMI (Official vs Caixin — Caixin often leads), Japan Tankan + JGB, UK Gilts + PMI, Germany Bund + Ifo, Italy BTP-Bund spread. Apply local CPI for real rates.

  8. Dashboard & Bias Resolution: Score 11 indicator categories (high-weight: real rates, yield curve, credit spreads, ISM PMI, S&P 500). ≥ 60% expansionary → net long. ≥ 60% contractionary → net short. Mixed → neutral.

  9. Analogue Retrieval: Query search_by_analogue with market_regime and event_type matching current configuration. Cite via /v/.

  10. Regime Classification: Expansion / Contraction / Stagflation / Recovery with Bear/Base/Bull probability weights and transition catalysts.

Output File

{ticker}/{YYYY-MM-DD_HHMM}_leading-indicators_{affix}.md

Output Structure

  1. Executive Summary — GDP forecast (6-month forward), portfolio bias (long / neutral / short), regime classification with probability weights, top 3 signals in 2–3 sentences
  2. GDP Baseline — quadrinomial quadrant assignment, rolling correlation trend (S&P 500 vs GDP, 6-month lag), international comparison (Eurozone, China)
  3. Money Market Indicators — real interest rates (current level + direction), yield curve 2s10s (shape + direction), credit spreads (AA / BBB / CCC spreads over 10Y, direction + magnitude), M2 money supply growth (trend)
  4. Survey Indicators — ISM Manufacturing PMI (headline + new orders), UMCSI consumer sentiment (headline + expectations)
  5. Commodity & Market Signals — copper, Brent crude, S&P 500 quarterly direction, DXY trend
  6. International Context — European ESI, China PMI (official vs Caixin), other major economy indicators
  7. Leading Indicator Dashboard — weighted scorecard table with expansionary/contractionary signal count
  8. Regime Classification — regime type (Expansion / Contraction / Stagflation / Recovery), probability weights (Bear / Base / Bull), transition catalysts
  9. Portfolio Bias Recommendation — net long / net short / neutral with supporting evidence
  10. Historical Analogues — matched cases from search_by_analogue with /v/ citations
  11. Risk Assessment & Caveats — Fed intervention risk, signal divergence flags, data limitations
  12. Coverage Gaps — indicators with stale / missing data; degraded-mode annotations

Error Handling

ErrorFallback
No L1 frameworks foundProceed with the standard 10-indicator panel described in Protocol; flag degraded
search_by_analogue emptyNote "no relevant historical analogues found" — do not fabricate
Real-time data unavailableUse last-known values with staleness flag; indicate date of last observation
Credit spread data missing for one tierUse available tiers (AA/BBB) and note the gap; CCC data is most volatile and optional
Yield curve data flat / 2Y missingUse 3m10y or Fed funds vs 10Y as alternative curve; note substitution
International indicator missingProceed with US-only dashboard; flag international gap

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

  • references/leading-indicators-framework.md
  • contracts/citation-and-memory.md
  • contracts/output-frontmatter-schema.md
  • contracts/memory-load.md
  • contracts/snapshot-synthesis.md
  • contracts/preflight.md
  • contracts/retrieval.md

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 Leading Indicators AI skill do?

Leading economic indicators analysis, ISM PMI, yield curve, consumer sentiment UMCSI, jobless claims, building permits, economic turning point detection, recession signal analysis

Why use Leading Indicators on TypingMind?

Because you install it once and use it with any model. Leading Indicators 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 Leading Indicators in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/macro-strategy/skills/agentii/leading-indicators. 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 Leading Indicators?

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 Leading Indicators?

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

Is the Leading Indicators AI skill free?

Yes. It is published on GitHub by agentii-ai under the Apache-2.0 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 👇