Agent skill

Commodity Cycle Analysis

by byteseek in byteseek/Mira

Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.

Apache-2.0Auto-check passedMarketing & SEO

Install Commodity Cycle Analysis

skills CLI
$ npx skills add byteseek/Mira --skill commodity-cycle-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install byteseek/Mira commodity-cycle-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/byteseek/Mira.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/commodity-cycle-analysis .claude/skills/commodity-cycle-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
commodity-cycle-analysis
GitHub stars
275
Token cost
~3k tokens
SKILL.md length
1,312 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.

  • Works in 10 steps: Routing Snapshot → Commodity Identity And Contract Map → Physical Balance → …
  • Tasks that involve Positioning and messaging
  • SKILL.md covers Use When, Avoid When, Required Inputs and Core Principle, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Commodity Cycle Analysis is an agent skill from byteseek/Mira. Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Positioning and messaging. The repository describes itself as: Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Positioning and messaging

Example prompts

  • “/commodity-cycle-analysis”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Routing Snapshot
  2. Commodity Identity And Contract Map
  3. Physical Balance
  4. Inventory And Curve Structure
  5. Cost Curve And Supply Response
  6. Demand Map
  7. Policy, Geopolitics And Trade Flow
  8. Financial Conditions And Positioning
  9. Asset Transmission
  10. Market Pricing And Variant Perception

What it can do on your machine

Read from SKILL.md and the folder at commit adddce7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Commodity Cycle Analysis loads about 3k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 1,312 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from byteseek/Mira at commit adddce7, republished under its Apache-2.0 licence (© byteseek). 1,312 words, ~2,965 tokens.

Download SKILL.mdSave it as .claude/skills/commodity-cycle-analysis/SKILL.md (or your agent's skills folder).
name
commodity-cycle-analysis
description
Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.

Commodity Cycle Analysis Skill

这个 skill 用于研究实物大宗商品、商品期货曲线、资源周期和商品价格对资产的传导。

它不是泛宏观综述,也不是资源股单票模板。它服务于一个核心问题:

当前商品价格到底由供需平衡、库存、成本曲线、政策/地缘风险、金融条件还是仓位驱动?这个驱动是否足以改变目标资产的盈利、估值、风险溢价或交易节奏?

Use When

  • 研究对象是原油、成品油、天然气、LNG、煤炭、铜、铝、镍、锂、铀、铁矿、钢、黄金、白银、农产品或其他商品。
  • 用户问商品价格、期货曲线、库存、供需平衡、成本曲线、OPEC、制裁、出口限制、矿山供给、天气、WASDE、EIA、IEA、LME、CFTC 或商品 ETF。
  • 单票、ETF 或产业研究的主变量是商品 beta,而不是公司自身执行、技术路线或普通宏观风险偏好。
  • 需要判断资源股、能源股、材料股、化工、航运、消费或通胀资产受到商品冲击的方向和幅度。

Avoid When

  • 目标资产的主要变量是公司订单、融资、生存性、监管审批、技术验证或并购催化剂。
  • 商品价格只是背景,不能改变收入、利润率、资本开支、估值、资金流或仓位。
  • 没有可用的供需、库存、曲线或成本数据,只能复述价格走势。
  • 研究对象是泛宏观 regime,且不需要拆具体商品的物理平衡表。

Required Inputs

  • commodity_or_asset
  • market_scope 例如 global / US / China / Europe / multi
  • research_question
  • research_cutoff_date
  • thesis_horizon 例如 days_weeks / 1Q_2Q / 2Q_8Q / cycle
  • current_market_pricing 至少包括现货、近月、远月、曲线形态或相关 ETF/股票表现中的两项。
  • commodity_sources 至少覆盖官方/行业数据、市场价格或仓位数据、公司/行业披露、机构或 practitioner 解释中的两类。

Core Principle

先拆物理平衡,再拆金融定价;先问价格在反映什么,再问这个反映能不能持续。

商品研究不能只看价格涨跌。必须把结论落到至少一条可证伪链条:

  • demand shock -> inventory draw -> curve backwardation -> producer cash flow revision
  • supply disruption -> spot premium -> cost passthrough -> downstream margin compression
  • cost curve reset -> marginal supply discipline -> long-dated price support
  • policy/geopolitics -> trade flow rerouting -> regional basis widening -> asset impact
  • real rates / dollar -> investment demand -> precious metal price -> miner multiple
  • weather / crop condition -> yield revision -> stock-to-use ratio -> futures curve
  • positioning squeeze -> price overshoot -> roll yield / equity beta risk

If no credible chain exists, commodity stays as context and should not enter the core thesis.

Analysis Sequence

0. Routing Snapshot

Start every formal note with:

  • task_mode
  • commodity_or_asset
  • market_scope
  • time_boundary
  • dominant_driver one of physical_balance, inventory_cycle, cost_curve, policy_geopolitics, financial_conditions, positioning, mixed
  • commodity_weight one of none, context, secondary, primary
  • routing_mismatch_risk
  • expected_output_package
1. Commodity Identity And Contract Map

Define what is being studied:

  • physical commodity, benchmark, grade, geography and delivery point
  • main traded instruments: spot benchmark, futures contract, ETF, equity proxy or spread
  • substitutes and adjacent commodities
  • most relevant consuming sectors
  • most relevant producing regions or companies

Avoid mixing benchmarks without saying so. WTI is not Brent; Henry Hub is not JKM; LME copper is not every copper concentrate or regional premium; gold bullion is not gold miners.

2. Physical Balance

Build the balance in levels and deltas:

  • production / supply
  • consumption / demand
  • imports / exports and trade flows
  • inventories and stock changes
  • spare capacity or shut-in / restart capacity
  • seasonal pattern
  • bottlenecks: logistics, refining, smelting, grid, shipping, storage or permitting

Separate:

  • level
  • change
  • surprise_vs_expectation
  • breadth
  • sustainability
3. Inventory And Curve Structure

Always inspect inventory together with curve structure.

Required checks:

  • exchange or official inventory level and direction
  • commercial / strategic / visible vs invisible inventory when available
  • days of cover or stock-to-use ratio when relevant
  • spot vs front-month vs deferred prices
  • contango / backwardation and spread movement
  • roll yield implication for ETFs and futures-based exposure

Interpretation guardrail:

  • Falling inventory with backwardation usually signals tightness, but can be distorted by logistics, sanctions, financing cost, storage constraints or contract-specific squeezes.
  • Rising inventory with contango usually signals slack, but can coexist with future supply risk or seasonal builds.
4. Cost Curve And Supply Response

For producers and resource equities, connect price to marginal economics:

  • cash cost, all-in sustaining cost, marginal cost or incentive price
  • capex cycle and project lead time
  • depletion, decline rate or reserve quality
  • shut-in, restart and substitution thresholds
  • cost inflation in labor, energy, freight, reagents, equipment or financing
  • producer discipline versus growth capex

Core question:

Is price above the level that changes behavior, or merely moving within noise?

5. Demand Map

Split demand by end market and sensitivity:

  • cyclical industrial demand
  • transport / mobility
  • power generation
  • construction / property
  • manufacturing / electronics
  • agriculture / food / feed
  • investment and reserve demand
  • policy-driven or energy-transition demand

For each demand bucket:

  • leading indicators
  • lag to commodity consumption
  • substitution risk
  • price elasticity
  • reliability of available data
6. Policy, Geopolitics And Trade Flow

Do not treat policy and geopolitics as generic risk labels.

Map the concrete mechanism:

  • production quota
  • export ban or license
  • sanctions and enforcement
  • tariffs or trade restrictions
  • strategic reserve purchase / release
  • environmental permit, mine license or pipeline approval
  • shipping route disruption
  • local subsidy or demand mandate

Then state:

  • affected volume
  • affected region or benchmark
  • expected duration
  • verification path
  • what would confirm
  • what would disconfirm
7. Financial Conditions And Positioning

Use this layer only after physical balance is clear, unless the commodity is primarily financialized in the current setup.

Check:

  • dollar and real rates
  • inflation expectations
  • CFTC COT or exchange positioning where available
  • ETF flows and open interest
  • volatility, skew and CTA trend risk when available
  • roll yield and funding cost

Do not confuse a positioning squeeze with a durable supply-demand deficit.

Precious Metals Residual Lens

For gold, silver and precious-metals ETFs, consider the gold-residual-regime-lens when the main question is whether price is explained by the usual macro factor stack or has entered a residual / bubble-like regime.

Use this lens only as a labeled overlay:

  • related card: memory/methodologies/gold-residual-regime-lens.md
  • compact template: templates/gold-residual-regime-check.csv
  • required status: gold_residual_lens = qualitative_only, recomputed, or calculation_gap

Minimum checks:

  • dollar proxy
  • real-rate or purchasing-power proxy
  • inflation or non-gold commodity proxy
  • crisis optionality / volatility proxy
  • ETF, central-bank, futures positioning or investment-flow proxy when available
  • whether residual widening is already priced by bullion, miners or ETFs

Guardrail: residual widening is a risk-regime input, not a standalone timing signal. If the factor stack is not independently rebuilt, mark calculation_gap and keep conclusions at working_view or monitor.

Show full SKILL.md (543 more words)Show less
8. Asset Transmission

Map commodity move to the target asset:

  • producers: realized price, hedges, cost inflation, volume, capex, FCF, buybacks/dividends
  • consumers: input cost, pass-through ability, gross margin, working capital, demand destruction
  • ETFs/futures: roll yield, benchmark tracking, liquidity, tax/structure risk
  • macro assets: inflation, fiscal/external balance, rates, currency and risk premium
  • resource equities: commodity beta, company alpha, balance sheet, project execution and political risk

For single-equity handoff, state:

  • commodity_beta one of low, medium, high
  • commodity_driver_quality one of high, medium, low, source_gap
  • company_alpha_separation what can be explained by commodity price versus company-specific execution.
9. Market Pricing And Variant Perception

Commodity work must include what is already priced:

  • current spot / curve shape
  • consensus or public forecast range when available
  • equity or ETF relative performance
  • inventory and curve signals already visible to market
  • key debate and opposing view

Then define:

  • base case
  • bull case
  • bear case
  • surprise needed for repricing
  • what would make the view stale

Required Source Types

Minimum coverage depends on the commodity, but every durable conclusion should try to include:

  • L2 official or industry data: EIA, IEA, OPEC, USDA WASDE, USGS, LME, exchange data, customs data, national statistics, industry associations.
  • L5 market data: spot/futures prices, curve spreads, ETF performance, open interest, CFTC COT or exchange positioning.
  • L1 company disclosures when mapping to equities: producer reports, reserves, cost guidance, hedges, capex and operating metrics.
  • L3 institutional or specialist research: used for interpretation, not as primary fact.
  • L4 news and practitioner commentary: useful for disruptions and trade-flow color, but must be cross-checked.

Source-quality rule:

  • Official data supports facts.
  • Market data supports pricing and positioning.
  • Company disclosure supports company exposure.
  • Institutional/practitioner sources support interpretation only unless independently verifiable.

Output Package

For standalone commodity work, output a commodity-analysis-package:

  • commodity-cycle-note.md
  • evidence-log.csv

commodity-cycle-note.md must contain:

  • routing snapshot
  • one-page view
  • contract / benchmark map
  • physical balance
  • inventory and curve structure
  • cost curve and supply response
  • demand map
  • policy / geopolitics / trade flow
  • financial conditions and positioning
  • asset transmission
  • market pricing and variant perception
  • monitoring dashboard
  • stale_after
  • must_refresh_if

For equity research, add commodity fields to memo or case notes:

  • selected_overlays: commodity
  • commodity_weight
  • commodity_overlay_basis
  • dominant_commodity_driver
  • commodity_transmission_chain
  • what_is_already_priced
  • commodity_mismatch_risk
  • commodity_refresh_triggers

Monitoring Dashboard

Every commodity view needs a small dashboard:

  • price: spot, front-month and key deferred contract
  • curve: nearest relevant spread
  • inventory: level and direction
  • supply: production / outage / quota / project update
  • demand: high-frequency proxy or official demand update
  • cost: marginal or incentive-cost proxy if available
  • policy/geopolitics: active event and verification path
  • positioning: COT / ETF flow / open interest where relevant
  • for precious metals when residual lens is used: factor stack status, residual state and calculation status

Failure Modes

  • Treating every commodity move as macro when the true driver is inventory or trade flow.
  • Treating every inventory draw as durable demand without checking seasonality and logistics.
  • Ignoring curve structure and roll yield when analyzing futures or commodity ETFs.
  • Using producer equities as pure commodity proxies without separating hedges, costs, balance sheet and project risk.
  • Confusing spot tightness with long-cycle incentive pricing.
  • Ignoring policy quota, sanctions, export bans or strategic reserve actions.
  • Explaining price action after the fact without predefining refresh and falsification triggers.
  • For gold, treating a residual / MSE spike as a trade signal without rebuilding the factor stack, checking flows / positioning, and separating bullion beta from miner equity alpha.

Current Status

  • methodology_status: trial
  • related_methodology_card: memory/methodologies/commodity-cycle-analysis.md
  • related_overlay: skills/equity-research-core/references/commodity-overlay.md
  • related_precious_metals_lens: memory/methodologies/gold-residual-regime-lens.md

© byteseek, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/commodity-cycle-analysis of byteseek/Mira.

Open the folder on GitHubat commit adddce7

Compare with similar skills

Commodity Cycle Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Commodity Cycle Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Commodity Cycle Analysis this skillbyteseek/Mira275—~3kAutomated safety check: PassApache-2.0
Marketing OsYuzzyuk/marketing-os538—~2.5kAutomated safety check: PassMIT
Revenue Centric Designheliocosta-dev/revenue-centric-design740—~1.6kAutomated safety check: PassCustom licence
Startup Positioningferdinandobons/startup-skill1.2k—~4.6kAutomated safety check: PassMIT
Stanley Druckenmiller Investmenttradermonty/claude-trading-skills3k1 repos~2kAutomated safety check: PassMIT
B2b Playbookweilun88313/B2B-Playbook203—~3.1kAutomated safety check: PassProprietary

Similar skills

  • Marketing Os

    Yuzzyuk/marketing-os

    A complete marketing department in one skill. An agent skill from Yuzzyuk/marketing-os.

    538 GitHub stars~2.5k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Revenue Centric Design

    heliocosta-dev/revenue-centric-design

    Playbook for designing SaaS and startup products that convert, retain, and monetize — landing pages & CRO, checkout & forms, onboarding/activation, churn reduction, pricing psychology, dashboards…

    740 GitHub stars~1.6k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Startup Positioning

    ferdinandobons/startup-skill

    Market positioning strategy using the April Dunford framework, enriched with JTBD discovery, Moore positioning statement, and Neumeier's Onliness Test.

    1.2k GitHub stars~4.6k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Stanley Druckenmiller Investment

    tradermonty/claude-trading-skills

    Druckenmiller Strategy Synthesizer - Integrates 8 upstream skill outputs (Market Breadth, Uptrend Analysis, Market Top, Macro Regime, FTD Detector, VCP Screener, Theme Detector, CANSLIM Screener)…

    3k GitHub starsUsed in 1 repo~2k tokens
    Marketing & SEOAuto-check passed
  • B2b Playbook

    weilun88313/B2B-Playbook

    Turn B2B marketing work into evidence-aware outputs using market, positioning, demand, account-program, lifecycle, and tool-selection guidance.

    203 GitHub stars~3.1k tokensUpdated 27 days ago
    Marketing & SEOAuto-check passed
  • Research Brand

    onvoyage-ai/gtm-engineer-skills

    Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and messaging.

    1.3k GitHub stars~1.3k tokensUpdated 4 mo ago
    Marketing & SEOAuto-check passed

More from byteseek/Mira

All 10 skills in this repo
  • Discover listed, pending, filed, or newly announced ETFs and create a structured candidate watchlist for ETF listing analysis.

    275 GitHub stars~887 tokensUpdated 1 mo ago
    Auto-check passed
  • Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.

    275 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Analyze new, pending, or expanding ETF products as product signals, exposure maps, demand indicators, and potential asset-pricing read-throughs.

    275 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Gate quantitative Mira conclusions by requiring reproducible data, formulas, calculation ledgers, or explicit downgrades when numbers drive judgment.

    275 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Analyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event.

    275 GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Map an unclear industry concept into boundaries, value chain, supply-demand mechanics, profit pools, evidence gaps, and investable candidates.

    275 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Commodity Cycle Analysis

What does Commodity Cycle Analysis do?

Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets. Commodity Cycle Analysis is an agent skill from byteseek/Mira. Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.

When should I use Commodity Cycle Analysis?

Commodity Cycle Analysis fits situations like: tasks that involve Positioning and messaging.

How do I install Commodity Cycle Analysis in Claude Code?

Run `npx skills add byteseek/Mira --skill commodity-cycle-analysis -a claude-code`. Or copy the skill folder (skills/commodity-cycle-analysis in byteseek/Mira) into .claude/skills/commodity-cycle-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Commodity Cycle Analysis in Codex?

Run `npx skills add byteseek/Mira --skill commodity-cycle-analysis -a codex`. Or copy the skill folder (skills/commodity-cycle-analysis in byteseek/Mira) into .agents/skills/commodity-cycle-analysis in your project. Codex loads it when a task matches its description.

Can I use Commodity Cycle Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add byteseek/Mira --skill commodity-cycle-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/commodity-cycle-analysis, .gemini/skills/commodity-cycle-analysis, .github/skills/commodity-cycle-analysis and .opencode/skills/commodity-cycle-analysis in your project.

What does Commodity Cycle Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Commodity Cycle Analysis is instructions for the agent only.

Does Commodity Cycle Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Commodity Cycle Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Commodity Cycle Analysis use?

Commodity Cycle Analysis is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Commodity Cycle Analysis use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Commodity Cycle Analysis?

Skills that share tags, products or a category with Commodity Cycle Analysis: Marketing Os (Yuzzyuk/marketing-os, 538 stars), Revenue Centric Design (heliocosta-dev/revenue-centric-design, 740 stars), Startup Positioning (ferdinandobons/startup-skill, 1.2k stars) and Stanley Druckenmiller Investment (tradermonty/claude-trading-skills, 3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Commodity Cycle Analysis?

byteseek (a GitHub organization) maintains it in byteseek/Mira, which has 275 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 8, 2026.

Source: byteseek/Mira on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.