{"id":"bcacefe2-ca50-4d43-a38c-1382b3ceb114","slug":"profit-atlas","kind":"skill","name":"profit-atlas","summary":"Agent skills for researching industry profit pools and company value chains.","owner":"Cheerfay","repoUrl":"https://github.com/Cheerfay/profit-atlas","license":"MIT","licenseTier":"permissive","trust":"community","stars":7,"match":null,"fewStars":false,"format":"skill","createdAt":"2026-10-22T16:34:24.000Z","addedAt":"2026-11-01T02:03:23.131Z","logoUrl":"https://avatars.githubusercontent.com/u/116006049?u=e78618c9935bc188f048fc1025bfc37a636a55ea&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["data-analytics"],"tags":["company-analysis","industry-analysis","market-research","value-chain","profit-pools"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-11-01T02:03:34.749Z","sample":false,"url":"https://conduits.dev/tools/profit-atlas","language":"","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Profit Atlas\n\n![Profit Atlas — research the economics beneath the surface](assets/social-preview.png)\n\n**Find where an industry or company actually makes money — and show the evidence.**\n\nProfit Atlas is a small, evidence-first collection of Agent Skills for research that starts in one of two places:\n\n| Start with | Skill | It helps answer |\n|---|---|---|\n| An industry or value chain | [`industry-profit-pool-research`](skills/industry-profit-pool-research/) | Where do revenue and profit pools sit, why, and which external startup entry points are credible? |\n| A named company | [`company-value-chain-review`](skills/company-value-chain-review/) | What does the company live on, and which operating chain turns value into revenue, profit, and cash? |\n\nThe skills compose, but remain separate: industry profit distribution and company economics need different units of comparison, evidence, and outputs.\n\n[中文说明](README.zh-CN.md)\n\n## See the work, not just the prompt\n\n| Research question | Complete, dated result |\n|---|---|\n| Where do China NEV value-chain profit pools sit, and what could an external founder actually build? | [Automotive profit-pool case](examples/industry/automotive-profit-pool-test-result-en.md) |\n| What does CATL fundamentally live on, and how does value become cash? | [CATL two-layer value-chain review](examples/company/catl-value-chain-review-en.md) |\n\nBoth reports distinguish disclosed facts, calculations, and inference; link primary sources; and state the limits of public data.\n\n## Quick start\n\nThis repository is a **portable Agent Plugin**: its root [`plugin.json`](plugin.json) identifies the package and each reusable workflow lives under [`skills/`](skills/). The layout follows the open Agent Skills convention.\n\n1. Add the public marketplace: `codex plugin marketplace add Cheerfay/profit-atlas`.\n2. Install the plugin: `codex plugin add profit-atlas@profit-atlas`.\n3. Start a new chat and ask a natural-language research question. The installed plugin exposes both Skills for automatic routing between industry-first and company-first questions.\n\nIf your host does not support marketplaces, clone or download this repository and copy either required folder from [`skills/`](skills/) into that host's configured Skills directory.\n\nFor current Codex desktop local-plugin installation, use an official [local marketplace](https://developers.openai.com/plugins/build/plugins/#install-a-local-plugin-manually) and restart the app after installing. The package layout and both Skill manifests were validated in a clean copied-folder check; full automatic activation has **not** yet been tested across every Agent Skills host.\n\n## Ask naturally\n\nThe descriptions are designed for automatic routing. For example:\n\n- “Map the profit pools in China's game industry and identify defensible startup entry points.”\n- “Analyze what BYD fundamentally lives on and how value becomes cash.”\n- “Compare Tencent, NetEase, and 37 Interactive: how do their business models and profit engines differ?”\n\nTo force a route, name the Skill:\n\n- “Use `industry-profit-pool-research` to study the automotive value chain.”\n- “Use `company-value-chain-review` to review Meituan.”\n\n## How the two Skills work together\n\nAn industry study selects representative companies by role or business model to support a profit-pool conclusion. It does not replace a full company review.\n\nWhen a company study needs industry context, run the industry Skill first and then use the company Skill to synthesize two layers:\n\n1. **Company economics:** payer, reason to pay, revenue, core profit, costs, and risks.\n2. **Value-to-cash workflow:** the few operating steps that determine revenue, cost, risk, and trust.\n\n## What the benchmark does—and does not—show\n\n[Benchmark v0.1](evals/profit-atlas-benchmark-v0.1.md) preserves two raw, fresh-context no-Skill baselines alongside the Skill-guided cases. It evaluates explicit value-chain coverage, source traceability, evidence labels, calculation consistency, and conclusion boundaries.\n\nIt is deliberately a two-prompt, author-run process evaluation—not a model leaderboard or a claim that unscripted research cannot be good. The observed advantage is more disciplined structure and evidence boundaries.\n\n## Evidence boundaries\n\n- Company revenue is not automatically comparable with industry sales.\n- Revenue share does not prove profit contribution.\n- Gross profit, operating profit, net profit, and cash flow are kept distinct.\n- Calculations and inference are labeled; undisclosed segment profit is not invented.\n- Startup opportunities are tested for external pain, budget, entry rights, defensibility, and economics. AI may be a core capability, an enhancement, an ordinary feature, or unnecessary—it is not the default answer.\n- Dedicated sector modules improve question coverage but are not required. An unlisted sector uses the general workflow and states missing evidence explicitly.\n\nProfit Atlas is a research framework, not investment advice. Independently verify evidence before making financial or operating decisions.\n\n## Repository map\n\n```text\nskills/       two installable research workflows\nexamples/     complete, sourced research outputs\nevals/        raw baselines and evaluation rubric\nassets/       social-preview artwork\nplugin.json   portable plugin manifest\n```\n\n## Contributing\n\nContributions should preserve the boundary between the two Skills and add an evaluation case for changed behavior. Add a sector module only after repeated real tests reveal a stable, sector-specific question the general workflow misses.\n\nBefore submitting a change, validate the Skill front matter, check every referenced resource, rerun relevant evaluation cases, and scan for private paths or credentials.\n\n## License\n\n[MIT](LICENSE)\n"}