{"id":50519390,"url":"https://github.com/Ericyoung-183/alpha-insights","last_synced_at":"2026-06-08T04:00:37.715Z","repository":{"id":346984649,"uuid":"1192426549","full_name":"Ericyoung-183/alpha-insights","owner":"Ericyoung-183","description":"Harness-enforced AI business research skill for Claude Code and Codex Desktop","archived":false,"fork":false,"pushed_at":"2026-06-02T10:49:53.000Z","size":21874,"stargazers_count":25,"open_issues_count":1,"forks_count":8,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-06-02T12:26:03.945Z","etag":null,"topics":["ai-agent","ai-agents","ai-research","ai-workflow","alpha-insights","business-analysis","business-intelligence","claude","claude-code","codex","codex-desktop","competitive-analysis","consulting","due-diligence","framework","market-research","open-source","prompt-engineering","skill","strategy"],"latest_commit_sha":null,"homepage":"https://ericyoung-183.github.io/alpha-insights/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ericyoung-183.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-26T07:50:52.000Z","updated_at":"2026-06-02T10:49:57.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Ericyoung-183/alpha-insights","commit_stats":null,"previous_names":["ericyoung-179/alpha-insights"],"tags_count":16,"template":false,"template_full_name":null,"purl":"pkg:github/Ericyoung-183/alpha-insights","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ericyoung-183%2Falpha-insights","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ericyoung-183%2Falpha-insights/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ericyoung-183%2Falpha-insights/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ericyoung-183%2Falpha-insights/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ericyoung-183","download_url":"https://codeload.github.com/Ericyoung-183/alpha-insights/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ericyoung-183%2Falpha-insights/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34047266,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agent","ai-agents","ai-research","ai-workflow","alpha-insights","business-analysis","business-intelligence","claude","claude-code","codex","codex-desktop","competitive-analysis","consulting","due-diligence","framework","market-research","open-source","prompt-engineering","skill","strategy"],"created_at":"2026-06-03T03:00:21.036Z","updated_at":"2026-06-08T04:00:37.710Z","avatar_url":"https://github.com/Ericyoung-183.png","language":"Python","funding_links":[],"categories":["Domain-Specific Skills","📊 Data \u0026 Analysis"],"sub_categories":["Compliance \u0026 Auditing"],"readme":"# Alpha Insights-BizAdvisor\n\n\u003e **Elite analyst methodology and frameworks, coded into a SKILL**\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-blue)](https://claude.ai/code)\n[![Codex Desktop](https://img.shields.io/badge/Codex%20Desktop-Skill-111111)](https://github.com/openai/codex)\n\n![Alpha Insights](assets/poster_en.png)\n\n---\n\n## What is Alpha Insights?\n\nAlpha Insights is a professional business analysis AI assistant for Claude Code compatible runtimes and Codex Desktop. It produces in-depth, decision-ready research reports — the kind a senior analyst would deliver.\n\n### Why this is not just prompts\n\nAlpha Insights enforces the research workflow with runtime checks, not only instructions:\n\n- `html_write_guard` prevents premature report writing before required artifacts are ready.\n- Stage gates validate each research stage, including the Stage 3.5 interview gate.\n- `resume_check` catches broken or inconsistent run state before continuing.\n- Progress logging and persisted artifacts make long research runs auditable instead of ephemeral.\n\n**Why Alpha Insights?**\n\n| Typical AI Analysis | Alpha Insights |\n|---------------------|----------------|\n| Generic, surface-level | **Framework-driven** — 19 professional analysis frameworks |\n| No source tracing | **Evidence chain** — every conclusion tagged with source \u0026 confidence |\n| Single data source | **Multi-track parallel** search with triangulation |\n| One-shot output | **Interactive iteration** — progressively deeper insights |\n| Skips steps silently | **Harness-enforced** — script-based gates, not just prompt instructions |\n\n### See It in Action\n\n\u003e **[View Demo Report (HTML)](https://ericyoung-183.github.io/alpha-insights/assets/demo-report.html)** — A competitive analysis of China's EV charging industry.\n\u003e Compact public demo with executive summary, Porter's Five Forces, competitive positioning charts, evidence-graded findings, and strategic recommendations — generated in one session. It is a Tier 2 topic-brief sample, not a full Tier 3 deep report.\n\n\u003e **[Read the V4.1 launch note](https://ericyoung-183.github.io/alpha-insights/launch.html)** — Why Alpha Insights treats serious AI research as a harness-enforced workflow, not another prompt pack.\n\n**Core Value**:\n- **L1 Efficiency Replacement**: Save 60%+ desk research time\n- **L2 Capability Surpass**: Methodology-driven output on par with senior analysts\n- **L3 Experience Compound**: Every research compounds into knowledge assets\n\n### V4: Harness Engineering\n\nPrompt instructions are probabilistic — AI tends to skip steps as context fills up. V4 invests in the **execution environment** instead of just prompts:\n\n- **State machine** — tracks research stage, tier, loaded frameworks, interview status\n- **7-stage + Stage 3.5 gate validators** — auto-check deliverables before advancing (PASS/FAIL/WARN)\n- **Evidence \u0026 Numeric Integrity Gate** — blocks stale entity claims, weak-source strong recommendations, and unlinked headline/chart numbers\n- **Hook automation** — HTML write guard, auto gate checks, incremental file persistence\n- **Dual-platform adapters** — native frontmatter hooks for Claude Code compatible runtimes, Codex wrappers for Codex Desktop\n- **Quality dashboard** — one-screen overview of all quality metrics before report generation\n\n---\n\n## Features\n\n### Thinking OS — 9 Methodologies\n\nMECE | Issue Tree | Hypothesis-Driven | Pyramid Principle | Triangulation | Pre-Mortem | First Principles | ACH (Analysis of Competing Hypotheses) | Expert Interview\n\n### Research Frameworks — 19\n\n**Original**:\n- ★ 3A-8 Steps Strategy — End-to-end methodology from industry landscape to strategic convergence\n\n**Classic**:\n- Strategy: Porter's Five Forces, Value Chain, SWOT, PESTEL, BCG Matrix\n- Business Model: Business Model Canvas, Platform Canvas, Unit Economics\n- Market: TAM/SAM/SOM, Competitive Positioning, Industry Lifecycle\n- Innovation: Disruption Theory, Blue Ocean Strategy, Jobs-to-be-Done\n- Planning: Playing to Win, Three Horizons, Flywheel, SCP\n\n### 10 Research Scenarios\n\n| Scenario | Coverage |\n|----------|----------|\n| 🎯 Industry Research | Market size, growth drivers, value chain, key players |\n| ⚔️ Competitive Analysis | Landscape, rival strategies, differentiation, response |\n| 📱 Product Analysis | Features, UX, comparison, positioning, iteration |\n| 💼 Business Model | Model teardown, revenue logic, unit economics |\n| 🔍 Opportunity Discovery | Value gaps, unmet needs, emerging trends |\n| 🌍 Market Entry | New market feasibility, entry path, go-to-market |\n| 💰 Investment Decision | Due diligence, valuation, investment thesis |\n| 📈 Strategic Planning | Annual/3-year plan, goals, roadmap |\n| 🔒 Due Diligence | Risk review, compliance, background check |\n| ❓ Ad-hoc Advisory | Policy impact, trend analysis, event assessment |\n\n---\n\n## Quick Start\n\n### Install\n\n**Recommended — ask your AI coding agent**:\n\n```text\nInstall Alpha Insights from this repository. Follow INSTALL_FOR_AGENTS.md exactly.\n```\n\n**Codex Desktop direct install**:\n\n```bash\ngit clone https://github.com/Ericyoung-183/alpha-insights.git\ncd alpha-insights\npython3 scripts/install_codex.py --verify\n```\n\n**Claude Code compatible install**:\n\nInstall this repository as the `alpha-insights` skill package. For the standard\nClaude Code skill directory:\n\n```bash\ngit clone https://github.com/Ericyoung-183/alpha-insights.git\nmkdir -p ~/.claude/skills\nrm -rf ~/.claude/skills/alpha-insights\ncp -R alpha-insights ~/.claude/skills/alpha-insights\npython3 ~/.claude/skills/alpha-insights/scripts/verify_cloudcode.py --skill-root ~/.claude/skills/alpha-insights\n```\n\nKeep the root `SKILL.md` frontmatter hooks intact. If your runtime uses a\ndifferent skill root, copy the same package directory there and run the verifier\nwith that path.\n\n### Usage\n\nAfter installation, ask a business analysis question:\n\n```\nUser: Analyze the competitive landscape of the EV charging industry in China\n```\n\nAlpha Insights will automatically:\n1. Identify the research scenario (Competitive Analysis)\n2. Select matching frameworks (Porter's Five Forces + Competitive Positioning)\n3. Run multi-track parallel data search\n4. Generate a structured HTML research report\n\n---\n\n## Data Source Configuration\n\n### 🟢 Works Out of the Box\n\n| Source | Description | How |\n|--------|------------|-----|\n| **Public channels** | Industry reports, analyst research, filings, news, policy docs | Search engine + web scraping |\n| **Expert interviews** | Custom interview guides, recording templates, analysis guidance | Built-in methodology |\n\n### 🟡 Optional Extensions\n\n| Source | Description | Required Setup |\n|--------|------------|----------------|\n| **Xiaohongshu (RedNote)** | Consumer sentiment, product feedback, trend signals | Public web search or a separately installed private adapter; the GitHub package does not bundle provider-specific collection scripts |\n| **Knowledge base** | Historical reports, industry notes | Knowledge-base CLI, Notion connector, or another available knowledge-base tool |\n| **Internal data** | Business metrics, user behavior | Available database or data warehouse tool |\n\n\u003e Unconfigured data sources are automatically skipped — core functionality is not affected.\n\n#### Internal Data Setup\n\nSQL examples in SKILL files use `{project}.{table_name}` placeholders. Once you configure a database or data-processing tool, the AI will discover available tables through the current environment's table search/query capability — no manual replacement needed.\n\n---\n\n## Directory Structure\n\n```\nalpha-insights/\n├── SKILL.md              # Main file (workflow orchestration, V4.1.4)\n├── INSTALL_FOR_AGENTS.md # Agent-first installation contract\n├── CHANGELOG.md          # Version history\n├── README.md             # This file\n├── frameworks/           # 19 analysis frameworks\n│   ├── _index.md         # Framework routing table\n│   ├── 3a_8steps_strategy.md\n│   ├── porters_five_forces.md\n│   └── ...\n├── methodology/          # 9 methodologies\n│   ├── mece.md\n│   ├── hypothesis_driven.md\n│   └── ...\n├── resources/            # Execution resources (Stage 3-5 input)\n│   ├── data_sources.md\n│   ├── research_engine.md\n│   ├── judgment_rules.md\n│   ├── quality_review.md # Independent Quality Review (IQR)\n│   └── anti_patterns.md\n├── references/           # Report standards (Stage 6-7 output)\n│   ├── report_standards.md\n│   └── report_template.html\n└── scripts/\n    ├── install_codex.py  # Codex Desktop installer\n    ├── verify_codex.py   # Codex Desktop verifier\n    ├── verify_cloudcode.py # Claude Code compatible verifier\n    ├── report_helper.py  # ReportBuilder for HTML generation\n    ├── codex_hooks/      # Codex hook wrappers\n    ├── harness/          # V4 Harness Engineering\n    │   ├── state_manager.py\n    │   ├── stage_gate.py\n    │   ├── dashboard.py\n    │   ├── resume_check.py\n    │   ├── validators/   # 7-stage + Stage 3.5 gate validators\n    │   └── hooks/        # automation hooks\n```\n\n---\n\n## Sample Output\n\nReports generated by Alpha Insights follow this structure:\n\n```\n📊 Research Report\n├── Executive Summary (1 page)\n├── Key Findings (3-5)\n├── Detailed Analysis\n│   ├── Industry Overview\n│   ├── Competitive Landscape\n│   ├── Key Player Profiles\n│   └── Opportunities \u0026 Risks\n├── Strategic Recommendations\n└── Appendix\n    ├── Source List (A/B/C/D graded)\n    └── Evidence Base\n```\n\n**Data Quality Grading**:\n\n| Grade | Standard | Confidence |\n|-------|----------|------------|\n| A | 3+ independent sources cross-validated | ✅ High |\n| B | 2 sources cross-validated | ⚠️ Moderate |\n| C | Single authoritative source | ⚠️ Suggest further validation |\n| D | Single source, questionable reliability | ❌ Reference only |\n\n---\n\n## Contributing\n\nContributions welcome!\n\n1. Fork the repo\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n**Areas to contribute**:\n- New analysis frameworks\n- Methodology improvements\n- Additional data source adapters\n- Test cases\n\n---\n\n## License\n\nMIT License\n\n---\n\n## Acknowledgments\n\n**Classic frameworks by**:\n- Michael Porter (Five Forces, Value Chain)\n- Boston Consulting Group (BCG Matrix)\n- McKinsey \u0026 Company (Three Horizons, Hypothesis-Driven)\n- Clayton Christensen (Disruption Theory, JTBD)\n- Jim Collins (Flywheel)\n- Alexander Osterwalder (Business Model Canvas)\n\n---\n\n**Author**: Eric Young\n**Original framework**: ★ 3A-8 Steps Strategy\n**Core philosophy**: Encode methodology into code\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEricyoung-183%2Falpha-insights","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEricyoung-183%2Falpha-insights","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEricyoung-183%2Falpha-insights/lists"}