lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 8 (Mode A) — Generate the Mode A Quick Briefing HTML file from analysis-result.json. Triggered by: CLAUDE.md after Analyst Agent (Step 7) completes for Mode A Reads: run-local analysis-result.json Writes: output/reports/{ticker}A{lang}{YYYY-MM-DD}.html References: references/analysis-framework-briefing.md…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 8 — Generate the Mode C HTML dashboard from analysis-result.json. Triggered by: CLAUDE.md when outputmode = "C" after Step 7 (Analyst Agent completes analysis) Reads: run-local analysis-result.json, references/html-template.md, references/color-system.md Writes…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 10 (post-analysis persistence) + Workflow 3 (portfolio & watchlist management) Triggered by: CLAUDE.md after Step 9 (quality check) for persistence; directly for Workflow 3 commands Reads: run-local analysis-result.json, optional run-local evidence-pack.json, optional run-local context-budget.json…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 5 — Validate all collected data through 3-layer fact-checking, assign confidence grades, build the evidence pack, measure Analyst context budget, and enforce the Blank-Over-Wrong principle. Triggered by: CLAUDE.md after Step 4 (web researcher) Reads: output/runs/{runid}/{ticker}/tier1-raw.json (Enhanced)…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
A tool that checks whether a stock is within the period around its next earnings announcement, classifying it as preview, review, or neither.
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 3 — Execute Financial Datasets MCP and FMP MCP API calls to collect structured financial data. Enhanced Mode only. Triggered by: CLAUDE.md when datamode = "enhanced" after Step 2 Reads: run-local research-plan.json, references/api-endpoints.md Writes: output/runs/{runid}/{ticker}/tier1-raw.json References…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 2 — Detect MCP availability, determine data mode (Enhanced/Standard), classify company type, identify peers, initialize a run-local artifact root, and write the research plan. Triggered by: CLAUDE.md after Step 1 (query interpretation) Reads: Session state from Step 1…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 8 — Generate the final analysis output in the requested mode (A, B, C, D). Mode A delegates to briefing-generator; Mode B uses scripts/render-comparison.py; Mode C delegates to dashboard-generator; Mode D uses scripts/docx-generator.py. Triggered by: CLAUDE.md after Analyst Agent (Step 7) completes Reads…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 9 — Perform output-facing quality checks and rebuild the deterministic run-local quality report before delivery to user. Auto-patch minor issues; flag persistent failures inline. Triggered by: CLAUDE.md after Step 8 (output generation), before final delivery Reads: Generated output file (or inline…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 1 — Parse the user's query to extract ticker(s), determine output mode, detect language, and validate intent. Triggered by: CLAUDE.md after Step 0 determines fresh collection needed Reads: User query, references/ticker-resolution-guide.md Writes: Sets session variables: ticker, market, outputmode…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 0 — Evaluate whether existing snapshot data is fresh enough to reuse, or whether new data collection is required. Triggered by: CLAUDE.md at the start of Workflow 1 (Single Stock Analysis) and Workflow 3 (Watchlist Scan) Reads: output/data/{ticker}/latest.json, staleness rules from this file Writes: Nothing…
lowtidebuild/public-equity-research
Skill Claude CodeCodex
Role: Step 4 — Collect qualitative context and fill data gaps via web search and direct URL fetch. Triggered by: CLAUDE.md after Step 3 (Enhanced Mode) or Step 2 (Standard Mode) Reads: run-local research-plan.json, tier2 search list, references/us-data-sources.md or references/kr-data-sources.md Writes…
lowtidebuild/public-equity-research
MCP server Claude CodeCodexCursor +2
MCP server "financialdatasets", hosted remotely at mcp.financialdatasets.ai, as configured in lowtidebuild/public-equity-research.
lowtidebuild/public-equity-research
Instructions file CodexOpenCode
Instructions for lowtidebuild/public-equity-research, covering codex harness entry, operating contract, primary commands, claude-to-codex tool mapping and environment variables.
lowtidebuild/public-equity-research
Instructions file
Instructions for lowtidebuild/public-equity-research, covering stock analysis agent — master orchestrator, section 1 — identity & mission, section 2 — session start protocol, mcp detection (run once, cache for session) and session state block (display at start).
lowtidebuild/consolidated-legal-research
Settings file Claude Code
Agent settings declaring 4 allowed tools.
lowtidebuild/consolidated-legal-research
MCP server Claude CodeCodexCursor +2
A local MCP server for researching Korean law through 42 government APIs. It covers statutes, court decisions, local ordinances, treaties, tax interpretations, time-based comparisons, and guided legal research.
lowtidebuild/consolidated-legal-research
MCP server Claude CodeCodexCursor +2
Parse Korean documents (HWP3-5, HWPX, HWPML, PDF, XLS(X), DOCX) to Markdown — CLI + MCP server with lossless patch/roundtrip, form-filler, document diff, print & layout-preserving SVG renderer. Runs locally from the kordoc npm package.
lowtidebuild/consolidated-legal-research
Instructions file
Claude Code instructions for lowtidebuild/consolidated-legal-research, covering legal agent orchestrator, workflow, step 1: intake and case id, step 2: classify the question and select agents and step 3: dispatch agents.
Command Claude Code
This command routes to Workflow 2 (Contract Review Pipeline). The single authoritative SOP is .claude/agents/review-agent/AGENT.md — do NOT perform the review inline in this session. Your job here is: locate the target, load baselines, and dispatch the review-agent with an explicit session id.
Command Claude Code
You are a contract drafting specialist preparing a contract for the client. The user will describe the contract they need and provide deal context.
Command Claude Code
Strip all [INTERNAL]-prefixed comments from a redlined DOCX to produce a version safe for counterparty delivery.
Command Claude Code
You are ingesting documents into the contract review library. The user has placed source files in contract-review/library/inbox/raw/.
Command Claude Code
You are managing the contract review library. Execute the requested library operation.