Parallax Earnings Quality

Earnings Quality Analysis

When not to use

• General stock analysis → use /parallax-deep-dive
• Full due diligence → use /parallax-due-diligence
• Quick stock check → use /parallax-should-i-buy

Gotchas

• JIT-load _parallax/parallax-conventions.md for RIC resolution, parallel execution, and fallback patterns
• getfinancialanalysis (Palepu framework) is async ~2-5 min — this is the core of the forensic analysis
• Quality score of 10 doesn't mean no risk — dig into sub-components
• Cross-reference news for context on any red flags found
• Focus output on actionable risk flags, not comprehensive financial review
• JIT-load _parallax/white-label/integration-pattern.md before the Pre-Render step. Loader call is load_visual_branding() (7-key visual subset; voice structurally excluded — branding["voice"] raises KeyError). Apply §5 (Branding Header) and §7 (About This Report) in Output Format.

Usage

/parallax-earnings-quality AAPL.O
/parallax-earnings-quality 7203.T "concerned about revenue recognition"

Workflow

Execute using mcp__claude_ai_Parallax__* tools. JIT-load _parallax/parallax-conventions.md for execution mode, RIC resolution, and fallback patterns.

Batch 0 — Tool Loading

Call ToolSearch with query "+Parallax" to load the deferred MCP tool schemas before the first mcp__claude_ai_Parallax__* call.

Batch A — Data gathering (parallel)

Fire all simultaneously:

| Tool | Parameters | Notes | |---|---|---| | get_score_analysis | symbol | Quality score trajectory (default 52-week lookback) | | get_financials | symbol, statement="income" | Revenue/margin trends (default 4 periods) | | get_financials | symbol, statement="cash_flow" | Cash conversion (default 4 periods) | | get_financials | symbol, statement="ratios" | Accrual ratios | | get_financial_analysis | symbol | Async ~2-5 min — Palepu forensic analysis | | get_news_synthesis | symbol | Async — accounting news, auditor changes |

Batch B — AI synthesis (after Batch A)

Call get_assessment with a prompt focused on: earnings quality concerns, revenue recognition patterns, accrual anomalies, cash flow vs. earnings divergence, and any specific concerns the user raised. Feed in all findings from Batch A.

Output Format

• Risk Summary (red/yellow/green traffic light for overall earnings quality)
• Quality Score Trend (52-week trajectory with inflection points flagged)
• Forensic Findings (from Palepu analysis — accruals, revenue quality, cash conversion)
• Red Flags (specific items that warrant investigation)
• News Context (any accounting-related developments)
• AI Assessment (synthesized risk opinion)
• Recommended Actions (what to monitor, what warrants deeper investigation)
• Branding Header (only if white_label_active AND client_name != "") — single line at the very top: **** earnings quality review. Logo handling per integration-pattern.md §5.
• About This Report (always present): one line stating branding state per integration-pattern.md §7. If a logo was skipped, append Logo on file: as a second About This Report line.

Pre-Render — Load white-label branding

Load _parallax/white-label/integration-pattern.md §2 and compute white_label_active + client_name per that section. Apply §5 (Branding Header) and §7 (About This Report) when composing the Output Format.

AI-interaction disclosure (required regardless of view state): Render parallax-conventions.md §9.2 immediately above the disclaimer below.

Render the standard disclaimer verbatim from parallax-conventions.md §9.1.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: bencharoenwong
• Source: bencharoenwong/parallax-workflows
• License: MIT

Install and usage instructions live in the source repository linked above.