Run the Tax Surplus / ACB engine (Reg. 5907, per-layer FX, 212-identity reconciliation harness) or its human-gated assurance loop. Use for cross-border tax demos, the FX sign-flip, --check gating, or drifted-workpaper remediation.
Scanned 8/31/2026
Install to Claude Code
npx -y skills add sophonfinance-wq/finance-automation-portfolio --skill surplus --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Surplus?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/sophonfinance-wq-surplus)More formats (shields.io, HTML) on the badges page.
---
name: surplus
description: "Run the Tax Surplus / ACB engine (Reg. 5907, per-layer FX, 212-identity reconciliation harness) or its human-gated assurance loop. Use for cross-border tax demos, the FX sign-flip, --check gating, or drifted-workpaper remediation."
---
# Tax Surplus / ACB Engine
Package `surplus_engine` in `tax-surplus-engine/`. Seed 20240607. Canadian foreign-affiliate surplus pools, distribution waterfall, ACB on capital events only.
## Commands (run from `tax-surplus-engine/`)
```bash
python -m surplus_engine --start 2021 --end 2024 --out out --xlsx
python -m surplus_engine --start 2021 --end 2024 --check # 212 identity checks; exit 1 on any break
python -m surplus_engine.loop --demo --out out # HUMAN-GATED LOOP: settle drifted periods earliest-first
python -m pytest -q # 7,498 tests
```
## Showpieces
- **FX sign-flip**: `out/fx_layer_analysis.md` — USD ACB $0 but per-layer CAD ACB $(660.35); find the flag glyph.
- **Loop demo**: 3 turns lock FY2021-23, breaks 6->4->2->0, verdict FLAG (CAD 107,088.50 adjustments for human review).
## Loop verdicts (`surplus_engine/loop.py`)
`PASS` (0) / `FLAG` (0, material -> human reviews what changed) / `FAIL` (1). Sensor = `reconcile.py` (independent re-derivation); authority = `SurplusEngine.run` on seeded facts. Never invents: settled set is byte-identical to a clean run.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.