Tax season throughput constraints

Skill deciqAI/knowledge-skills/tax-season-throughput-constraints

Open-source thinking-framework skills that make rigorous reasoning executable for AI agents — first-principles, inversion, second-order thinking, Occam's razor, Bayesian reasoning. Built by deciqAI.

Install

npx -y skills add deciqAI/knowledge-skills --skill tax-season-throughput-constraints

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Activate when: returns are piling up before a deadline; reviewer/preparer is the bottleneck; 'we can't get through them all,' 'clients waiting on missing docs,' planning staffing for Jan–Apr. Do NOT activate when: off-season, low volume; the issue is a single stuck return (use debugging, not capacity theory). More: deciqai.com/s/tax-season-throughput-constraints

SKILL.md

3.2 KB, 652 tokens by cl100k_base, as published. Nobody here has run it

Tax Prep — Season Throughput (Theory of Constraints)

Industry front door for theory-of-constraints. Adds domain triggers, example, packs only. Parent Process unchanged.

Activate when: returns are piling up before a deadline; reviewer/preparer is the bottleneck; "we can't get through them all," "clients waiting on missing docs," planning staffing for Jan–Apr. Do NOT activate when: off-season, low volume; the issue is a single stuck return (use debugging, not capacity theory).

Why this variant

The parent theory-of-constraints finds the one step that caps total output and subordinates everything to it. In a tax practice the constraint is almost never "preparation" — it's usually the reviewer or client missing-documents. Optimizing anything else is wasted motion during season.

Domain inputs → parent's Process

Pipeline stages: intake → doc-complete → prep → review → e-file.

Measure WIP at each stage; the stage with the growing queue = constraint.
Exploit: protect reviewer time (no admin), pre-triage returns so review is fast.
Subordinate: preparers pace to reviewer capacity, not their own.
Elevate: add reviewer capacity / async review / raise complexity threshold for partner review.

Worked example

80 returns in "prep-done," 6 cl2ear/day through review → 13-day backlog vs 5 days to deadline. → Constraint = review. Exploit: batch simple returns for a fast lane; move partner off prep entirely. Missing-docs is the upstream feeder — a chaser (see onboarding/data-room agents) protects the constraint from starving.

Packs

Solo: one fast-lane vs deep-lane split; cap daily complex intake.
Firm: reviewer-protected calendar; WIP board; extension-triage rule when backlog > days-remaining.

Red flags

Preparers "busy" but review queue growing = optimizing the non-constraint.
Missing-docs starving the constraint (idle reviewer waiting on clients).

Verification

Constraint stage identified by queue growth, not opinion
Non-constraint work subordinated to it
Extension policy triggered when backlog > remaining days
Upstream doc-chaser keeps constraint fed

Part of deciqAI Knowledge Skills. Core method: theory-of-constraints.

Part of deciqAI Knowledge Skills — 233 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. See it run → https://www.deciqai.com/s/tax-season-throughput-constraints · Built by deciqAI · github.com/deciqAI · Contributions welcome.

Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/tax-season-throughput-constraints.json