Menu
Six Sigma: reduce defects to 3.4 per million by eliminating variance.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Canonical b00t reviewer capability — adversarial multi-framework code/datum review. Shared across all harnesses (Claude Code, opencode, Hermes, b00t-cli). Loaded via: b00t learn reviewer, or by harness-specific role supplements.
Remove AI-generated artifacts from code. Three-phase certainty-graded cleanup. Use after any AI implementation session or before PR creation.
8-phase agile workflow — strategy→ideate→brainstorm→plan→work→review→compound→pulse. State machine with FOL-guarded transitions, gh-issues backlog, executable just harness. Inspired by everyinc/compound-engineering-plugin.
Australian crypto tax treatment per ATO guidance QC 53725. Crypto assets are CGT assets under ITAA 1997 s 108-5. Each disposal triggers CGT event A1. Covers personal-use exception, trading stock test, and the 50% CGT discount.
Australian R&D Tax Incentive (RDTI) — ITAA 1997 Division 355. Covers eligibility criteria for core and supporting R&D activities, registration with AusIndustry/IP Australia, expenditure categories, offset rates, and the company size threshold test.
Evidence graph construction for tax audit trails. Each Satisfies check emits EvidenceNode structs with Blake3 content hashes. Evidence chains are tamper-evident and link legislative citations to factual findings.
| name | six-sigma |
| type | skill |
| hint | DMAIC — Define, Measure, Analyze, Improve, Control; reduce variance via data-driven decisions |
| version | 1.0.0 |
| tags | ["transferable","dmaic","six-sigma","variance","quality","data-driven","control","defect","sigma"] |
| tier | sm0l |
| complexity | 4 |
| description | Six Sigma: reduce defects to 3.4 per million by eliminating variance. |
Six Sigma aims to reduce defects to 3.4 per million by eliminating variance through the DMAIC cycle. The five phases are: (1) Define — what is the problem? what is the target state? who is affected? (2) Measure — collect baseline data. No guessing, no anecdote. (3) Analyze — find root cause using fishbone, 5-whys, or Pareto analysis. Do not fix symptoms. (4) Improve — implement targeted solution. Pilot first, measure impact. (5) Control — lock in the gain. Add monitoring and set triggers to catch regression.
The key rule: never skip Measure — improving an unmeasured process is theater. In code, DMAIC maps to: define acceptance criteria → measure test coverage → analyze failure modes → improve code → add CI gates.
Apply DMAIC when improving a process, reducing error rates, or addressing quality issues. Use it whenever you need a data-driven approach to process improvement rather than intuition-based changes.
