メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | reviewer |
| description | 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. |
| version | 1.0.0 |
| allowed-tools | All |
| capability_type | skill |
| harness_targets | ["claude-code","opencode","hermes","b00t-cli"] |
Canonical reviewer capability for the b00t hive. Applies MECE structural decomposition, TRIZ contradiction analysis, and Eureka insight search to code, datums, and system configs. Produces machine-parseable verdicts (APPROVE/REQUEST_CHANGES) suitable for pre-commit gates, PR review, and governance enforcement.
| Harness | How It Loads | File |
|---|---|---|
| b00t-cli | b00t learn reviewer | This SKILL.md |
| Claude Code | b00t whoami --role=reviewer | AGENTS/--role=reviewer.md (thin wrapper) |
| opencode | Native skill load | This SKILL.md |
| Hermes | Skill bundle | references/ this directory |
VERDICT: APPROVE
or
VERDICT: REQUEST_CHANGES
Preceded by brief justification (1-3 lines). No markdown after VERDICT.
| Script | Purpose |
|---|---|
| system-normal.rhai | Precriteria gate — git stash, conflicts, branch, submodules |
| autoexec.rhai | Autonomous review loop — poll queue → dispatch → post → repeat |
_b00t_/reviewer.role.toml — role datum with capabilities, sub-agents, compliance rules_b00t_/multi-framework-review.datum.toml — 7-phase state machine_b00t_/datum-review.datum.toml — datum-specific review skill_b00t_/pr-risk-scorer.datum.toml — PR risk tier routingb00t script run, b00t task list, b00t agent delegate)b00t script eval)1.0.0 — Initial canonical reviewer skill. Replaces scattered role supplements with single source of truth. All harnesses reference this canonical capability.
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.
ISO and IFRS accounting standards used in the Tax-Lawyer Platform: ISO 20022 (financial messaging), IFRS 9 (financial instruments), LEI (ISO 17442), and ISO 4217 (currency codes). Grounds monetary domain objects in formal standards.