원클릭으로
tomllm-format
.tomllm / .tomllmd = valid TOML + enriched # comment conventions for LLM context.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
.tomllm / .tomllmd = valid TOML + enriched # comment conventions for LLM context.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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 | tomllm-format |
| type | skill |
| hint | TOML+LLM format conventions — valid TOML with enriched |
| version | 1.0.0 |
| tags | ["tomllm","format","tail-map","convention","llm"] |
| tier | sm0l |
| complexity | 3 |
| description | .tomllm / .tomllmd = valid TOML + enriched # comment conventions for LLM context. |
The TOML+LLM format defines conventions for enriching valid TOML with comment annotations optimized for LLM consumption. .tomllm (machine-oriented) and .tomllmd (documentation-heavy) files extend plain .toml with three comment conventions: # @tribal: / # 🤓 for non-obvious knowledge, design rationale, and gotchas; # @example: for usage examples inline with the datum; and # b00t:map v1 as a structured tail-map footer (last ≤10 lines of the file).
The tail-map contains: summary (one-line description, ≤120 chars), tags (comma-separated keywords), tier (sm0l/ch0nky/frontier), cmds (comma-separated relevant commands), and complexity (1-10 integer). The critical rule: the tail-map MUST be the last ≤10 lines of the file — nothing follows it.
Use .tomllmd for documentation-heavy datums like PRDs and schemas. Use .tomllm for machine-oriented configuration datums. Use plain .toml as the fallback. Load this skill when authoring any new b00t datum.
# 🤓 / # @tribal: comments for non-obvious design rationale.# @example: comments for usage examples.# b00t:map v1 as the footer with summary, tags, tier, cmds, complexity.