メニュー
Operationalize expert methods into corpus, quote bank, triangulated kernel, operator library, and validators. Use when distilling a methodology or mining session history into executable rules.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/oysteinkrog/dotfiles --skill operationalizing-expertiseコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
SOC 職業分類に基づく
| name | operationalizing-expertise |
| description | Operationalize expert methods into corpus, quote bank, triangulated kernel, operator library, and validators. Use when distilling a methodology or mining session history into executable rules. |
Goal: turn tacit method into executable, auditable artifacts.
Use when you only need a stable, parseable methodology (Lemelson-style).
Summary: corpus + quote bank + triangulated kernel + operator library + validators.
Full steps: references/WORKFLOWS.md.
Use when you want multi-agent sessions that compile into structured artifacts (Brenner-style).
Summary: kickoff -> deltas -> deterministic merge + lint -> artifacts.
Full steps: references/WORKFLOWS.md and references/ARTIFACTS.md.
Use when operationalizing your own repeated behaviors into a reusable skill.
If unsure, start with Track A then add Track B only if you need orchestration.
corpus/primary_sources/ with source transcripts or paperscorpus/quote_bank/quote_bank.md with stable anchors + tagscorpus/distillations/{gpt,opus,gemini}/...corpus/specs/triangulated_kernel.md with START/END markerscorpus/specs/operator_library.md with operator cards + prompt modulescorpus/specs/session_kickoff*.md (role prompts or kickoff templates)scripts/validate-corpus.py, scripts/validate-operators.py, scripts/extract-kernel.pyartifacts/ for compiled outputs (if Track B)See references/FORMATS.md (kernel markers, quote bank entries, operator cards, delta blocks).
See references/WORKFLOWS.md for detailed steps.
See references/VALIDATION.md (includes the minimum gate list verbatim).
See references/ANTI-PATTERNS.md (includes the minimum list verbatim).
See references/OUTPUT.md.
references/CORPUS.mdreferences/DISTILLATION.mdreferences/TRIANGULATION.mdreferences/OPERATORS.mdreferences/KICKOFF.mdreferences/ARTIFACTS.mdreferences/VALIDATION.mdreferences/JARGON.mdreferences/ANTI-PATTERNS.mdreferences/CASE-STUDY.mdConsult Fable (primary oracle) for expert second opinions; escalate to GPT-5.6 Sol (via Codex CLI) or GPT-5.5-Pro (via PAL) only for extremely important or complex tasks (always paired with Fable). Use for complex decisions, architecture choices, debugging hard problems, or when user says "consult oracles", "ask the experts", or wants a second opinion.
Run 2x oracle sessions (FOR + AGAINST stances) to validate design decisions, plans, or bead readiness. Default = two Fable subagents; escalate to GPT-5.6 Sol via Codex CLI or PAL 2x GPT-Pro (always paired with Fable) for extremely important or complex validations. Use after design rounds, before implementation, or to challenge architecture decisions.
Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task via `codex exec`, ONLY when the user explicitly asks for Codex to do it. Also covers how to prompt Codex.