본문으로 건너뛰기
cccskills
무료GitHub에 공개

decision-framework-invoker

Triggers for automatically invoking the decision-framework skill before irreversible or high-blast-radius operations. Use as a checkpoint: when a proposed action matches a trigger pattern, pause and run the appropriate framework (first-principles, inversion, decision matrix, second-order thinking) before proceeding. Prevents ad-hoc calls from becoming regret.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md4.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Decision Framework Invoker

The decision-framework skill provides thinking frameworks (First Principles, 5 Whys, Eisenhower, Pareto, Inversion, Second-Order, Decision Matrix). This invoker skill captures when to use it — the trigger patterns that should prompt a pause-and-frame before proceeding.

Trigger Patterns

Invoke a decision framework when the proposed action matches any of these:

Irreversibility

  • Destructive git operations: push --force, reset --hard, branch -D
  • Committing generated content to a shared repo (N files where N > 100)
  • Applying a schema migration to a production DB
  • Sending a message (Slack, email, PR comment) that cannot be recalled

→ Framework: Inversion ("what's the worst outcome; can we back out?")

Blast Radius

  • Changes affecting multiple packages / projects
  • Renaming public APIs, CLI flags, config keys
  • Removing a feature that has downstream consumers
  • Rewriting > 1,000 lines across a codebase

→ Framework: Second-Order Thinking ("what does this cause, and what does that cause?")

Multi-Option Judgment Calls

  • Choosing between 3+ architectural paths
  • Picking a library/framework with long-tail commitment
  • Prioritizing between competing feature requests

→ Framework: Decision Matrix (columns = options, rows = weighted criteria)

Root Cause Debugging

  • A bug has returned after being "fixed"
  • A pattern keeps recurring across unrelated work
  • A test failure has non-obvious cause

→ Framework: 5 Whys (keep asking until you hit the infrastructural cause)

Scoping Ambition

  • Feature spec has 20+ items; need to prioritize
  • Time-boxed session; need to pick highest-leverage work

→ Framework: Pareto 80/20 ("which 20% delivers 80% of value?")

Reframing Stuck

  • Been spinning on an approach that isn't working
  • Assumptions feel embedded but might not be true

→ Framework: First Principles (strip to the problem; rebuild from truths)

Invocation Shape

When a trigger fires:

  1. Name the trigger in plain language: "About to commit 1,881 generated chapter files — this is the blast-radius: committing generated content trigger."
  2. Pick the framework from the mapping above.
  3. Apply it in-line in the conversation — usually 3-5 sentences is enough to surface the tradeoff.
  4. Record the decision via observe.mjs event decision <label> <payload> so the retrospective captures it.
  5. Proceed with eyes open, or adjust the approach.

Example — The 1,881-File Publish (v1.49 release-history work)

Trigger: "About to commit 1,881 auto-generated markdown files into docs/release-notes/v*/chapter/."

This hit two trigger categories:

  • Blast radius: large diff affecting 1,881 files
  • Irreversibility-ish: git commit is reversible, but reverting a commit that size is painful

Framework applied (Inversion):

  • Worst case: "These files are regenerable from the DB. If we commit them and hate the shape, we can rm -rf and regenerate. Cost: a revert commit."
  • Best case: "Anyone browsing the repo on GitHub can read chapters without running the pipeline."
  • Hidden third option: "Commit only the top-level index files (STORY.md, INDEX.md) and leave per-chapter files local."

Decision: commit all 1,881. Rationale: regenerable, reviewable on GitHub, user asked. Recorded via observe.mjs event decision.

What This Skill is NOT

  • A mandatory gate — you don't need a framework for every tool call
  • A substitute for doing the work — frame the decision, then act
  • A bureaucratic checklist — most triggers take 30 seconds to resolve

Related

  • decision-framework — the actual frameworks this skill invokes
  • session-observatory-live — record the decision via observe.mjs

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Provides web accessibility best practices for semantic HTML, ARIA, keyboard navigation, color contrast, and screen reader patterns. Use when building UI components, reviewing accessibility, or when user mentions 'a11y', 'accessibility', 'ARIA', 'screen reader', 'keyboard navigation', 'WCAG'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Active listening techniques for effective communication. Covers attending behaviors, paraphrasing, reflective listening, clarifying questions, empathic response, barriers to listening, listening in conflict, and cross-cultural listening. Use when building listening skills, improving understanding in conversation, mediating disputes, or analyzing communication breakdowns.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Adversarial spec-compliance PR review — cross-references diffs against approved specs, verifies runtime claims against source, detects competing PRs, audits scope/convention compliance. Use before merging.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Provides best practices for AI agent orchestration including MCP servers, A2A protocol, multi-agent coordination, and swarm architectures. Use when designing agent systems, configuring MCP servers, setting up agent teams, or when user mentions 'MCP', 'A2A', 'agent orchestration', 'multi-agent', 'swarm', 'agent team', 'LangGraph', 'CrewAI', 'AutoGen'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Symbolic manipulation, equation solving, and algebraic structures for mathematical reasoning. Covers distributive law, factoring, completing the square, linear through polynomial equation solving, systems of equations (substitution, elimination, Gaussian elimination, matrix methods), algebraic structures (groups, rings, fields), modular arithmetic, polynomial theory, and inequalities. Use when solving equations, simplifying expressions, working with algebraic structures, or performing symbolic manipulation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Understanding how algorithmic systems shape what users see, know, and do -- from recommendation feeds to search ranking to credit scoring to hiring software. Covers the mechanics of recommendation systems, algorithmic bias and its sources, personalization's effects on information diets, opacity and accountability, AI limitations (hallucination, confident wrongness), and the human-in-the-loop question. Use when a learner needs to think critically about why particular content reached them.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tibsfox/gsd-skill-creator712026년 7월 20일 업데이트

Tibsfox의 스킬 모두 보기

이 스킬의 문제 신고