본문으로 건너뛰기
cccskills
무료GitHub에 공개

cognitive-compile

Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept note.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Mark393295827/third-brain-v7-skills스타 141(GitHub 141 + cccskills 0)
연동 도구Obsidian

실행 점수 미검증

설치 방법 보기

포함된 파일(1)

  • SKILL.md3.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Cognitive Compile

<skill_contract> <input>Source-grounded material, original question, learning or decision goal, audience, and destination.</input> <output>An eight-part evidence-aware mental model separating facts, mechanisms, conflicts, hypotheses, decisions, and action.</output> <done>Each material claim retains provenance and uncertainty, and one bounded next action answers the original question.</done> <non_goals>Inventing missing claims, erasing contradictions or provenance, or treating interpretation as source fact.</non_goals>

Compile information into a decision-ready mental model. Compression must preserve provenance, uncertainty, contradiction, and the original question.

Usage Template

Provide: source material, original question, intended decision or learning goal, and preferred destination. Optional: existing wiki concepts to compare.

Workflow

<intake>

Identify the source boundary, original question, audience, and required fidelity. Label direct source claims, external facts, and analyst inferences before synthesis.

</intake>

<unknowns_gate>

If the source is inaccessible, truncated, or missing the material needed to answer the question, return INSUFFICIENT_EVIDENCE. Ask one probe only when its answer changes the compile structure; otherwise proceed with explicit unknowns.

</unknowns_gate>

<execute>

Produce eight compact sections:

  1. Original question — the problem the material helps answer.
  2. Key facts — source-grounded claims with locators when available.
  3. Concepts and entities — stable terms worth linking.
  4. Patterns — mechanisms, feedback loops, or recurring structures.
  5. Conflicts — contradictions with the source, prior knowledge, or internal claims.
  6. Hypotheses — falsifiable interpretations, explicitly labeled.
  7. Decision support — options, tradeoffs, and what the evidence changes.
  8. Action — one bounded next test, note, or decision.

Prefer one durable concept note over several thin notes. Preserve source links or block references; do not rewrite immutable source notes.

</execute> <evaluate>

Verify that every material conclusion traces to evidence or is labeled inference; the original question is answered; contradictions remain visible; and the action follows from the model. Remove summaries that merely restate the source without changing understanding.

</evaluate>

Failure Protocol

  • NEEDS_INPUT: the intended question or audience is absent and materially changes the output.
  • INSUFFICIENT_EVIDENCE: the source cannot support the requested compile.
  • VERIFY_FAILED: a conclusion lacks traceable evidence; downgrade it to hypothesis or remove it.

Output Contract

Return status, result (the eight-section compile), evidence (source locators), unknowns, and next_action.

Edge Cases

  • Two sources disagree: preserve both claims, compare evidence quality, and state what observation could resolve the conflict.
  • The source is mostly opinion: compile mechanisms and assumptions, but do not promote assertions into facts.

Success Metrics

  • The result answers one explicit question with traceable evidence.
  • Facts, conflicts, and hypotheses are distinguishable at a glance.
  • At least one decision or test becomes clearer.

Quality Gates

  • Source boundary and provenance are explicit.
  • All eight sections are present or marked not applicable with reason.
  • No hypothesis is phrased as established fact.
  • The next action is bounded and verifiable.

</skill_contract>

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

Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command scaled from 5 to 100+ agents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Mark393295827/third-brain-v7-skills1412026년 9월 19일 업데이트

Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Mark393295827/third-brain-v7-skills1412026년 9월 19일 업데이트

Use when property-service operations need an AI plus ontology plus DMAIC design for work orders, dispatch, quotes, evidence, CTQ metrics, and control dashboards.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Mark393295827/third-brain-v7-skills1412026년 9월 19일 업데이트

Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocation, 3B creativity, experiments, and prediction-error learning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Mark393295827/third-brain-v7-skills1412026년 9월 19일 업데이트

Use when a goal must be converted into a repeatable behavior, cue, SOP, review cadence, and identity-aligned reinforcement.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Mark393295827/third-brain-v7-skills1412026년 9월 19일 업데이트

Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based model routing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Mark393295827/third-brain-v7-skills1412026년 9월 19일 업데이트

Mark393295827의 스킬 모두 보기

이 스킬의 문제 신고