본문으로 건너뛰기
cccskills
무료GitHub에 공개

bdi-normative-reasoning

Design an agent's handling of obligations, prohibitions, permissions, and conflicts among norms and goals. Use when an autonomous agent must decide which norms apply and what to do when they conflict. NOT for simple fixed policy checks, ordinary BDI commitment design, or organizational metaphor.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy
설치 방법 보기

포함된 파일(37)

  • SKILL.md3.4 KB
  • sources/a-normative-extension-for-the-bdi-agent/_book_identity.json2.7 KB
  • sources/a-normative-extension-for-the-bdi-agent/_raw_response.md95.2 KB
  • sources/a-normative-extension-for-the-bdi-agent/CHANGELOG.md476 B
  • sources/a-normative-extension-for-the-bdi-agent/diagrams/01_flowchart_decision-points.md680 B
  • sources/a-normative-extension-for-the-bdi-agent/diagrams/INDEX.md179 B
  • sources/a-normative-extension-for-the-bdi-agent/references/desire-internalization-as-norm-adoption-mechanism.md10.6 KB
  • sources/a-normative-extension-for-the-bdi-agent/references/maximal-non-conflicting-subsets-for-action-selection.md18.7 KB
  • sources/a-normative-extension-for-the-bdi-agent/references/norm-instantiation-through-belief-grounding.md17.6 KB
  • sources/a-normative-extension-for-the-bdi-agent/references/normative-conflict-resolution-through-consequence-ranking.md11.7 KB
  • sources/a-normative-extension-for-the-bdi-agent/references/separation-of-norm-recognition-and-norm-internalization.md13.3 KB
  • sources/a-normative-extension-for-the-bdi-agent/references/three-types-of-consistency-for-norm-adoption.md14.9 KB
  • sources/a-normative-extension-for-the-bdi-agent/SKILL.md9.1 KB
  • sources/INDEX.md5.8 KB
  • sources/normative-bdi-agent-architecture/_book_identity.json1.8 KB
  • sources/normative-bdi-agent-architecture/_raw_response.md95.2 KB
  • sources/normative-bdi-agent-architecture/CHANGELOG.md975 B
  • sources/normative-bdi-agent-architecture/diagrams/01_flowchart_decision-points.md1.2 KB
  • sources/normative-bdi-agent-architecture/references/desire-internalization-as-norm-adoption-mechanism.md6.1 KB
  • sources/normative-bdi-agent-architecture/references/maximal-non-conflicting-subsets-for-action-selection.md5.9 KB
  • sources/normative-bdi-agent-architecture/references/norm-instantiation-through-belief-grounding.md10.2 KB
  • sources/normative-bdi-agent-architecture/references/normative-conflict-resolution-through-consequence-ranking.md5.6 KB
  • sources/normative-bdi-agent-architecture/references/separation-of-norm-recognition-and-norm-internalization.md5.2 KB
  • sources/normative-bdi-agent-architecture/references/source-boundary-and-authority-trace.md2.0 KB
  • sources/normative-bdi-agent-architecture/references/three-types-of-consistency-for-norm-adoption.md7.7 KB
  • sources/normative-bdi-agent-architecture/SKILL.md15.0 KB
  • sources/normative-bdi-agents/_book_identity.json1.8 KB
  • sources/normative-bdi-agents/_raw_response.md94.9 KB
  • sources/normative-bdi-agents/CHANGELOG.md710 B
  • sources/normative-bdi-agents/references/desire-internalization-as-norm-adoption-mechanism.md6.1 KB
  • sources/normative-bdi-agents/references/maximal-non-conflicting-subsets-for-action-selection.md5.9 KB
  • sources/normative-bdi-agents/references/norm-instantiation-through-belief-grounding.md10.2 KB
  • sources/normative-bdi-agents/references/normative-conflict-resolution-through-consequence-ranking.md5.6 KB
  • sources/normative-bdi-agents/references/separation-of-norm-recognition-and-norm-internalization.md5.2 KB
  • sources/normative-bdi-agents/references/source-boundary-and-authority-trace.md1.8 KB
  • sources/normative-bdi-agents/references/three-types-of-consistency-for-norm-adoption.md7.7 KB
  • sources/normative-bdi-agents/SKILL.md11.6 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

BDI Normative Reasoning

Use this skill when norms are represented as decision-relevant objects, rather than a fixed if statement at an external enforcement boundary.

Decision procedure

  1. Specify each norm's issuer, scope, activation condition, addressee, required or forbidden action, expiry, and enforcement consequence. Keep a recognized Abstract Norm Base (ANB) candidate distinct from a grounded active Norm Instance Base (NIB) instance.
  2. Ground applicability in source-tagged current beliefs; distinguish “not observed” from “known false.” Instantiate only after confirming binding, activation, and non-expiry under a declared reconciliation policy.
  3. Keep norm recognition separate from adoption as a goal or intention. An applicable norm need not be internalized if the design permits refusal.
  4. Detect conflicts among norms and with existing intentions using a joint plan witness. Separate an empty complete plan catalog from incomplete search or unknown effects. Name the chosen resolution criterion: an applicable hard priority, a scoped partial-order comparison, or explicit escalation. Preserve incomparable alternatives.
  5. Produce a decision trace showing applicable norms, rejected alternatives, source authority, search coverage, and the rule used. Keep any local desire update separate from authorization to execute an external effect.
flowchart LR
  B[Beliefs] --> G[Ground norms]
  N[Norm catalog] --> G
  G --> C{Conflict?}
  C -->|no| A[Adopt or comply]
  C -->|yes| R[Resolve by declared policy]
  R --> A
  A --> T[Decision trace]

Boundaries

  • Do not use consequence ranking as a universal conflict resolver. The cited model can leave consequences incomparable; a tie policy must be separately declared. Verified hard constraints still bound feasible actions.
  • External policy enforcement may be simpler and safer than autonomous norm adoption. Choose this architecture only if the agent truly has discretion.
  • bdi-agent-architecture handles basic goals and commitments; bdi-agent-interpreters handles the executable cycle.

Source-bound checks

  • Read sources/normative-bdi-agent-architecture/references/source-boundary-and-authority-trace.md for primary-source scope, ANB/NIB distinctions, and independent effect admission.
  • Read sources/normative-bdi-agents/references/source-boundary-and-authority-trace.md when comparing source variants. The similarly named 2014, 2015, and 2012 works are distinct; do not collapse their results.
  • An active NIB instance is a local model state, not a legal, ethical, or execution authority.

Source bundles

The three imported variants are preserved under sources/normative-bdi-agent-architecture/, sources/normative-bdi-agents/, and sources/a-normative-extension-for-the-bdi-agent/. Compare them before quoting a paper-specific rule; verify claims against the primary publication.

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

2000s-visualization-expert

무료

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy32026년 10월 19일 업데이트

2026-legal-research-agent

무료

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy32026년 10월 19일 업데이트

3d-cv-labeling-2026

무료

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy32026년 10월 19일 업데이트

a-discussion-of-decision-making-applied

무료

Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy32026년 10월 19일 업데이트

a-naturalistic-study-of-insight

무료

Use for insight, reframing, contradiction, impasse, and anomaly-driven problem solving when execution effort no longer helps. NOT for routine optimization, error correction, or well-specified tasks with known solution paths.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy32026년 10월 19일 업데이트

a-task-analysis-of-pier-side-ship-handli

무료

Apply cognitive task analysis to expert work that depends on perceptual cues, branching judgment, and recurring monitoring loops. Use when decomposing expert capability into agent structure, simulation design, or validation interviews. NOT for ordinary step-by-step SOP capture or simple pipelines with no tacit cue layer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy32026년 10월 19일 업데이트

curiositech의 스킬 모두 보기

이 스킬의 문제 신고