무료GitHub에 공개

bdi-agent-architecture

Design an individual agent's belief, goal, intention, and reconsideration model. Use when specifying autonomous decision state, commitment policy, or recovery from failed plans. NOT for AgentSpeak interpreter mechanics, organization modeling, normative conflicts, or multi-agent execution waves.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

curiositech/port-daddy

설치 방법 보기

포함된 파일(77)

SKILL.md4.0 KB
sources/bdi-agency-model/_book_identity.json3.1 KB
sources/bdi-agency-model/_raw_response.md102.9 KB
sources/bdi-agency-model/CHANGELOG.md207 B
sources/bdi-agency-model/diagrams/01_flowchart_bdi_agent_decision_cycle_and_r.md1.5 KB
sources/bdi-agency-model/diagrams/02_stateDiagram-v2_intention_lifecycle-_commitmen.md1.8 KB
sources/bdi-agency-model/diagrams/03_quadrantChart_environment_dynamics_vs._compu.md836 B
sources/bdi-agency-model/diagrams/INDEX.md1.0 KB
sources/bdi-agency-model/references/evidence-scope.md651 B
sources/bdi-agency-model/references/INDEX.md1.1 KB
sources/bdi-agency-model/references/learning-the-missing-piece.md10.3 KB
sources/bdi-agency-model/references/multi-agent-commitment-and-coordination.md21.2 KB
sources/bdi-agency-model/references/rational-commitment-and-reconsideration.md16.4 KB
sources/bdi-agency-model/references/soar-bdi-convergent-evolution.md18.3 KB
sources/bdi-agency-model/references/task-vs-goal-orientation.md18.2 KB
sources/bdi-agency-model/references/why-beliefs-desires-intentions-exist.md14.7 KB
sources/bdi-agency-model/SKILL.md16.5 KB
sources/belief-desire-intention-model-of-agency/_book_identity.json3.1 KB
sources/belief-desire-intention-model-of-agency/_raw_response.md103.1 KB
sources/belief-desire-intention-model-of-agency/CHANGELOG.md223 B
sources/belief-desire-intention-model-of-agency/diagrams/01_flowchart_bdi_agent_decision_cycle_and_r.md1.5 KB
sources/belief-desire-intention-model-of-agency/diagrams/02_stateDiagram-v2_intention_lifecycle-_commitmen.md1.8 KB
sources/belief-desire-intention-model-of-agency/diagrams/03_quadrantChart_environment_dynamics_vs._compu.md836 B
sources/belief-desire-intention-model-of-agency/references/commitment-boundary-and-trace.md2.1 KB
sources/belief-desire-intention-model-of-agency/references/learning-the-missing-piece.md10.3 KB
sources/belief-desire-intention-model-of-agency/references/multi-agent-commitment-and-coordination.md21.2 KB
sources/belief-desire-intention-model-of-agency/references/rational-commitment-and-reconsideration.md16.4 KB
sources/belief-desire-intention-model-of-agency/references/soar-bdi-convergent-evolution.md18.3 KB
sources/belief-desire-intention-model-of-agency/references/task-vs-goal-orientation.md18.2 KB
sources/belief-desire-intention-model-of-agency/references/why-beliefs-desires-intentions-exist.md14.7 KB
sources/belief-desire-intention-model-of-agency/SKILL.md16.3 KB
sources/INDEX.md12.7 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/_book_identity.json3.4 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/_raw_response.md92.3 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/CHANGELOG.md237 B
sources/rao-georgeff-1991-modeling-rational-agents-bdi/diagrams/01_stateDiagram-v2_bdi_mental_state_transitions_&.md2.7 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/diagrams/02_flowchart_goal_decomposition_&_side-effe.md1.6 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/diagrams/03_mindmap_bdi_conceptual_hierarchy_&_mod.md1.7 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/diagrams/INDEX.md1006 B
sources/rao-georgeff-1991-modeling-rational-agents-bdi/references/avoiding-logical-omniscience-closure-problems.md12.8 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/references/branching-time-choice-vs-epistemic-uncertainty.md8.0 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/references/commitment-strategies-as-persistence-axioms.md13.5 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/references/intention-to-action-volitional-commitment.md12.3 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/references/problem-decomposition-through-world-branching.md13.6 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/references/sub-world-compatibility-solves-side-effects.md9.5 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/references/when-bdi-formalism-applies-and-when-it-breaks.md14.3 KB
sources/rao-georgeff-1991-modeling-rational-agents-bdi/SKILL.md13.4 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/_book_identity.json631 B
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/_raw_response.md113.4 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/CHANGELOG.md243 B
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/diagrams/01_stateDiagram-v2_bdi_agent_decision_cycle-_beli.md911 B
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/diagrams/02_flowchart_plan_selection_pipeline-_from_.md1.0 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/diagrams/03_sequenceDiagram_resource-bounded_rationality-_.md1.4 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/diagrams/INDEX.md505 B
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/commitment-strategies-and-reconsideration.md3.2 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/decision-trees-to-symbolic-reasoning.md4.5 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/failure-modes-complex-agent-systems.md2.3 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/option-generation-problem-filtering.md2.0 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/paper-scope-and-calibration.md2.3 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/plans-as-knowledge-compilation.md3.3 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/resource-bounded-rationality-three-attitudes.md2.8 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/theory-practice-gap-practical-approximation.md2.3 KB
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/SKILL.md11.1 KB
sources/the-belief-desire-intention-model-of-age/_book_identity.json3.1 KB
sources/the-belief-desire-intention-model-of-age/_raw_response.md103.1 KB
sources/the-belief-desire-intention-model-of-age/CHANGELOG.md223 B
sources/the-belief-desire-intention-model-of-age/diagrams/01_flowchart_bdi_agent_decision_cycle_and_r.md1.5 KB
sources/the-belief-desire-intention-model-of-age/diagrams/02_stateDiagram-v2_intention_lifecycle-_commitmen.md1.8 KB
sources/the-belief-desire-intention-model-of-age/diagrams/03_quadrantChart_environment_dynamics_vs._compu.md836 B
sources/the-belief-desire-intention-model-of-age/diagrams/INDEX.md1.1 KB
sources/the-belief-desire-intention-model-of-age/references/learning-the-missing-piece.md10.3 KB
sources/the-belief-desire-intention-model-of-age/references/multi-agent-commitment-and-coordination.md21.2 KB
sources/the-belief-desire-intention-model-of-age/references/rational-commitment-and-reconsideration.md16.4 KB
sources/the-belief-desire-intention-model-of-age/references/soar-bdi-convergent-evolution.md18.3 KB
sources/the-belief-desire-intention-model-of-age/references/task-vs-goal-orientation.md18.2 KB
sources/the-belief-desire-intention-model-of-age/references/why-beliefs-desires-intentions-exist.md14.7 KB
sources/the-belief-desire-intention-model-of-age/SKILL.md13.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

BDI Agent Architecture

Use this skill to decide what an individual agent must represent, and when it should revisit a chosen course of action. Use bdi-agent-interpreters when the decision becomes an event loop, plan library, or transition system.

Decision procedure

Name the environment observations and their uncertainty. Store them as beliefs with provenance or confidence where the system needs it.
Separate candidate goals from selected intentions. Record the resource or consistency constraints that make a candidate ineligible.
Give every intention an achievement condition, an abandonment condition, and a current means. An intention is a commitment to pursue a goal, not merely a preference.
Reconsider on relevant changes: a goal is achieved, its preconditions fail, its cost or risk changes materially, or a conflicting obligation appears. Choose periodic checks only where event triggers cannot cover the failure modes.
Check that the agent can explain a chosen action from source-tagged beliefs, selected intention, and plan; test recovery when the plan fails. Record external actions through a separate authorization and result boundary.

flowchart LR
  O[Observation] --> B[Belief update]
  B --> D[Candidate goals]
  D --> I[Select compatible intentions]
  I --> P[Choose means]
  P --> A[Act and monitor]
  A --> B
  B --> R{Material trigger?}
  R -->|yes| I
  R -->|no| P

Boundaries and cautions

A fixed workflow may be adequate when the environment and goals are stable; do not add mental-state machinery just for the label.
Do not claim that BDI's three categories are mathematically necessary for all resource-bounded agents. They are a useful architecture whose value depends on the task.
Do not assert a universal optimal reconsideration frequency. Measure the environment's change rate and the costs of deliberation and action.
A local BDI transition does not prove rationality, security, message delivery, joint commitment, or an external effect. Keep inter-agent commitments in an explicit protocol and check effect admission separately.
Joint intentions and norms require additional mechanisms; route to bdi-organizational-modeling or bdi-normative-reasoning.

Source bundles

The recovered source bundles, including every original reference, diagram, provenance file, and example, are under sources/<original-name>/. Read only the relevant bundle:

sources/rao-georgeff-1991-modeling-rational-agents-bdi/ for formal mental-state semantics.
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/ for theory-to-system design.
sources/belief-desire-intention-model-of-agency/ for commitment and reconsideration discussions.
sources/the-belief-desire-intention-model-of-age/ for the second recovered copy; compare it before citing claims.
sources/bdi-agency-model/references/evidence-scope.md for the local-reasoning boundary.
sources/belief-desire-intention-model-of-agency/references/commitment-boundary-and-trace.md for commitment trace requirements.
sources/rao-georgeff-1995-bdi-agents-from-theory-to-practice/references/paper-scope-and-calibration.md for paper-scoped reconsideration claims.
sources/bdi-agency-model/ for a broader imported survey.

Treat empirical numbers and cross-architecture equivalences in recovered prose as leads to verify in primary papers, not established findings. The source title and license are preserved with each bundle.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

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

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

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

설치

명령으로 설치

npx skills add https://github.com/curiositech/port-daddy --skill bdi-agent-architecture

터미널에 붙여 넣고 실행합니다(Node.js 필요). Claude Code, Codex 등 설치할 에이전트를 고를 수 있습니다.

에이전트에게 부탁하기

다음 Agent Skill을 설치해 주세요.
https://github.com/curiositech/port-daddy/tree/main/skills/bdi-agent-architecture

먼저 SKILL.md와 첨부 파일의 내용을 확인해 수상한 처리(외부 전송, 인증 정보 읽기 등)가 없는지 확인한 뒤 Claude Code는 ~/.claude/skills/bdi-agent-architecture/, Codex는 ~/.agents/skills/bdi-agent-architecture/ 에 배치해 주세요.

이 문장을 그대로 Claude Code나 Codex에 보내면 내용을 확인한 뒤 설치해 줍니다.

GitHub에서 소스 보기

저장소: curiositech/port-daddy
스타: 3
포크: 1
카테고리: 디자인
라이선스: Apache-2.0
원문 언어: 영어
최종 업데이트: 2026년 10월 19일

스킬은 에이전트를 위한 지시와 스크립트의 묶음입니다. cccskills는 내용의 안전성을 보증하지 않습니다. 설치하기 전에 내용을 확인하세요.