MCP HubMCP Hub
스킬 목록으로 돌아가기

basic-obedience

pjt222
업데이트됨 Yesterday
17
2
17
GitHub에서 보기
기타ai

정보

이 스킬은 강화 훈련을 통해 앉아, 기다려, 와 같은 핵심 명령을 가르쳐 개에게 기본적인 복종 훈련을 제공합니다. 타이밍, 훈련 세션 구성, 방해 요소 대처 방법 등 주요 훈련 요소를 다룹니다. 새로 데려온 강아지, 기본기가 필요한 성견, 구조견, 또는 고급 훈련 전에 약화된 명령을 복습해야 하는 경우에 사용하세요.

빠른 설치

Claude Code

추천
기본
npx skills add pjt222/agent-almanac -a claude-code
플러그인 명령대체
/plugin add https://github.com/pjt222/agent-almanac
Git 클론대체
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/basic-obedience

Claude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요

문서

Grundgehorsam

Lehren foundation commands (sit, stay, come, heel, down) using positive reinforcement and marker training.

Wann verwenden

  • A new puppy (8+ weeks) is ready for foundation training
  • An adult dog lacks reliable basic commands
  • A rescue or rehomed dog needs to learn the household's command vocabulary
  • Before advancing to more complex behaviors or off-leash work
  • When existing commands have degraded and need re-establishing

Eingaben

  • Erforderlich: A dog (any breed, any age 8+ weeks)
  • Erforderlich: High-value treats (small, soft, quickly consumed)
  • Optional: Clicker or verbal marker word (e.g., "yes")
  • Optional: 6-foot leash and flat collar or harness
  • Optional: Quiet training space with minimal distractions (initially)

Vorgehensweise

Schritt 1: Establish the Marker

The marker bridges the gap zwischen the desired behavior and the reward.

Marker Training Protocol:
1. Choose your marker: clicker (precise) or verbal "yes" (always available)
2. Charge the marker (10-15 reps):
   - Mark (click or "yes") then immediately deliver a treat
   - No behavior required — just marker → treat, marker → treat
   - Dog should begin orienting toward you at the sound of the marker
3. Test: mark when the dog is looking away. Does the dog turn toward
   you expecting a treat? If yes, the marker is charged.

Timing Rule:
The marker must occur WITHIN 1 second of the desired behavior.
Late marking teaches the wrong behavior.
Mark → then reach for the treat (not the reverse).

Erwartet: The dog reliably orients toward the handler upon hearing the marker, expecting a reward.

Bei Fehler: If the dog nicht respond to the marker nach 20 reps, the treat value is too low. Switch to higher-value rewards (cheese, chicken, liver). If the dog is too distracted to eat, die Umgebung is too stimulating — move to a quieter space.

Schritt 2: Lehren the Five Foundation Commands

Work on one command per session until reliable, then begin mixing.

Command Protocols:

SIT:
1. Hold treat above dog's nose, slowly arc backward over the head
2. As the dog's head follows up, the rear naturally lowers
3. The instant the rear touches the ground → mark and treat
4. Add the verbal cue "sit" AFTER the dog is offering the behavior reliably
   (cue comes before behavior only once the dog understands the behavior)

DOWN:
1. From a sit, hold treat at the dog's nose then lower slowly to the ground
2. Draw the treat slightly forward along the ground
3. As elbows touch the ground → mark and treat
4. If the dog stands instead, reset and try with less forward movement

STAY:
1. Ask for a sit or down
2. Open palm toward the dog, say "stay"
3. Wait 1 second → mark and treat while the dog is still in position
4. Gradually increase duration: 2s, 5s, 10s, 30s, 1 min
5. Add distance: one step back, then two, then five
6. Add distraction: only after duration and distance are solid
   (the "three Ds": Duration, Distance, Distraction — increase one at a time)

COME (recall):
1. Start on a long line (15-30 ft) in a low-distraction environment
2. Let the dog wander, then call name + "come" in an upbeat tone
3. If the dog turns toward you → mark → reward generously when the dog arrives
4. NEVER call "come" for something unpleasant (bath, crate, leaving the park)
5. Recall is the most important safety command — make it the most rewarding

HEEL:
1. Dog on your left side, treat in left hand at your hip
2. Take one step, if the dog moves with you → mark and treat
3. Gradually increase to two steps, five steps, ten steps
4. Mark and treat for maintaining position (head roughly at your knee)
5. If the dog pulls ahead, stop walking. Resume when the leash is loose.

Erwartet: Each command is performed reliably in a low-distraction environment with treats as motivation.

Bei Fehler: If a command ist nicht progressing nach 3 sessions, break it into smaller steps. The dog may need an intermediate behavior (e.g., for "down," reward the head-lowering motion vor requiring full elbows-on-ground).

Schritt 3: Structure Training Sessions

Session Guidelines:
+--------------------+------------------------------------------+
| Parameter          | Guideline                                |
+--------------------+------------------------------------------+
| Duration           | 5-10 minutes (puppies: 3-5 minutes)      |
| Frequency          | 2-3 sessions per day                     |
| End on success     | Always end after a successful rep, not   |
|                    | after a failure                          |
| Reward rate        | Initially: every correct rep             |
|                    | Later: intermittent (variable schedule)  |
| Energy management  | High-energy dog? Exercise BEFORE training|
|                    | Low-energy dog? Train when most alert    |
| Session structure  | Warm-up (easy known command) → new       |
|                    | material → cool-down (easy command)      |
+--------------------+------------------------------------------+

The 80/20 Rule:
- 80% of reps should succeed (dog is getting it right)
- If success rate drops below 80%, the criteria is too high — go easier
- 20% challenge keeps the dog engaged without frustrating

Erwartet: Short, successful sessions that leave the dog wanting more.

Bei Fehler: If the dog disengages (sniffing, looking away, lying down), the session is too long, too hard, or the rewards are insufficiently motivating. End the session and reassess.

Schritt 4: Distraction-Proof the Commands

Once reliable in a quiet environment, systematically add distractions.

Distraction Ladder (work through sequentially):
1. Quiet room, no distractions (starting point)
2. Room with a family member present
3. Backyard or garden
4. Front yard with street noise
5. Quiet park or trail
6. Busy park with other dogs at a distance
7. Busy park with other dogs nearby
8. Novel environments (pet store, cafe patio)

At each new level:
- Expect performance to decrease — this is normal
- Increase reward rate back to every correct rep
- Do not add more distraction until the current level is reliable
- If the dog fails 3 reps in a row, you moved up too fast — go back one level

Erwartet: Commands work reliably in progressively more distracting environments.

Bei Fehler: If a specific distraction (other dogs, squirrels) consistently breaks training, that distraction needs separate counter-conditioning work (see behavioral-modification).

Validierung

  • Marker is charged and the dog responds reliably
  • All five commands are performed in a low-distraction environment
  • Training sessions are 5-10 minutes, ending on success
  • Success rate is at or ueber 80% fuer jede command
  • Commands are being generalized durch the distraction ladder
  • The handler's timing (marker innerhalb 1 second) is consistent

Haeufige Stolperfallen

  • Repeating the cue: Saying "sit, sit, SIT" teaches the dog that the first "sit" is optional. Say it once and wait
  • Treating too late: The treat should follow the marker innerhalb 2-3 seconds. Late treating breaks the association
  • Luring forever: The hand motion with the treat (lure) sollte faded innerhalb 10-20 reps. Otherwise the dog only responds when food is visible
  • Punishing failed recalls: Calling "come" and then scolding the dog (for being slow, for having something in its mouth) poisons the recall cue permanently
  • Training too long: A fatigued dog learns nothing. Quit while ahead
  • Inconsistent cues: All household members must use the same words and gestures fuer jede command

Verwandte Skills

  • behavioral-modification — for addressing unwanted behaviors that interfere with basic obedience

GitHub 저장소

pjt222/agent-almanac
경로: i18n/de/skills/basic-obedience
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

연관 스킬

llamaguard

기타

LlamaGuard는 폭력 및 혐오 발언 등 6가지 안전 범주에서 LLM 입력과 출력을 조정하기 위한 Meta의 70-80억 파라미터 모델입니다. 94-95% 정확도를 제공하며 vLLM, Hugging Face 또는 Amazon SageMaker를 사용해 배포할 수 있습니다. 이 기술을 사용하여 AI 애플리케이션에 콘텐츠 필터링 및 안전 가드레일을 손쉽게 통합하세요.

스킬 보기

cost-optimization

기타

이 Claude Skill은 리소스 적정화, 태깅 전략, 지출 분석을 통해 개발자들이 클라우드 비용을 최적화할 수 있도록 지원합니다. AWS, Azure, GCP에서 클라우드 비용을 절감하고 비용 거버넌스를 구현하기 위한 프레임워크를 제공합니다. 인프라 비용을 분석하거나, 리소스를 적정화하거나, 예산 제약을 충족해야 할 때 사용하세요.

스킬 보기

quantizing-models-bitsandbytes

기타

이 스킬은 bitsandbytes를 사용하여 LLM을 8비트 또는 4비트 정밀도로 양자화하며, 최소한의 정확도 손실로 50-75%의 메모리 감소를 달성합니다. 제한된 GPU 메모리에서 더 큰 모델을 실행하거나 추론을 가속화하는 데 이상적이며, INT8, NF4, FP4와 같은 형식을 지원합니다. 이 스킬은 HuggingFace Transformers와 통합되어 QLoRA 학습 및 8비트 옵티마이저를 가능하게 합니다.

스킬 보기

dispatching-parallel-agents

기타

이 Claude Skill은 3개 이상의 독립적인 문제를 동시에 조사하고 해결하기 위해 다중 에이전트를 배치합니다. 공유 상태나 의존성 없이 해결 가능한 무관련 장애 시나리오에 맞게 설계되었습니다. 핵심 기능은 병렬 문제 해결로, 각 독립 문제 영역마다 하나의 에이전트를 할당하여 효율성을 극대화합니다.

스킬 보기