MCP HubMCP Hub
스킬 목록으로 돌아가기

basic-obedience

pjt222
업데이트됨 Yesterday
4 조회
17
2
17
GitHub에서 보기
기타ai

정보

이 스킬은 긍정적 강화 방식을 사용해 앉아, 기다려, 와 같은 기본적인 개 훈련 명령에 대한 체계적인 지도를 제공합니다. 강아지, 성견, 구조견 모두를 위한 핵심 훈련 기법, 세션 구성, 방해 요소 극복 방법을 다룹니다. 개발자는 이를 활용해 애플리케이션에 신뢰할 수 있고 단계별로 구성된 복종 훈련 가이드를 통합할 수 있습니다.

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

Basic Obedience

Teach foundation commands (sit, stay, come, heel, down). Use positive reinforcement, marker training.

When Use

  • New puppy (8+ weeks) ready for foundation training
  • Adult dog lacks reliable basic commands
  • Rescue or rehomed dog must learn household command vocabulary
  • Before complex behaviors or off-leash work
  • Existing commands degraded, need re-establishing

Inputs

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

Steps

Step 1: Establish the Marker

Marker bridges gap between desired behavior and 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).

Got: Dog reliably orients toward handler on hearing marker, expecting reward.

If fail: Dog doesn't respond to marker after 20 reps? Treat value too low. Switch to higher-value rewards (cheese, chicken, liver). Dog too distracted to eat? Environment too stimulating — move to quieter space.

Step 2: Teach the Five Foundation Commands

Work one command per session until reliable, then mix.

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.

Got: Each command performed reliably in low-distraction environment with treats as motivation.

If fail: Command not progressing after 3 sessions? Break into smaller steps. Dog may need intermediate behavior (e.g., for "down," reward head-lowering motion before full elbows-on-ground).

Step 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

Got: Short, successful sessions. Dog wants more.

If fail: Dog disengages (sniffing, looking away, lying down)? Session too long, too hard, or rewards not motivating. End session, reassess.

Step 4: Distraction-Proof the Commands

Reliable in quiet environment? Add distractions systematically.

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

Got: Commands work reliably in progressively more distracting environments.

If fail: Specific distraction (other dogs, squirrels) consistently breaks training? Needs separate counter-conditioning (see behavioral-modification).

Checks

  • Marker charged, dog responds reliably
  • All five commands performed in low-distraction environment
  • Sessions 5-10 minutes, ending on success
  • Success rate ≥ 80% for each command
  • Commands being generalized via distraction ladder
  • Handler timing (marker within 1 second) consistent

Pitfalls

  • Repeating the cue: Saying "sit, sit, SIT" teaches dog first "sit" optional. Say once, wait
  • Treating too late: Treat must follow marker within 2-3 seconds. Late treating breaks association
  • Luring forever: Hand motion with treat (lure) must fade within 10-20 reps. Else dog only responds when food visible
  • Punishing failed recalls: Calling "come" then scolding (for slow, for holding item) poisons recall cue permanently
  • Training too long: Fatigued dog learns nothing. Quit while ahead
  • Inconsistent cues: All household members must use same words and gestures for each command

See Also

  • behavioral-modification — addresses unwanted behaviors interfering with basic obedience

GitHub 저장소

pjt222/agent-almanac
경로: i18n/caveman/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