MCP HubMCP Hub
스킬 목록으로 돌아가기

fungi-identification

pjt222
업데이트됨 Yesterday
3 조회
17
2
17
GitHub에서 보기
기타ai

정보

이 스킬은 버섯의 갓, 주름, 포자 무늬와 같은 현장 특성을 통해 곰팡이를 식별하며, 안전을 강조하고 유독한 유사종을 구분합니다. 채집 중 종 확인, 소유지 내 버섯 평가, 섭취 전 식용 여부 확인에 사용하세요. 버섯 식별을 위해 구조화된 안전 우선 접근 방식을 제공합니다.

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/fungi-identification

Claude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요

문서

Fungi Identification

Identify fungi in the field using morphological features, spore prints, habitat, and season with an absolute safety-first approach.

When to Use

  • You encounter an unknown fungus and need to identify it
  • You are foraging for edible mushrooms and need to confirm species before consumption
  • You want to assess whether fungi in your garden or property are harmful
  • You are building field identification skills through structured observation practice
  • You need to differentiate an edible species from a dangerous look-alike

Inputs

  • Required: A fungus specimen or clear observation of one in situ
  • Required: Ability to observe fine morphological details (cap, gills, stem, base)
  • Optional: Field guide or reference material for the region
  • Optional: Paper and glass for spore prints
  • Optional: Knife for cross-section examination
  • Optional: Hand lens (10x) for fine detail

Procedure

Step 1: The Cardinal Rule

Before any identification work, internalize the absolute rule of mycology.

CARDINAL RULE:
If you are not 100% certain of the identification, DO NOT EAT IT.

There is no "universal edibility test" for mushrooms.
Some deadly species taste pleasant.
Some deadly species have delayed symptoms (24-72 hours).
Some deadly species have NO antidote.

The cost of a false positive (eating a misidentified mushroom) is
organ failure and death. The cost of a false negative (skipping an
edible mushroom) is a missed meal.

ALWAYS ERR TOWARD CAUTION.

Got: The cardinal rule is internalized before proceeding with identification.

If fail: There is no failure mode for this step. If the rule is not internalized, do not proceed to field identification for consumption purposes.

Step 2: Document the Habitat

Context narrows identification before touching the specimen.

Habitat Recording:
+--------------------+------------------------------------------+
| Factor             | Record                                   |
+--------------------+------------------------------------------+
| Substrate          | Soil, wood (dead/living), dung, leaf      |
|                    | litter, moss, other fungi                |
+--------------------+------------------------------------------+
| Tree association   | What trees are within 10m? (Many fungi    |
|                    | are mycorrhizal with specific tree genera)|
+--------------------+------------------------------------------+
| Moisture           | Dry, damp, wet, waterlogged              |
+--------------------+------------------------------------------+
| Light              | Full shade, dappled, open                |
+--------------------+------------------------------------------+
| Season             | Early spring, late spring, summer, early  |
|                    | autumn, late autumn, winter              |
+--------------------+------------------------------------------+
| Altitude           | Lowland, mid-altitude, montane           |
+--------------------+------------------------------------------+
| Growth pattern     | Solitary, scattered, clustered, ring,    |
|                    | shelf/bracket                            |
+--------------------+------------------------------------------+

Got: A complete habitat record that provides context for species-level identification.

If fail: If habitat is unclear (e.g., urban garden with mixed plantings), record what is visible. Incomplete habitat data reduces identification confidence — factor this into the safety assessment.

Step 3: Examine Morphological Features

Systematic examination of the specimen itself.

Morphological Checklist:

CAP (Pileus):
- Shape: convex, flat, concave, conical, umbonate, bell-shaped
- Diameter (measure or estimate)
- Surface: smooth, scaly, fibrous, slimy, dry, cracked
- Colour (note if colour changes with age or moisture)
- Margin: smooth, striate, inrolled, appendiculate (veil remnants)

GILLS / PORES / SPINES (Hymenium):
- Type: gills (lamellae), pores (tubes), spines (teeth), smooth
- Attachment: free, adnexed, adnate, decurrent
- Spacing: crowded, close, distant
- Colour (important — note changes with age)
- Bruising: do gills change colour when damaged?

STEM (Stipe):
- Height and diameter
- Shape: equal, tapered, bulbous, club-shaped
- Surface: smooth, fibrous, scaly, reticulate (netted)
- Interior: solid, hollow, stuffed (pithy center)
- Ring (annulus): present/absent, position, persistent/fragile
- Volva (cup at base): present/absent — ALWAYS check by
  carefully excavating the base (Amanita species have a volva)

FLESH (Context):
- Colour when cut
- Colour change on exposure to air (note time to change)
- Texture: firm, brittle, fibrous, gelatinous
- Smell: mushroomy, anise, radish, flour, chlorine, unpleasant
- Taste: (ONLY if species is confirmed non-deadly by an expert;
  for unknown species, DO NOT taste)

SPORE PRINT:
- Remove the stem; place the cap gill-side down on paper
  (half white, half dark paper to see any colour)
- Cover with a glass or bowl to maintain humidity
- Wait 4-12 hours
- Record spore colour: white, cream, pink, brown, purple-brown,
  black, rust-orange

Got: A complete morphological description covering all major features.

If fail: If a feature cannot be observed (e.g., no ring visible but it may have been lost), record it as "not observed" rather than "absent." The distinction matters for identification.

Step 4: Identify Using Multiple Confirmations

Cross-reference all data against reference material.

Identification Protocol:
1. Use habitat + season to narrow to likely genera
2. Use cap shape + gill type + spore colour to narrow to species group
3. Check ALL features against the candidate species description
4. Specifically check against dangerous look-alikes:
   - Does this species have a deadly doppelganger?
   - What feature distinguishes the edible from the deadly?
   - Can I see that distinguishing feature clearly?

Confidence Levels:
+----------+---------------------------+---------------------------+
| Level    | Criteria                  | Action                    |
+----------+---------------------------+---------------------------+
| Certain  | All features match; no    | Safe to collect (for      |
|          | look-alike confusion;     | experienced identifiers)  |
|          | experienced with species  |                           |
+----------+---------------------------+---------------------------+
| Probable | Most features match;      | DO NOT eat. Collect for   |
|          | one or two uncertain;     | further study (spore      |
|          | look-alike eliminated     | print, expert review)     |
+----------+---------------------------+---------------------------+
| Possible | Some features match;      | DO NOT eat. Photograph    |
|          | look-alike not fully      | and seek expert opinion   |
|          | eliminated                |                           |
+----------+---------------------------+---------------------------+
| Unknown  | Cannot narrow to species  | DO NOT eat. DO NOT        |
|          |                          | handle extensively        |
+----------+---------------------------+---------------------------+

Got: A species-level identification with explicit confidence level and look-alike assessment.

If fail: If identification stalls at genus level, that is acceptable for learning purposes. For consumption, only species-level "Certain" identification is acceptable.

Validation

  • The cardinal rule was acknowledged before starting identification
  • Habitat was documented before examining the specimen
  • All morphological features were examined systematically
  • The base was excavated to check for a volva
  • A spore print was taken (if time allows)
  • Dangerous look-alikes were explicitly checked and eliminated
  • Confidence level was honestly assessed
  • Only "Certain" identifications were considered for consumption

Pitfalls

  • Relying on a single feature: "It looks like a chanterelle" based on colour alone. True chanterelles have false gills (ridges), grow from soil near trees, and have a specific apricot smell. False chanterelles and Jack-o'-lanterns share the colour but differ in every other feature
  • Skipping the base examination: Failing to dig up the base misses the volva — the single most important feature for identifying deadly Amanita species (death cap, destroying angel)
  • Trusting apps blindly: AI-based mushroom identification apps have significant error rates for look-alike species. Use them as a starting point, never as confirmation
  • Assuming "common = safe": Abundance does not indicate edibility. Deadly species can be locally abundant
  • Tasting unknown species: Some mycologists use taste as a diagnostic tool, but this requires expert-level knowledge of which species are safe to taste. For non-experts, do not taste unknown fungi
  • Ignoring temporal toxins: Some species (e.g., Amanita phalloides) have pleasant taste and delayed symptoms. By the time symptoms appear (24-48 hours), liver damage is severe

Related Skills

  • mushroom-cultivation — growing known species eliminates identification risk entirely
  • forage-plants — complementary field identification skill; shares the multi-feature confirmation methodology

GitHub 저장소

pjt222/agent-almanac
경로: i18n/caveman-lite/skills/fungi-identification
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