スキル一覧に戻る

fungi-identification

pjt222
更新日 2 days ago
3 閲覧
17
2
17
GitHubで表示
その他ai

について

このスキルは、形態的特徴、胞子紋、生息環境の文脈を分析し、安全性最優先の厳格なアプローチで、野外における菌類の同定を可能にします。外見が類似する種の識別や毒性リスクの評価を支援し、主にキノコ採集時の摂取前の種確認を目的としています。開発者は、キノコ同定ツール、安全性評価ツール、または教育用菌学アプリケーションを構築する際に、このスキルを活用してください。

クイックインストール

Claude Code

推奨
メイン
npx skills add pjt222/agent-almanac -a claude-code
プラグインコマンド代替
/plugin add https://github.com/pjt222/agent-almanac
Git クローン代替
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/fungi-identification

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Fungi Identification

Field ID fungi via morphology + spore print + habitat + season. Safety-first.

Use When

  • Unknown fungus → ID
  • Foraging edible → confirm species before eat
  • Garden fungi harmful?
  • Building field ID skill
  • Differentiate edible from deadly look-alike

In

  • Required: specimen or clear in-situ observation
  • Required: ability to observe fine details (cap, gills, stem, base)
  • Optional: field guide for region
  • Optional: paper + glass for spore print
  • Optional: knife for cross-section
  • Optional: 10× hand lens

Do

Step 1: Cardinal Rule

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.

→ Rule internalized before ID.

If err: no failure mode. Rule not internalized → do not proceed for consumption.

Step 2: Document habitat

Context narrows ID before touching.

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                            |
+--------------------+------------------------------------------+

→ Complete habitat record for species ID context.

If err: unclear (urban mixed) → record what visible. Incomplete → reduces confidence → factor into safety.

Step 3: Examine morphology

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

→ Complete morphological description.

If err: feature unobservable (no ring but may have been lost) → "not observed" not "absent". Distinction matters.

Step 4: ID via multiple confirmations

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        |
+----------+---------------------------+---------------------------+

→ Species-level ID + explicit confidence + look-alike assessment.

If err: stalls at genus → OK for learning. For consumption → only "Certain" species-level.

Check

  • Cardinal rule acknowledged
  • Habitat documented
  • All morphology examined
  • Base excavated → volva check
  • Spore print (if time)
  • Look-alikes ruled out
  • Confidence honestly assessed
  • Only "Certain" → consumption

Traps

  • Single feature: "looks like chanterelle" by colour alone. True chanterelle = false gills + soil near trees + apricot smell. False chanterelle + Jack-o'-lantern share colour only.
  • Skip base: miss volva → deadly Amanita (death cap, destroying angel).
  • App trust: AI ID apps → high error on look-alikes. Starting point not confirmation.
  • "Common = safe": abundance ≠ edible. Deadly can be locally abundant.
  • Taste unknown: expert-only diagnostic. Non-expert: never taste unknown.
  • Delayed toxins: A. phalloides → pleasant taste + 24-48 hr symptoms → liver damage by then.

  • mushroom-cultivation — growing known species eliminates ID risk
  • forage-plants — complementary field ID, multi-feature confirmation

GitHub リポジトリ

pjt222/agent-almanac
パス: i18n/caveman-ultra/skills/fungi-identification
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

関連スキル

llamaguard

その他

LlamaGuardは、暴力やヘイトスピーチなど6つの安全性カテゴリーにおいて、LLMの入力と出力をモデレートするMetaの70-80億パラメータモデルです。94〜95%の精度を提供し、vLLM、Hugging Face、Amazon SageMakerを使用してデプロイ可能です。このスキルを使用して、AIアプリケーションにコンテンツフィルタリングと安全策を簡単に統合できます。

スキルを見る

cost-optimization

その他

このClaudeスキルは、リソースの適正サイジング、タグ付け戦略、支出分析を通じて、開発者がクラウドコストを最適化することを支援します。AWS、Azure、GCPにわたるクラウド支出の削減とコストガバナンスの実施のためのフレームワークを提供します。インフラコストの分析、リソースの適正サイジング、または予算制約への対応が必要な際にご利用ください。

スキルを見る

quantizing-models-bitsandbytes

その他

このスキルは、bitsandbytesを使用してLLMを8ビットまたは4ビット精度に量子化し、精度の低下を最小限に抑えつつ50〜75%のメモリ削減を実現します。限られたGPUメモリでより大規模なモデルを実行したり、推論を高速化するのに理想的で、INT8、NF4、FP4などのフォーマットをサポートしています。HuggingFace Transformersと統合され、QLoRAトレーニングや8ビットオプティマイザーを可能にします。

スキルを見る

dispatching-parallel-agents

その他

このClaudeスキルは、複数のエージェントを配備し、3つ以上の独立した問題を並行して調査・修正します。共有状態や依存関係がなく解決可能な、無関係な障害が発生するシナリオ向けに設計されています。中核となる機能は並列問題解決であり、効率を最大化するために独立した問題領域ごとに1つのエージェントを割り当てます。

スキルを見る