fungi-identification
について
このスキルは、形態的特徴、胞子紋、生息地を分析することで、野外での菌類の同定を可能にします。外見の類似種の区別、毒性の評価、そして摂取前には絶対的な確証を得るという安全第一の原則を徹底するのに役立ちます。キノコ採り、種の確認、あるいは敷地内の未知の菌類を評価する際にご利用ください。
クイックインストール
Claude Code
推奨npx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit 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
Find mushroom ID in field. Use shape, spore prints, habitat, season. Safety first, always.
When Use
- Unknown fungus, need ID
- Foraging edible mushrooms, confirm species before eat
- Garden/property fungi: harmful?
- Build field ID skill with structured observation
- Tell edible from dangerous look-alike
Inputs
- Required: Fungus specimen or clear observation in situ
- Required: Eye for fine detail (cap, gills, stem, base)
- Optional: Field guide for region
- Optional: Paper + glass for spore prints
- Optional: Knife for cross-section
- Optional: Hand lens (10x) for fine detail
Steps
Step 1: Cardinal Rule
Before any ID work, burn rule into head.
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: Cardinal rule internalized before proceeding.
If fail: No failure mode for this step. Rule not internalized → do not proceed to field ID for consumption.
Step 2: Document Habitat
Context narrows ID before touching 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: Complete habitat record gives context for species ID.
If fail: Habitat unclear (urban garden, mixed plantings)? Record what visible. Incomplete habitat = lower ID confidence — factor into safety check.
Step 3: Examine Morphological Features
Systematic look at specimen.
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: Full morphological description — all major features.
If fail: Feature not observable (no ring visible, may have been lost)? Record "not observed" not "absent." Distinction matters for ID.
Step 4: ID with Multiple Confirmations
Cross-reference all data vs 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: Species-level ID with explicit confidence + look-alike assessment.
If fail: ID stalls at genus level? OK for learning. For eating, only species-level "Certain" ID acceptable.
Checks
- Cardinal rule acknowledged before starting
- Habitat documented before examining specimen
- All morphological features examined systematically
- Base excavated to check volva
- Spore print taken (if time allows)
- Dangerous look-alikes explicitly checked + eliminated
- Confidence level honestly assessed
- Only "Certain" IDs considered for eating
Pitfalls
- One-feature ID: "Looks like chanterelle" by colour alone. True chanterelles have false gills (ridges), grow from soil near trees, apricot smell. False chanterelles + Jack-o'-lanterns share colour but differ every other feature
- Skipping base check: No dig = no volva — single most important feature for deadly Amanita (death cap, destroying angel)
- Trust apps blind: AI mushroom ID apps big error rates for look-alikes. Use as start, never as confirmation
- "Common = safe": Abundance no tell edibility. Deadly species can be locally abundant
- Tasting unknowns: Some mycologists taste as diagnostic, needs expert knowledge of safe-to-taste species. Non-experts → no taste unknown fungi
- Ignoring delayed toxins: Some species (Amanita phalloides) pleasant taste + delayed symptoms. When symptoms appear (24-48h), liver damage severe
See Also
mushroom-cultivation— growing known species kills ID risk entireforage-plants— complementary field ID skill; same multi-feature confirmation method
GitHub リポジトリ
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。
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。
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。
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。
