fungi-identification
О программе
Этот навык определяет грибы по полевым признакам, таким как шляпка, пластинки и споровый отпечаток, уделяя особое внимание безопасности и различиям с ядовитыми двойниками. Используйте его для проверки видов при сборе, оценки грибов на вашем участке или подтверждения съедобности перед употреблением. Он предлагает структурированный подход к идентификации грибов с приоритетом безопасности.
Быстрая установка
Claude Code
Рекомендуетсяnpx 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-identificationСкопируйте и вставьте эту команду в Claude Code для установки этого навыка
Документация
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 entirelyforage-plants— complementary field identification skill; shares the multi-feature confirmation methodology
GitHub репозиторий
Похожие навыки
llamaguard
ДругоеLlamaGuard — это модель от Meta с 7–8 миллиардами параметров для модерации входных и выходных данных больших языковых моделей по шести категориям безопасности, таким как насилие и разжигание ненависти. Она обеспечивает точность 94–95% и может быть развернута с помощью vLLM, Hugging Face или Amazon SageMaker. Используйте этот навык, чтобы легко интегрировать фильтрацию контента и защитные механизмы в ваши ИИ-приложения.
cost-optimization
ДругоеЭтот навык Claude помогает разработчикам оптимизировать облачные расходы за счет правильного подбора ресурсов, стратегий тегирования и анализа затрат. Он предоставляет framework для сокращения облачных расходов и внедрения управления затратами в AWS, Azure и GCP. Используйте его, когда вам нужно проанализировать расходы на инфраструктуру, оптимизировать ресурсы или уложиться в бюджетные ограничения.
quantizing-models-bitsandbytes
ДругоеЭтот навык выполняет квантизацию LLM до 8-битной или 4-битной точности с использованием библиотеки bitsandbytes, обеспечивая сокращение использования памяти на 50-75% при минимальной потере точности. Он идеально подходит для запуска больших моделей при ограниченной памяти GPU или для ускорения вывода, поддерживая форматы INT8, NF4 и FP4. Навык интегрируется с HuggingFace Transformers и позволяет использовать обучение QLoRA и 8-битные оптимизаторы.
dispatching-parallel-agents
ДругоеЭтот навык Claude распределяет нескольких агентов для исследования и устранения трёх и более независимых проблем параллельно. Он предназначен для сценариев с несвязанными сбоями, которые можно устранить без общего состояния или зависимостей. Ключевая возможность — параллельное решение проблем, где за каждую независимую предметную область назначается отдельный агент для максимальной эффективности.
