read-garden
について
このスキルは、介入前に庭の健康状態を体系的に観察・評価するための構造化された感覚プロトコルを提供します。ユーザーを、クリアリング、ゲシュタルト観察、詳細な感覚チェック、パターン分析の段階へと導き、問題を診断します。植物のストレス評価、季節の変化の観察、定期的なモニタリング時に使用し、データに基づいた園芸判断を支えます。
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/read-garden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
Read Garden
Observe + assess garden via structured sensory protocol → before any intervention decision.
Use When
- Before any intervention → read first, act second
- Plant stress (yellow, wilt, curl, spots)
- Seasonal trans (spring wake, autumn decline)
- New site eval before plant
- Regular weekly/biweekly monitor
- After extreme weather (frost, heat, heavy rain)
In
- Required: Physical access garden
- Required: Journal/notebook → record obs
- Optional: Prev records → compare
- Optional: Soil thermometer, pH strips, moisture meter
- Optional: Hand lens (pest/disease ID)
Do
Step 1: Meditate Check — Pre-Entry Clear
Before enter for assess, clear preconceptions.
Pre-Garden Clearing (3-5 minutes):
1. Stand at the garden's edge — do not enter yet
2. Take three slow breaths (inhale 4 counts, exhale 6 counts)
3. Set aside what you expect to find:
- "I think the tomatoes need water" → Set aside
- "That pest spray probably didn't work" → Set aside
- "The lettuce should be ready by now" → Set aside
4. Adopt the observer's stance: you are here to receive information,
not confirm hypotheses
5. Let your eyes soften — peripheral vision, not focused scanning
6. When you feel neutral and receptive, enter the garden
Why this matters:
Gardeners who enter with a diagnosis in mind see confirmation
everywhere and miss what the garden is actually showing them.
Observation before interpretation is the foundation of good practice.
→ Calm, receptive, no preconceptions.
If err: can't release expectations (anxiety, frustration) → ack emotion, write "AOL: [concern]", proceed. Naming reduces influence.
Step 2: Stage I — Gestalt
Walk perimeter. Record first unfiltered impression.
Gestalt Protocol:
1. Walk slowly around the entire garden boundary
2. Do NOT examine individual plants yet — take in the whole
3. Record your impression using only these categories:
- Overall vigour: thriving / stable / declining
- Dominant colour tone: deep green / pale / mixed / yellowing
- Density: lush / adequate / sparse / bare patches
- Energy: (subjective) vibrant / calm / tired / distressed
4. Note what draws your eye first — this is often the loudest signal
5. Record ambient conditions: temperature, wind, sky, soil moisture
(visual), recent weather
Example Gestalt Record:
Date: 2026-04-15, 9:30am, 14°C, overcast, light rain yesterday
Overall: Stable, but northeast corner looks depleted
Colour: Mixed — good green on brassicas, pale on tomato starts
Density: Adequate except herb bed (sparse)
Energy: Calm, not vibrant — spring is slow this year
Eye drawn to: Wilting squash transplants (row 3)
→ Brief holistic record, no analysis or diagnosis.
If err: start diagnose ("squash wilts because...") → write "AOL: [diagnosis]" → return to obs. Analysis = Stage III.
Step 3: Stage II — Sensory
Move bed by bed. Engage all senses each area.
Sensory Observation Protocol (per bed or zone):
LEAF LANGUAGE:
- Colour: Deep green, pale green, yellowing, purpling, browning
- Yellowing (chlorosis): general = nitrogen, interveinal = iron/manganese
- Purpling: phosphorus deficiency or cold stress
- Browning: tip burn = salt/fertilizer, edge burn = potassium
- Curl direction:
- Upward: heat stress, drought, herbicide exposure
- Downward: overwatering, root damage
- Inward (cupping): virus, mite damage
- Surface: Smooth, rough, sticky (aphid honeydew), powdery (mildew), spotted
- Underside: Check for eggs, mites (tiny dots), early mildew
STEM AND STRUCTURE:
- Strength: Upright and sturdy vs. leaning or lodged
- Colour: Normal woody/green vs. blackening (rot) or pale (etiolation)
- Flexibility: Supple (healthy) vs. brittle (dehydrated) vs. mushy (disease)
- Growth pattern: Normal internodes vs. elongated (light-seeking)
ROOT SIGNALS (check at soil line and during transplant):
- Colour: White/cream (healthy), brown/black (rot), orange (rust fungus)
- Smell: Earthy (healthy), sour/sulphurous (anaerobic rot)
- Structure: Fibrous network (good) vs. circling (pot-bound) vs. sparse (stress)
SOIL AT THE PLANT:
- Moisture: Dry and cracked / moist and dark / waterlogged and gleaming
- Surface: Mulched / bare / crusted / mossy / algae-covered
- Smell: Sweet and earthy (good) / sour (anaerobic) / musty (fungal)
- Inhabitants: Earthworms, beetles, spiders (good) / slugs, ants farming aphids (concerning)
Record each observation as a sensory descriptor — no analysis yet.
Wrong: "The tomatoes have early blight"
Right: "Tomato lower leaves: brown spots, concentric rings, yellowing around spots"
→ Detailed sensory record per bed/zone, descriptive only.
If err: catch self diagnosing (name disease, blame pest) → "AOL: [diagnosis]" → return raw obs. Name later, data first.
Step 4: Stage III — Pattern
Now, only now, connect obs to patterns.
Pattern Analysis Protocol:
1. Review your Stage II notes for each bed
2. Ask these structured questions:
SPATIAL:
- Are symptoms localized (one plant, one bed) or systemic (whole garden)?
- Is there a gradient? (Worse near a fence = shade; worse near path = compaction)
- Are only certain species affected? (Host-specific = disease; all species = environmental)
TEMPORAL:
- Is this new growth or old growth?
- New growth affected: nutrient deficiency (can't build new tissue)
- Old growth affected: mobile nutrient being relocated, or infection spreading
- Did symptoms appear suddenly (weather event, application) or gradually (chronic condition)?
POPULATION:
- One plant: likely individual issue (root damage, transplant shock)
- One species: likely species-specific (disease, pest preference)
- All plants: likely environmental (soil, water, weather)
3. Cross-reference with Five Indicators (leaf, stem, root, soil, phenology):
- Do multiple indicators point to the same cause?
- Convergent signals = higher confidence diagnosis
- Contradictory signals = more observation needed
AOL Management:
If your mind jumps to a conclusion before the pattern analysis is complete:
- Write "AOL: [conclusion]" on a separate line
- Do NOT act on it yet
- Return to the data
- If the same conclusion re-emerges from multiple independent observations,
it graduates from AOL to tentative diagnosis
- A tentative diagnosis is still not action — it's a hypothesis to test
Distinguish:
- Premature label (low evidence, high confidence) → dangerous
- Convergent conclusion (high evidence, proportional confidence) → actionable
→ One+ tentative diagnoses backed by multi indep obs.
If err: no clear pattern → garden may be healthy (not all = problem) or signals too early. Record + reassess 1 week. Time clarifies what single visit can't.
Step 5: Heal Check — Triage
Convert obs → prioritized action plan.
Garden Health Triage Matrix:
┌──────────┬──────────────────────────┬─────────────────────────────┐
│ Priority │ Criteria │ Example Actions │
├──────────┼──────────────────────────┼─────────────────────────────┤
│ TODAY │ Actively dying, wilting │ Deep water. Emergency shade.│
│ (Red) │ severely, pest │ Hand-remove pests. Support │
│ │ infestation visible │ lodged stems. │
├──────────┼──────────────────────────┼─────────────────────────────┤
│ THIS │ Declining but stable, │ Feed (compost tea or foliar │
│ WEEK │ nutrient deficiency │ seaweed). Mulch bare soil. │
│ (Amber) │ symptoms, early disease │ Improve drainage. Prune │
│ │ signs │ affected foliage. │
├──────────┼──────────────────────────┼─────────────────────────────┤
│ WATCH │ Subtle changes, early │ Record in journal. Reassess │
│ (Green) │ signs that may resolve │ in 1 week. Take photos for │
│ │ naturally, seasonal │ comparison. Do NOT │
│ │ transitions │ intervene yet. │
├──────────┼──────────────────────────┼─────────────────────────────┤
│ HEALTHY │ No issues observed, │ Appreciate. Continue │
│ (Blue) │ vigorous growth, good │ current care. Note what's │
│ │ colour, active biology │ working for future seasons. │
└──────────┴──────────────────────────┴─────────────────────────────┘
Triage Rules:
1. Address RED items immediately — everything else can wait
2. Address AMBER items this week — schedule specific days
3. GREEN items: observe only. Most "watch" items resolve themselves.
The most common gardener error is treating green items as amber
4. BLUE items: actively note what's working — these are your successes
5. Never address more than 2 priorities per garden visit
(doing too many things at once means doing nothing well)
→ Triaged action list w/ clear priority + timeline.
If err: all feels red → may be anxiety mode not obs. Return Step 1, re-enter. True emergencies rare → most problems develop slow, can wait day.
Step 6: Record + Track
Complete session w/ journal entry.
Garden Observation Record Template:
Date: ___________ Time: ___________
Weather: ___________ Recent weather: ___________
GESTALT: (1-2 sentences from Stage I)
BED-BY-BED OBSERVATIONS: (Stage II data)
Bed 1: ___________
Bed 2: ___________
[...]
PATTERNS NOTED: (Stage III analysis)
___________
TRIAGE:
RED (today): ___________
AMBER (this week): ___________
GREEN (watch): ___________
BLUE (healthy): ___________
AOLs RECORDED: (list any premature conclusions that arose)
___________
ACTIONS TAKEN:
___________
COMPARE TO LAST VISIT:
Improving: ___________
Worsening: ___________
Unchanged: ___________
→ Complete dated record → comparable to prev visits.
If err: journal feels burden → minimum: date, weather, triage, one obs/bed. Consistency > detail.
Check
- Meditate done before enter
- Gestalt recorded before exam plants
- Stage II sensory uses descriptive lang (no diagnosis)
- AOLs ID'd + set aside (no premature act)
- Pattern → spatial, temporal, population
- Triage matrix done w/ clear priority
- Record dated + filed
- Actions proportional to triage (no over-treat green)
Traps
- Confirmation bias: Enter looking for problem → find it. Meditate prevents.
- Diagnose Stage II: Naming disease during sensory biases data. Stay descriptive til Stage III.
- Green as amber: Most "problems" resolve. Spray/prune first sign → more harm than symptom.
- Skip record: No journal → every visit fresh. Patterns need time + records.
- AOL suppress vs mgmt: Goal ≠ no analytic thoughts (impossible). Goal = notice, name, set aside til data supports/refutes.
- Over-intervention: Protocol → increase confidence + reduce actions. Doing more after reading → treating anxiety not garden.
→
meditate— pre-entry clear protocolheal— triage pattern in checkpointprepare-soil— soil assess overlaps soil obs layercultivate-bonsai— bonsai health assess same staged obsplan-garden-calendar— records inform calendar mid-seasonremote-viewing— CRV-adapted staging origins
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。
