read-garden
について
`read-garden`スキルは、開発者がプログラムによって庭の健全性を評価するための構造化されたプロトコルを提供します。これは植物と土壌を体系的に観察するために、Coordinate Remote Viewingの段階を適応させたものです。植物のストレス、季節の変化、または定期的なモニタリングによってトリガーされ、感覚データの収集、パターン認識、健全性トリアージマトリックスを通じて導きます。このツールは、データに基づいた園芸の意思決定を情報提供するため、あらゆる介入の前に使用するように設計されています。
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 and assess garden with structured sensory protocol before any intervention decision.
When Use
- Before intervention — read garden first, act second
- Plants show stress (yellow, wilt, curl, spots)
- Seasonal transitions (spring wakeup, autumn decline) need check
- New garden site eval before plant
- Regular (weekly or biweekly) garden health monitoring
- After extreme weather (frost, heat wave, heavy rain)
Inputs
- Required: Physical access to garden
- Required: Garden journal or notebook for record
- Optional: Prior observation records for compare
- Optional: Soil thermometer, pH strips, moisture meter
- Optional: Hand lens or magnifier (pest/disease ID)
Steps
Step 1: Meditate Checkpoint — Pre-Entry Clearing
Before enter garden, 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.
Got: Calm, receptive state. No preconceptions about what you find.
If fail: Cannot release expectations (strong worry over specific plant, frustration from recent loss)? Acknowledge emotion, write as "AOL: [concern]", proceed. Naming reduces influence.
Step 2: Stage I — Gestalt Impression
Walk garden 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)
Got: Brief holistic record of garden state. No analysis or diagnosis.
If fail: Start diagnose right away (e.g., "the squash wilts because...")? Write "AOL: [diagnosis]". Return to pure observation. Analysis comes in Stage III.
Step 3: Stage II — Sensory Layer
Move through garden bed by bed. Engage all senses for 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"
Got: Detailed sensory record per bed or zone. Descriptive language only.
If fail: Catch self diagnose (name disease, blame pest)? Write "AOL: [diagnosis]". Return to raw observation. Name comes later — data first.
Step 4: Stage III — Pattern Recognition
Now, and only now, start connect observations 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
Got: One or more tentative diagnoses backed by multiple independent observations.
If fail: No clear pattern? Garden may be healthy (not all is problem) or signals too early to read. Record observations. Reassess in one week. Time clarifies what one visit cannot.
Step 5: Heal Checkpoint — Garden Health Triage
Convert observations into 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)
Got: Triaged action list. Clear priorities and timeline.
If fail: All feels like red? You may be in anxiety mode, not observation mode. Return to meditate checkpoint (Step 1). Re-enter. True emergencies rare — most garden problems develop slow, can wait a day.
Step 6: Record and Track
Close observation session with 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: ___________
Got: Complete dated observation record. Comparable to prior visits.
If fail: Journaling burdensome? Cut to minimum: date, weather, triage summary, one observation per bed. Consistency beats detail.
Checks
- Meditate checkpoint done before enter garden
- Gestalt impression recorded before examine individual plants
- Sensory observations use descriptive language (no diagnosis in Stage II)
- AOLs identified, set aside (not acted on premature)
- Pattern analysis covers spatial, temporal, population factors
- Triage matrix done with clear priority levels
- Observation record dated, filed in garden journal
- Actions match triage level (no over-treat green items)
Pitfalls
- Confirmation bias: Enter garden looking for specific problem = guarantee you find it (or look-alike). Meditate checkpoint prevents this
- Diagnose in Stage II: Name disease during sensory observation biases all next data. Stay with descriptors until Stage III
- Treat green as amber: Most garden "problems" resolve themselves. Spray or prune at first sign often causes more harm than original symptom
- Skip record: No journal = every visit starts from scratch. Patterns emerge only over time — time needs records
- AOL suppress vs manage: Goal is not zero analytical thoughts — impossible. Goal: notice, name, set aside until data supports or refutes
- Over-intervention: Reading protocol should boost confidence, cut number of actions. Doing more after reading? Maybe treating anxiety, not garden
See Also
meditate— Pre-entry clearing protocol (full meditation procedure)heal— Health triage pattern used in checkpointprepare-soil— Soil assessment overlaps with soil observation layercultivate-bonsai— Bonsai health assessment follows same staged observationplan-garden-calendar— Observation records inform calendar tweaks mid-seasonremote-viewing— CRV-adapted staging protocol originates from this skill
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。
