document-insect-sighting
정보
이 스킬은 GPS, 사진, 행동 기록과 같은 구조화된 데이터로 곤충 관찰을 기록하고, 예비 식별을 수행합니다. 시민 과학 플랫폼(iNaturalist 등)에 기여하거나 개인 관찰 일지를 구축하는 데 활용할 수 있도록 설계되었습니다. 개발자는 이를 통해 애플리케이션에 생태 데이터 수집 기능을 추가할 수 있습니다.
빠른 설치
Claude Code
추천npx 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/document-insect-sightingClaude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요
문서
Document Insect Sighting
Record insect sightings with structured data, quality photographs, and citizen science submission for biodiversity research.
适用场景
- You encounter an insect you want to document for personal records or research
- You are contributing observations to citizen science platforms such as iNaturalist or BugGuide
- You are building a systematic observation journal for a habitat or region
- You want to support ecological surveys with georeferenced, photographed records
- You are a beginner learning to notice and record insect diversity
输入
- 必需: An insect sighting (live insect in the field or recently encountered specimen)
- 必需: A camera or smartphone capable of close-up photography
- 可选: GPS device or smartphone with location services enabled
- 可选: Notebook or field journal for written observations
- 可选: Hand lens (10x) for fine detail observation
- 可选: Ruler or coin for photographic scale reference
- 可选: iNaturalist account or equivalent citizen science platform account
步骤
第 1 步:Record Location, Date, and Weather
Capture the context before approaching the insect. Many species are habitat-specific and seasonally active, so this metadata is as important as the photograph itself.
Sighting Record — Context:
+--------------------+------------------------------------------+
| Field | Record |
+--------------------+------------------------------------------+
| Date | Full date and time (e.g., 2026-06-15, |
| | 14:30 local time) |
+--------------------+------------------------------------------+
| Location | GPS coordinates if available; otherwise |
| | describe precisely (e.g., "south bank of |
| | Elm Creek, 200m east of footbridge") |
+--------------------+------------------------------------------+
| Elevation | Meters above sea level if available |
+--------------------+------------------------------------------+
| Weather | Temperature (estimate is fine), cloud |
| | cover, wind, recent rain |
+--------------------+------------------------------------------+
| Season phase | Early spring, late spring, summer, early |
| | autumn, late autumn, winter |
+--------------------+------------------------------------------+
预期结果: A complete context record with date, time, precise location (ideally GPS coordinates), and weather conditions at the time of observation.
失败处理: If GPS is unavailable, describe the location relative to landmarks (trail junctions, buildings, water features) with enough detail that the site could be relocated. If weather data is uncertain, estimate temperature range and note "overcast" or "clear" rather than leaving the field blank.
第 2 步:Document Habitat and Microhabitat
Record where within the landscape the insect was found and what immediate substrate or structure it was using.
Habitat Recording:
+--------------------+------------------------------------------+
| Factor | Record |
+--------------------+------------------------------------------+
| Broad habitat | Deciduous forest, grassland, wetland, |
| | urban garden, riparian corridor, desert |
+--------------------+------------------------------------------+
| Microhabitat | Underside of leaf, bark crevice, flower |
| | head, soil surface, under rock, on water |
| | surface, in flight |
+--------------------+------------------------------------------+
| Substrate | Specific plant species if known, dead |
| | wood, dung, carrion, bare soil, rock |
+--------------------+------------------------------------------+
| Plant association | What plant is the insect on or near? |
| | (host plant relationships are diagnostic) |
+--------------------+------------------------------------------+
| Light conditions | Full sun, partial shade, deep shade |
+--------------------+------------------------------------------+
| Moisture | Dry, damp, wet, submerged margin |
+--------------------+------------------------------------------+
预期结果: A description of the habitat that places the insect in ecological context, including both the broad landscape and the immediate microhabitat where the insect was found.
失败处理: If the microhabitat is difficult to characterize (e.g., insect in flight), note what it was flying near or what it landed on. Record "in flight, 1m above meadow grasses" rather than leaving the field blank.
第 3 步:Photograph with Diagnostic Quality
Good photographs are the single most important element of a sighting record. Citizen science identifications rely almost entirely on image quality.
Photography Protocol:
Shots to take (in priority order):
1. DORSAL (top-down) — shows wing pattern, body shape, coloration
2. LATERAL (side view) — shows leg structure, body profile, antennae
3. FRONTAL (head-on) — shows eyes, mouthparts, antennae base
4. VENTRAL (underside) — if accessible, shows leg joints, abdominal pattern
5. SCALE REFERENCE — place a coin, ruler, or finger near the insect
for size comparison (do not touch the insect)
Tips for quality macro photographs:
- Get as close as your camera allows while maintaining focus
- Use natural light; avoid flash if possible (causes glare and flattens detail)
- Shoot against a neutral background when feasible (leaf, paper, hand)
- Hold the camera parallel to the insect's body plane for maximum sharpness
- Take multiple shots at each angle — at least 3 per view
- If the insect is moving, use burst mode or continuous shooting
- Photograph the insect in situ first, then closer shots if it remains
- Include at least one photo showing the insect in its habitat context
- If wings are open, photograph quickly — the pattern may change when
wings close (especially butterflies and dragonflies)
预期结果: At least 3 usable photographs: one dorsal, one lateral, and one with scale reference. Ideally 5 or more images covering multiple angles.
失败处理: If the insect moves before multiple angles are captured, prioritize the dorsal view (top-down) as it carries the most diagnostic information for identification. A single sharp dorsal photograph is better than multiple blurry images. If the insect flies away before any photograph, sketch the body shape and note colors from memory immediately.
第 4 步:Note Behavior and Interactions
Behavioral observations add ecological value that photographs alone cannot capture.
Behavioral Notes:
+--------------------+------------------------------------------+
| Category | Record what you observe |
+--------------------+------------------------------------------+
| Activity | Feeding, flying, resting, mating, |
| | ovipositing (egg-laying), burrowing, |
| | grooming, basking |
+--------------------+------------------------------------------+
| Movement | Crawling, hovering, darting, undulating |
| | flight, walking on water, jumping |
+--------------------+------------------------------------------+
| Feeding | What is it eating? Nectar, pollen, leaf |
| | tissue, other insects, dung, sap? |
+--------------------+------------------------------------------+
| Interactions | Other insects nearby? Being predated? |
| | Ants attending? Parasites visible? |
+--------------------+------------------------------------------+
| Sound | Buzzing, clicking, stridulation (wing or |
| | leg rubbing)? Silent? |
+--------------------+------------------------------------------+
| Abundance | Solitary individual, a few, many (swarm, |
| | aggregation)? |
+--------------------+------------------------------------------+
| Duration | How long did you observe? |
+--------------------+------------------------------------------+
预期结果: At least 3 behavioral observations recorded: activity, movement pattern, and abundance.
失败处理: If the insect is encountered briefly (e.g., lands and immediately flies away), record what you did observe and note the observation duration. Even "resting on leaf surface, solitary, flew when approached, observation duration 5 seconds" is useful data.
第 5 步:Preliminary Identification to Order
You do not need to identify the species. Placing the insect into its order narrows identification significantly and helps citizen science reviewers.
Quick Key to Major Insect Orders:
1. Count the legs.
- 6 legs → insect (proceed below)
- 8 legs → arachnid (spider, tick, mite) — not an insect
- More than 8 legs → myriapod (centipede, millipede) — not an insect
- Wings but hard to count legs → likely insect; look at wings
2. Examine the wings.
- Hard front wings (elytra) covering body → Coleoptera (beetles)
- Scaly wings, often colorful → Lepidoptera (butterflies/moths)
- Two wings + knob-like halteres → Diptera (flies)
- Four membranous wings + narrow waist → Hymenoptera (bees/wasps/ants)
- Half-leathery, half-membranous front wings → Hemiptera (true bugs)
- Large, transparent wings + long abdomen → Odonata (dragonflies/damselflies)
- Straight, narrow, leathery front wings → Orthoptera (grasshoppers/crickets)
- No wings, laterally flattened, jumps → Siphonaptera (fleas)
- No wings, pale body, in wood or soil → Isoptera (termites)
3. If unsure, note: "Order uncertain — resembles [description]"
预期结果: A preliminary identification to order (e.g., "Coleoptera — beetle") or an honest "order uncertain" with a physical description.
失败处理: If the insect does not clearly match any order in the quick key, record the body shape, wing type, and number of legs. Platforms like iNaturalist will accept "Insecta" as a starting identification, and community identifiers will refine it. An honest "unknown" is always better than a forced guess.
第 6 步:Submit to Citizen Science Platform
Upload the sighting to a platform where experts and community identifiers can verify and refine the identification.
Submission Checklist for iNaturalist (or equivalent):
1. Upload photographs — start with the best dorsal shot
2. Set location — use the map pin or enter GPS coordinates
3. Set date and time of observation
4. Add initial identification (order or family if known; "Insecta" if not)
5. Add observation notes:
- Habitat and microhabitat
- Behavior observed
- Approximate size
- Any sounds produced
6. Mark as "wild" (not captive/cultivated)
7. Set location accuracy — use the uncertainty circle to reflect GPS precision
8. Submit and monitor for community identifications
Data Quality Tips:
- Observations with 3+ photos from different angles get identified faster
- Including habitat context in one photo helps remote identifiers
- Adding a size reference dramatically improves identification accuracy
- Responding to identifier questions speeds up the process
- "Research Grade" status requires 2+ agreeing identifications at species level
预期结果: A complete observation submitted to a citizen science platform with photographs, location, date, and preliminary identification, ready for community review.
失败处理: If no internet access is available in the field, save all photographs and notes locally with the intention to upload later. Most platforms allow backdated submissions. If you do not have an account, store the record in your personal journal — the data still has value for your own learning and can be uploaded later.
验证清单
- Date, time, and precise location were recorded before approaching the insect
- Weather and habitat context were documented
- At least 3 photographs were taken from different angles
- At least one photograph includes a scale reference
- Behavior and activity were noted
- A preliminary identification to order was attempted (or honestly marked as unknown)
- The observation was submitted to a citizen science platform or stored in a structured journal
常见问题
- Approaching too quickly: Many insects flee when approached rapidly. Move slowly and avoid casting your shadow over the subject. Photograph from farther away first, then gradually close distance
- Ignoring habitat context: A photograph of an insect on a white wall loses the ecological context. Always include at least one in-situ photograph showing the insect in its natural setting
- Relying on a single photograph: One image is often insufficient for identification. Wing pattern, leg structure, and antennae may only be visible from specific angles
- Forgetting scale: Without a size reference, a 5mm beetle and a 50mm beetle can look identical in photographs. Always include a coin, ruler, or finger for scale
- Forcing an identification: Submitting a confident but incorrect identification on citizen science platforms creates noise for researchers. "Insecta" or "order unknown" is always acceptable and preferred over a wrong genus or species
- Not recording negatives: "No insects observed on milkweed patch" is valuable absence data for surveys. Record what you checked, not just what you found
相关技能
identify-insect— detailed morphological identification procedure when you need to go beyond preliminary order-level placementobserve-insect-behavior— structured ethological observation protocols for deeper behavioral studycollect-preserve-specimens— when a physical specimen is needed for definitive identificationsurvey-insect-population— scaling individual sightings into systematic population-level surveys
GitHub 저장소
연관 스킬
content-collections
메타이 스킬은 콘텐츠 콜렉션(Content Collections)을 위한 프로덕션 검증된 설정을 제공합니다. 콘텐츠 콜렉션은 Markdown/MDX 파일을 Zod 검증이 포함된 타입 안전한 데이터 콜렉션으로 변환해주는 TypeScript 최우선 도구입니다. 블로그, 문서 사이트 또는 콘텐츠 중심의 Vite + React 애플리케이션을 구축할 때 타입 안전성과 자동 콘텐츠 검증을 보장하기 위해 사용하세요. Vite 플러그인 구성과 MDX 컴파일부터 배포 최적화 및 스키마 검증에 이르기까지 모든 것을 다룹니다.
polymarket
메타이 스킬은 개발자들이 Polymarket 예측 시장 플랫폼을 활용한 애플리케이션을 구축할 수 있도록 지원하며, 거래 및 시장 데이터를 위한 API 통합 기능을 포함합니다. 또한 WebSocket을 통한 실시간 데이터 스트리밍을 제공하여 실시간 거래와 시장 활동을 모니터링할 수 있습니다. 이를 통해 거래 전략을 구현하거나 실시간 시장 업데이트를 처리하는 도구를 생성하는 데 활용할 수 있습니다.
creating-opencode-plugins
메타이 스킬은 개발자들이 명령어, 파일, LSP 작업 등 25개 이상의 이벤트 유형에 연결되는 OpenCode 플러그인을 만들 수 있도록 돕습니다. JavaScript/TypeScript 모듈을 위한 플러그인 구조, 이벤트 API 명세, 구현 패턴을 제공합니다. OpenCode AI 어시스턴트의 라이프사이클을 사용자 정의 이벤트 기반 로직으로 가로채거나, 모니터링하거나, 확장해야 할 때 사용하세요.
sglang
메타SGLang은 RadixAttention 프리픽스 캐싱을 활용하여 JSON, 정규식, 에이전트 워크플로우를 위한 고속 구조화 생성에 특화된 고성능 LLM 서빙 프레임워크입니다. 특히 반복되는 프리픽스가 있는 작업에서 상당히 빠른 추론 속도를 제공하여 복잡한 구조화 출력 및 다중 턴 대화에 이상적입니다. 제약 디코딩이 필요하거나 광범위한 프리픽스 공유가 있는 애플리케이션을 구축할 때는 vLLM과 같은 대안보다 SGLang을 선택하십시오.
