bioepic-data/ecosim-agent / .agents/skills/plant-trait-target-deriver
plant-trait-target-deriver
VerifiedUse this skill when you need to derive, from web-sourced evidence, typical values for a named plant's annual GPP, LAI, specific LAI or specific leaf area, Rubisco Vcmax at 25oC, Jmax at 25oC, root-to-shoot ratio, rooting depth, leaf protein nitrogen, and leaf chlorophyll nitrogen.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.1 KB |
| references/trait_derivation_guide.md | markdown | 3.0 KB |
| references/trait_output_schema.md | markdown | 727 B |
references/trait_derivation_guide.md
View on GitHub# Trait Derivation Guide
Use this guide when deriving a compact species trait summary for a named plant.
## Recommended source hierarchy
### Identity and growth form
- [Plants of the World Online](https://powo.science.kew.org/?locale=en_US)
- USDA species pages or equivalent official species profiles
Use these to resolve:
- accepted scientific name
- family
- woody vs herbaceous form
- annual vs perennial habit
### General ecology and crop constraints
- [FAO ECOCROP](https://www.fao.org/geospatial/data-and-tools/data-portals/ecocrop/en)
- USDA crop or forestry pages
- US Forest Service species syntheses
- FEIS species reviews
Useful for:
- climate envelope
- phenology
- growth habit
- rooting tendency
- canopy characteristics
### Trait databases and literature
- [TRY Plant Trait Database](https://www.try-db.org/TryWeb/Home.php/RegStart.php)
- peer-reviewed species, genus, or functional-type studies
Useful for:
- SLA
- nitrogen concentrations
- photosynthetic parameters
- root:shoot allocation
## Trait-by-trait recommendations
### Annual GPP
Preferred evidence:
- flux tower studies in stands dominated by the target species
- crop productivity papers
- ecosystem carbon balance papers
Fallback:
- functional-type-level range with strong caveat
### LAI
Preferred evidence:
- field observations
- crop manuals
- canopy structure papers
- flux metadata if clearly species-relevant
### Specific LAI / SLA
Preferred evidence:
- trait databases
- leaf economics studies
- species physiology papers
Interpretation:
- default to specific leaf area unless the user specifies a different meaning
- final preferred unit for EcoSIM-facing output: `m2 gC-1`
- when literature reports dry-mass SLA, convert to `m2 gC-1` only if leaf carbon fraction is given or can be justified from the same source or a tightly matched source
### Vcmax25 and Jmax25
Preferred evidence:
- peer-reviewed gas exchange studies
- trait compilations reporting standardized values at 25oC
Avoid:
- rough conversions from unrelated temperatures without a cited method
### Root-to-shoot ratio
Preferred evidence:
- biomass partitioning studies
- forestry allometry papers
- crop allocation studies
### Rooting depth
Preferred evidence:
- crop handbooks
- forestry or root ecology papers
- species reviews
### Leaf protein nitrogen
Preferred evidence:
- leaf biochemistry or nitrogen allocation studies
Avoid:
- substituting total leaf nitrogen unless clearly noted as a proxy
### Leaf chlorophyll nitrogen
Preferred evidence:
- chlorophyll-N allocation studies
- papers partitioning photosynthetic nitrogen pools
Avoid:
- inferring from total chlorophyll alone unless the paper gives a supported relationship
## Provenance labels
Use one of:
- `species-sourced`
- `genus-inferred`
- `functional-type-inferred`
- `no-defensible-estimate`
## Minimal final note
When values come from mixed evidence, say so directly:
`This summary combines species-level measurements where available with genus- or functional-type inference for sparse traits.`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |