add-score — Claude Code skill: formulas and installation
add-score — a Claude Code skill that adds a new derived measure to a PLSI map. It activates when a request needs a score or equation the existing maps do not compute.
MIT ★ 93 updated 2026-11-15
npx skills add Insilico-org/plsi --skill add-score -a claude-codeWhat add-score does
The skill adds a measure to a user PLSI map as a derived coordinate. It finds a published equation, checks its source, then confirms that the required coordinates and units are available. Unit conversion can be written into the formula.
Before installing the map for the user, the skill tests the equation against a worked example in a separate PLSI instance. A mismatch blocks installation. The reported value comes from plsi project, along with its unit, source, and the new states hash.
Lookup tables and fitted models cannot be expressed as a map formula, so those requests go to PLSI Engineer. Censored inputs can produce an error status when the formula uses comparisons, where, min, max, or abs. After a formula changes, older predictions are scored against their saved map snapshot.
What it helps with
- add a published measure to a PLSI map
- represent a composite outcome as one predicted value
- test an equation against a paper’s worked example
- convert an input unit inside a formula
Example prompts for the agent
- Add the eGFR measure to PLSI using the published CKD-EPI 2021 equation.
- Create a composite measure in the PLSI map from these coordinates.
- Find and verify the equation for this index, then test it against the paper’s example.
How to install add-score
1Skills CLI (Vercel)
npx skills add Insilico-org/plsi --skill add-score -a claude-code2Manually: put the files in place
~/.claude/skills/add-score/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/add-score/
1Skills CLI (Vercel)
npx skills add Insilico-org/plsi --skill add-score -a codex2Manually: put the files in place
.agents/skills/add-score/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Insilico-org/plsi --skill add-score -a cursor2Manually: put the files in place
.cursor/skills/add-score/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Insilico-org/plsi skills/processor/add-score2Manually: put the files in place
.github/skills/add-score/SKILL.md1Skills CLI (Vercel)
npx skills add Insilico-org/plsi --skill add-score -a gemini-cli2Platform CLI
gemini skills install https://github.com/Insilico-org/plsi --path skills/processor/add-scoreManually: put the files in place
.devin/skills/add-score/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about add-score
How do I install add-score in Claude Code?
Run npx skills add Insilico-org/plsi --skill add-score -a claude-code. The skill file is installed at ~/.claude/skills/add-score/SKILL.md.
What does add-score do?
It adds a measure missing from PLSI maps as a derived coordinate. The skill tests the formula against a published example before installation and gets the resulting value from plsi project.
What does add-score need to work?
It requires PLSI and its plsi commands. The formula’s source is searched and checked with plsi evidence search and plsi evidence verify.
Source text
SKILL.md · MIT
---
name: add-score
description: Use as PLSI Data Processor when PLSI asks for a score, ratio, index or published equation that no map computes yet (e.g. a lipid ratio, a kidney-function equation, a fibrosis index), so it becomes a derived coordinate the triad computes, stores, predicts and scores.
---
# PLSI add a score
A score is a safe formula inside a State Map (Tier 1): no code, no install step beyond the map. If the computation
cannot be written as one formula (lookup tables, a fitted model), say so in your `result` so PLSI hands it to PLSI Engineer (`engineer/extend`); Engineer not on the team: code extensions are off and PLSI offers "Add PLSI Engineer?".
## When to use
- The user names a score PLSI does not have, or a paper's equation would answer their question.
- A plan needs a composite outcome that should be predicted and scored as one value.
## Steps
1. Find the published formula and verify its source before using it.
```bash
plsi evidence search --source pubmed --query "<score name> equation validation"
plsi evidence verify --kind doi --id <doi>
```
2. Check the inputs. Each variable must be a coordinate with a canonical unit; read units from the map and convert
inside the formula when the paper uses another unit (e.g. creatinine umol/L -> mg/dL is `creatinine / 88.42`).
```bash
plsi maps show blood_phenoage
plsi maps show cardiometabolic
```
3. Write a user map `user_<score>.yaml` holding the input coordinates (copy them from `maps show`) plus one derived
coordinate:
```yaml
- id: egfr_ckd_epi_2021
label: eGFR (CKD-EPI 2021)
kind: derived
unit: mL/min/{1.73_m2}
derive:
engine: expr
model: egfr_ckd_epi_2021
inputs: [creatinine]
formula: >-
142 * min(creatinine / 88.42 / where(female, 0.7, 0.9), 1) ** where(female, -0.241, -0.302)
* max(creatinine / 88.42 / where(female, 0.7, 0.9), 1) ** -1.2 * 0.9938 ** age * where(female, 1.012, 1)
correspondence_type: validated
sources: [{kind: doi, id: <verified doi>}]
```
Formula language: numbers, `+ - * / **`, comparisons, `log ln log10 exp sqrt abs min max`, `where(cond, a, b)`;
variables are the `inputs` plus `age` (years at the draw), `female`, `male` (1 or 0). `inputs` must list exactly
the coordinate variables the formula uses.
4. Validate, then prove the formula on the paper's worked example in a fresh scratch instance per score (`scratch-<score>`, sex and birth year from the worked
example) before using it for the user: ingest the example's input values, project, and compare with the published result (allow rounding).
```bash
plsi maps validate user_egfr.yaml --live
plsi init --instance scratch-egfr --birth-year <example birth year> --sex <example sex> --relation sample
plsi maps install --instance scratch-egfr --file user_egfr.yaml
plsi ingest --instance scratch-egfr --file example_inputs.json
plsi project --instance scratch-egfr --map user_egfr
```
5. Install for the user and project, then send ONE `result` to PLSI with the value, unit, source, the new `states`
hash and any worked-example mismatch (also when the install was refused):
```bash
plsi maps install --instance <instance> --file user_egfr.yaml
plsi project --instance <instance> --map user_egfr
```
## Rules
- Never compute a score yourself; the value is whatever `project` returns.
- No worked-example match, no install for the user. Say what did not match.
- A censored input (e.g. `<0.3`) is propagated as a bound only through formulas without comparisons, `where`, `min`,
`max` or `abs`; otherwise the score shows status `error` with that reason. Say so in your `result`.
- Bump `map_version` when you change a formula; old predictions keep scoring against their snapshot.
- The map stays `claim_level: designed` until a prediction on the score has been scored.
© Insilico-org · MIT · Insilico-org/plsi