Skip to main content
skill CX Codex

grounding — Claude Code skill: what it does, how to install

The grounding Claude Code skill grounds claims in assessments of biological targets. It runs on demand before drafting an assessment or passing a target brief to another bot.

MIT ★ 93 updated 2026-11-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Insilico-org/plsi --skill grounding -a claude-code
Open on GitHub

What grounding does

The skill checks what supports each target claim, asks for a source identifier, and explains assessment refusals. It also flags common reasoning errors, such as treating a screening result as proof of lethality or confusing a trial’s phase with its indication.

PMID, NCT, DOI, and drug-label identifiers are checked against a verification ledger; that check remains valid for thirty days. Other identifiers trace information to the dossier but do not establish a research result by themselves. Claims without an identifier belong in limitations; plsi targets assess rejects identifiers outside its closed list.

What it helps with

  • attach a source identifier to a target claim
  • separate a database entry from a study result
  • identify rule violations behind a rejected assessment
  • avoid treating gene essentiality as proof of target safety
  • record a limitation when a claim lacks a source

Example prompts for the agent

  • Check the source support for each claim in this target assessment.
  • Explain why this assessment is refused and list the violations.
  • Draft a target brief for another bot, separating database records from study findings.

How to install grounding

1Skills CLI (Vercel)

npx skills add Insilico-org/plsi --skill grounding -a claude-code

2Manually: put the files in place

~/.claude/skills/grounding/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/grounding/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about grounding

How do I install grounding in Claude Code?

Run npx skills add Insilico-org/plsi --skill grounding -a claude-code. The skill file is placed at ~/.claude/skills/grounding/SKILL.md.

What does grounding do?

It helps support claims in biological target assessments, explains refusal rules, and flags common errors in interpreting database records and research findings.

Which identifiers can support target claims?

Claims need an identifier from a closed list, such as a PMID, NCT, DOI, or ChEMBL ID. PMID, NCT, DOI, and drug-label identifiers are checked against a ledger, and that verification lasts thirty days.

Source text

SKILL.md · MIT
---
name: grounding
description: Use as PLSI Target Hunter on demand, before writing an assessment or handing a target brief to another bot - what a claim has to carry, what each refusal checks, what a database record can and cannot support, and the claims in this field that are most often wrong.
---

# Grounding a target claim

Craft, read when needed, not on
every run.

In a target report a sentence written from a paper looks the same as one written from memory. These rules keep them
apart; whether a target is worth pursuing stays your judgment.

## Every claim carries an identifier

Written inline in the sentence it supports:

| Form | From |
|---|---|
| `(PMID 12345678)` | `plsi evidence search --source pubmed\|europepmc` |
| `(NCT01234567)` | `plsi evidence search --source ctgov`, or the dossier's asset table |
| a DOI, `10.1234/abcd` | Open Genes rows, Europe PMC |
| a drug label set id (a UUID) | `plsi evidence search --source openfda` |
| a UniProt accession | the dossier's protein block |
| an AlphaFold id, `AF-<accession>-F1` | the structures block, where nothing is crystallised |
| a ChEMBL id, `CHEMBL<n>` | the asset table and the chemistry block |
| a PDB entry, written `PDB <code>` | the structures block |
| an Ensembl gene id, `EFO_<n>`, `MONDO_<n>`, `MGI:<n>`, `rs<n>` | the dossier itself |

This is the closed list: an identifier outside it is not a source and `assess` refuses the claim. A PDB entry needs
the literal `PDB` in front, because a bare four-character code can read as a year. The PMID, NCT, DOI and label ids
are checked against the verification ledger; the rest are carried for provenance and support "the dossier records
X", not "X was shown".

A PMID check confirms the record exists; a DOI check confirms only that the DOI resolves. For a directional or
mechanistic claim, read the abstract (`europepmc --query "EXT_ID:<pmid>"`). Verify before citing; a check holds for
thirty days:

```bash
plsi evidence verify --kind pmid --id <pmid>
plsi evidence verify --kind nct  --id <NCT id>
plsi evidence verify --kind doi  --id <doi>
```

With no identifier, put the claim in `limitations` as a gap instead of asserting it.

## The refusals

`plsi targets assess` returns every violation at once and writes nothing. Refusals 1-4 and 7 carry the rule
`target-refusal-<n>`; 5 and 6 come back as schema errors (`CLOSED_VOCABULARY`).

| | Refused | Because |
|---|---|---|
| 1 | a rationale, risk or strategy with no identifier | prose in the tables reads as a finding |
| 2 | a hand-harvested asset that duplicates one the dossier holds (its trial id is required and checked by 4) | a duplicate makes the field look wider than it is |
| 3 | a superlative with no source in the same sentence | a claim about everything that exists, from a table known to be incomplete |
| 4 | a PMID, NCT, DOI or label id the ledger has not verified in the last thirty days | a well-formed id is not a record |
| 5 | a rating outside `high`, `moderate`, `low`, `unknown`, or a verdict outside `pursue`, `monitor`, `deprioritize` | one closed vocabulary keeps sections comparable |
| 6 | a missing `falsifier` or an empty `limitations` | an assessment with no way to be wrong is a recommendation |
| 7 | a `platform_reads` entry with no billed call to that platform (for PandaOmics, that tool) in the egress ledger in the last thirty days | the platform cannot have been asked |

`target-refusal-3` is checked per sentence, so a citation in a neighbouring sentence does not earn the superlative,
and Markdown emphasis does not hide one ("no *identified*" is "no identified"). It is not checked on `limitations`,
where "no other registry was searched" is the honest sentence. No refusal checks that a
resolving citation is relevant; that is on you.

## What a database record supports

A curated record (an Open Genes lifespan row naming a DOI, an Open Targets safety liability naming a PMID) is a
curation decision, not a sentence from the paper.

- A record supports "the source records X, citing Y", not "X was shown".
- To claim the result, retrieve the source; `europepmc` returns abstracts.
- A finding written from the record alone passes no `text`; its quote stays unverified.

## Claims that are most often wrong

1. **"The knockout is lethal."** A high-throughput knockout screen is a first pass and often wrong for a given gene.
   Never state lethality, or lower a safety rating on it, without a targeted-knockout paper; if the literature says
   viable, report viable and the discordance.
2. **"Essential, therefore unsafe."** DepMap essentiality is about cell lines. Genetic constraint is the human read,
   and it is a bin, not a verdict.
3. **"Well characterised" or "novel".** Use Pharos' level (`Tclin`, `Tchem`, `Tbio`, `Tdark`) and say it is Pharos'
   judgment; when it disagrees with the ChEMBL counts, report both.
4. **"Phase 2."** A phase belongs to an indication. A registered trial with no phase is not phase 1. The sponsor is
   the trial record's lead sponsor, verbatim, never a developer inferred from press or recalled.
5. **"90% identical."** Quote the dossier's computed identities, never recalled ones. They are full-length; the
   active-site identity decides selectivity and is not in these sources. `query_identity` (coverage of the human
   protein) and `target_identity` (coverage of the other) are different numbers.
6. **"There is a pocket."** A tractability bucket is a prediction; a co-crystal is a molecule actually bound. "All
   structures read are apo", "no structure" and "a ligand has been bound" are three claims.
7. **"It is ligandable."** Potency filed against a protein family (`family_target`) is a claim about the family.
8. **"The evidence is thin."** Compare `shown` with `counts`: the curated lists are sampled at gather time. Say
   `n of N`.
9. **"Changing this gene extended lifespan."** Check `perturbed`: Open Genes files an experiment under a gene when it
   is in the mechanism, not only when it was changed. Those rows never reach a brief; `with-others` is a double
   mutant.
10. **"There is potent chemistry"** without a direction. IC50, Ki and Kd are inhibition and binding; EC50 is agonism.
    Quote `chemistry.inhibition` or `chemistry.activation`, whichever matches the direction of effect.
11. **"An approved drug exists"** without reading `withdrawn` and `black_boxed`: withdrawals and boxed warnings are
    precedent that argues the other way.
12. **A patent count as current activity.** Pharos' series stops years back (`patent_note`): it answers "has this been
    fought over", not "is anyone filing now".

Behind all of them: **an absence in a database is not an absence in the world**. The honest wording is "no
identified ...", written in `limitations`, or elsewhere only with a source identifier in the same sentence
(`target-refusal-3` refuses it anywhere else).

### Three absences

| What happened | Where it shows | What you may write |
|---|---|---|
| The source answered and holds nothing | `open_questions` | "no identified chemical matter in ChEMBL", a claim about one source, in `limitations` |
| The source did not answer | `unread`, `computed.not_read` | nothing about the target; gather again, or say it was not read |
| The lookup could not run | `computed.not_read`, with the reason | nothing about the target (an RNA gene has no UniProt accession) |

Check this before writing any sentence containing "no".

## Handing a target to the Research Orchestrator

`plsi targets brief --gene <SYMBOL> --question "<question>"` is the only way a dossier reaches it; it writes
nothing into a research topic or a note. Each row hands over the claim, the identifier, the stored record and a
suggested `design` and `species`. Save its output under `<PLSI_HOME>/work/<thread>/` and say, when passing it on:

- it is a **database record, not a quote**; the receiving bot retrieves any source it wants to quote;
- a residue number is UniProt's or a deposited structure's annotation, never recalled;
- `design` and `species` are suggestions from the record's shape, to be checked against the retrieved source;
- an animal result stays `species: animal`: it may refute a hypothesis about people, never support one.

It goes to PLSI as a file, and PLSI decides whether it reaches another bot.

© Insilico-org · MIT · Insilico-org/plsi

Similar skills

All skills for Science and research →

From the same set85

The whole set →
run This Claude Code skill runs a PLSI research cycle for a project topic. It follows the cursor for one assigned move, saves the result, then stops when the budget or topic state calls for it. CX Codex +1 ★ 93repo stars stack This Claude Code skill evaluates supplements for longevity goals against research and personal care context. It activates for questions about vitamins, supplements, or an existing stack. CX Codex +1 ★ 93repo stars urgent The urgent Claude Code skill detects emergencies and mental-health crises from user messages, bot flags, or critical values. It pauses other flows and directs the person to care. CX Codex +1 ★ 93repo stars exercise This Claude Code skill builds exercise plans from health-state data and research. For a single upcoming workout, it uses recent Hevy sessions and submits the session for approval. CX Codex +1 ★ 93repo stars report A Claude Code skill turns target dossiers and assessments into evidence-based reports. It runs when a target evaluation or shortlist is handed over to PLSI. CX Codex +1 ★ 93repo stars physicians This Claude Code skill prepares visit materials and handles communication with physicians. It activates before or after an appointment, when finding a clinician, or when a follow-up is due. CX Codex +1 ★ 93repo stars charts A skill for Claude Code turns PLSI data into charts and explains their visual form. It activates when a graph can clarify a trend, a reference-range result, or past predictions. CX Codex +1 ★ 93repo stars trajectory The trajectory Claude Code skill compares a proposed plan with the current course and models alternative scenarios. It runs after a plan proposal or a request to assess where the current path leads. CX Codex +1 ★ 93repo stars

Project sponsors

Companies that keep this analytics open