원클릭으로 Manus에서 모든 스킬 실행

ersilia-model-test

스타2

포크0

업데이트2026년 7월 1일 09:49

Tests an Ersilia Model Hub model before hub incorporation. Runs `ersilia test --shallow` on a locally cloned model repository, reads the results, identifies failing checks, and proposes a debugging strategy to the user — but does not apply fixes automatically. Use this skill whenever a user wants to test, validate, or debug an Ersilia model before submitting it to the hub, mentions test failures, says "the test is failing", or is preparing a model for hub incorporation. Trigger even if the user just says "test the model" or "run ersilia test" in any Ersilia context.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

ersilia-os

ersilia-os/ersilia-skills

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Ersilia Model Tester

Your job is to run the Ersilia shallow test on a locally cloned model, read the results, and tell the user what is failing and how to fix it. You propose fixes — you do not apply them unless the user explicitly asks you to.

What you receive

The model ID (format: eos + 4 alphanumeric characters, e.g. eos4ywv)
The local path to the cloned GitHub repository (e.g. /home/user/eos4ywv)

If either is missing, ask the user before proceeding.

Step 1: Run the shallow test (once)

Always run inside the ersilia conda environment, from the model directory:

cd <model_path>
conda run -n ersilia ersilia test <model_id> --shallow --from_dir <model_path>

This produces a JSON report <model_id>-test.json in the current directory. Capture the terminal output too — it often contains error tracebacks that explain why a check failed.

Important: Never delete, remove, or modify any directories or folders. Never touch run.sh. Never touch run_output.csv.

Step 2: Read and triage the results

Read <model_id>-test.json. It contains boolean results for each check.

Ignore — these are auto-populated after hub merge and not your concern:

Any check with value "not present" (S3 URL, DockerHub, model size, incorporation date, computational performance, release version, etc.)

Focus on everything that is false. Group them:

Run failure (simple_model_run: false) — the model crashes on execution. This is the most critical. All other checks below it will also be false as a side effect — focus on fixing the run first.
Metadata failures — fields like model_description, model_task, etc.
File structure failures — columns format, install.yml syntax, etc.
Consistency failures — output varies between runs, or differs between Ersilia CLI and direct bash execution.

Step 3: Diagnose each failure

For each failing check, read the relevant files to understand the root cause. Do not guess — look at the actual code and config. Relevant files to read:

Failing check	Files to read
`simple_model_run`	`model/framework/code/main.py`, terminal error output
`model_description`	`metadata.yml` (check Description field length — max 600 characters)
`metadata_*`	`metadata.yml`
`columns` / `metadata_dim_and_run_column_file_dim_check`	`model/framework/columns/run_columns.csv`, `metadata.yml`
`install_yaml_check`	`install.yml`
`check_consistency_of_model_output` / `rmse_mean`	`model/framework/code/main.py` (look for random seeds, stochastic operations)

See references/troubleshooting.md for specific causes and fixes for each check type.

Step 4: Present findings and proposed fixes to the user

After diagnosing, give the user a clear summary structured like this:

Test result: X checks failing (ignoring "not present" fields)

For each failing check:

What failed: name of the check
Why: one-sentence root cause based on what you read in the code
Proposed fix: exactly what to change and in which file

Then ask: "Would you like me to apply these fixes?"

Only apply fixes if the user says yes. If the user asks you to apply, make the changes and then re-run the test to confirm.

Cleanup

After presenting findings (or after any re-run), delete the JSON report:

rm -f <model_path>/<model_id>-test.json

Model template structure (for reference)

<model_id>/
├── model/
│   ├── framework/
│   │   ├── run.sh              ← NEVER modify
│   │   ├── code/
│   │   │   └── main.py
│   │   ├── examples/
│   │   │   ├── run_input.csv
│   │   │   └── run_output.csv  ← NEVER modify
│   │   └── columns/
│   │       └── run_columns.csv
│   └── checkpoints/            ← do not modify
├── metadata.yml
└── install.yml

Next steps

Remaining steps:

Run /model-incorporation-reproduce to verify the model performs as reported in the paper

Push and open a pull request from your fork to ersilia-os/eosXXXX

이 저장소의 다른 Skills

같은 저장소

model-incorporation-code

ersilia-os/ersilia-skills

Integrate the code of a new ML model into an Ersilia model template repository. Use this skill whenever the user has: (1) a source model repository with the original ML code, (2) an ersilia-model-template repository (already forked/cloned), and (3) optionally a PDF of the scientific article — and needs to wire up the actual model code. The skill handles all coding steps: copying checkpoints with git-lfs tracking, adapting main.py to replace the molecular-weight placeholder with real inference, creating run_columns.csv, updating install.yml with pinned versions, and producing run_input.csv and run_output.csv by actually running the model. Trigger on phrases like "incorporate model code", "fill in the template", "adapt main.py", "add checkpoints", "create run_columns", "create install.yml for ersilia", "generate example files for ersilia model", or any request to wire a source model into the eos-template format.

2026-07-012

model-incorporation-metadata

ersilia-os/ersilia-skills

Fills in the required metadata fields for an Ersilia Model Hub model, given the metadata.yml file and the original publication PDF. Reads the source code URL directly from the metadata file — no need to provide it separately. Use this skill whenever a user wants to populate, complete, or update a metadata.yml file for an Ersilia model, mentions an Ersilia model contribution, or is working on model metadata for the Ersilia Model Hub. Trigger even if the user just says "fill in the metadata" or "help me with the metadata.yml" in any Ersilia context.

2026-07-012

model-incorporation-request

ersilia-os/ersilia-skills

Open a model request issue on ersilia-os/ersilia for a new model to be incorporated into the Ersilia Model Hub. Use this skill whenever a user wants to request a new model, open a model request, or start the model incorporation pipeline. The skill reads the publication PDF and source code repository to propose all required fields, asks the user to confirm, then opens the GitHub issue mimicking the official ersilia-os/ersilia model request form. Trigger on phrases like "request a model", "open a model request", "add a new model to the hub", "start model incorporation", or "open an issue for a new model".

2026-07-012

model-incorporation-reproduce

ersilia-os/ersilia-skills

Reproduce the key performance metrics reported in a paper for an Ersilia Model Hub model. Reads the publication PDF, extracts reported results (AUC, RMSE, accuracy, R², etc.), assesses whether each benchmark dataset is publicly available, acquires the datasets, runs the incorporated model, and compares reproduced vs reported metrics with tolerance-aware verdicts. Use this skill whenever a user wants to verify that an incorporated model performs as described in its paper, after running model-incorporation-code. Trigger on phrases like "reproduce the results", "check model performance", "validate the model against the paper", "does the model match what the paper reports", "benchmark the model", or any request to verify an incorporated Ersilia model against its publication.

2026-06-302

literature-digest

ersilia-os/ersilia-skills

Produce the weekly Ersilia literature digest. Primary mission: surface every model and dataset that could plausibly join the Ersilia Model Hub — across all six Hub task families (Property prediction, Activity prediction, Featurization, Projection, Similarity search, Generation), with antimicrobial / antipathogen drug discovery as the most-prioritised disease lens. Secondary mission: keep the team current on agentic AI for science, automation in chemistry, open-source drug discovery, and global health. Apply an explicit LMIC and decolonisation lens throughout. Use this skill whenever the user asks to prepare, run, or refresh the literature digest. Triggers include: "weekly literature digest", "literature digest for Ersilia", "/literature-digest", "lit digest this week", "what did we miss last week", "digest the literature". Always use this skill for digest requests even if the ask seems simple.

2026-06-302

literature-review

ersilia-os/ersilia-skills

Conduct deep, structured literature research for Ersilia drug discovery work. Use this skill whenever a user asks to find, review, or summarise scientific papers about a disease, biological target, compound class, or AI/ML method in the context of drug discovery — especially for neglected tropical diseases (NTDs), antimicrobial resistance (AMR), or global health. Triggers include target names (e.g. Mtb, PfDHFR, TryR, InhA), disease names (e.g. malaria, leishmaniasis, tuberculosis, Chagas, schistosomiasis), model or method types (e.g. GNN, QSAR, ChemBERTa), and requests like "find papers on", "what does the literature say about", "summarise research on", "literature review for", or "what's been published about". Always use this skill for Ersilia-context literature work, even if the request is phrased casually.

2026-06-162

name

ersilia-model-test

description

Ersilia Model Tester

What you receive

The model ID (format: eos + 4 alphanumeric characters, e.g. eos4ywv)
The local path to the cloned GitHub repository (e.g. /home/user/eos4ywv)

If either is missing, ask the user before proceeding.

Step 1: Run the shallow test (once)

Always run inside the ersilia conda environment, from the model directory:

cd <model_path>
conda run -n ersilia ersilia test <model_id> --shallow --from_dir <model_path>

This produces a JSON report <model_id>-test.json in the current directory. Capture the terminal output too — it often contains error tracebacks that explain why a check failed.

Important: Never delete, remove, or modify any directories or folders. Never touch run.sh. Never touch run_output.csv.

Step 2: Read and triage the results

Read <model_id>-test.json. It contains boolean results for each check.

Ignore — these are auto-populated after hub merge and not your concern:

Any check with value "not present" (S3 URL, DockerHub, model size, incorporation date, computational performance, release version, etc.)

Focus on everything that is false. Group them:

Run failure (simple_model_run: false) — the model crashes on execution. This is the most critical. All other checks below it will also be false as a side effect — focus on fixing the run first.
Metadata failures — fields like model_description, model_task, etc.
File structure failures — columns format, install.yml syntax, etc.
Consistency failures — output varies between runs, or differs between Ersilia CLI and direct bash execution.

Step 3: Diagnose each failure

For each failing check, read the relevant files to understand the root cause. Do not guess — look at the actual code and config. Relevant files to read:

Failing check	Files to read
`simple_model_run`	`model/framework/code/main.py`, terminal error output
`model_description`	`metadata.yml` (check Description field length — max 600 characters)
`metadata_*`	`metadata.yml`
`columns` / `metadata_dim_and_run_column_file_dim_check`	`model/framework/columns/run_columns.csv`, `metadata.yml`
`install_yaml_check`	`install.yml`
`check_consistency_of_model_output` / `rmse_mean`	`model/framework/code/main.py` (look for random seeds, stochastic operations)

See references/troubleshooting.md for specific causes and fixes for each check type.

Step 4: Present findings and proposed fixes to the user

After diagnosing, give the user a clear summary structured like this:

Test result: X checks failing (ignoring "not present" fields)

For each failing check:

What failed: name of the check
Why: one-sentence root cause based on what you read in the code
Proposed fix: exactly what to change and in which file

Then ask: "Would you like me to apply these fixes?"

Only apply fixes if the user says yes. If the user asks you to apply, make the changes and then re-run the test to confirm.

Cleanup

After presenting findings (or after any re-run), delete the JSON report:

rm -f <model_path>/<model_id>-test.json

Model template structure (for reference)

<model_id>/
├── model/
│   ├── framework/
│   │   ├── run.sh              ← NEVER modify
│   │   ├── code/
│   │   │   └── main.py
│   │   ├── examples/
│   │   │   ├── run_input.csv
│   │   │   └── run_output.csv  ← NEVER modify
│   │   └── columns/
│   │       └── run_columns.csv
│   └── checkpoints/            ← do not modify
├── metadata.yml
└── install.yml

Next steps

Remaining steps:

Run /model-incorporation-reproduce to verify the model performs as reported in the paper

Push and open a pull request from your fork to ersilia-os/eosXXXX