ワンクリックでManusで任意のスキルを実行

model-incorporation-request

スター2

フォーク0

更新日2026年7月1日 09:08

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".

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

ersilia-os

ersilia-os/ersilia-skills

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Model Incorporation Request

Your job is to open a model request issue on ersilia-os/ersilia that exactly mirrors the official model request form, using information extracted from the publication and source code repository.

Parse Arguments

--pdf <pdf-path> (required): local path to the publication PDF
--publication <url> (required): URL to the publication (DOI, arXiv, journal)
--source <url> (required): URL to the source code repository (GitHub, GitLab, Zenodo, etc.)

If any argument is missing, ask the user before proceeding.

Phase 1 – Extract Information

1a. Read the PDF

Extract:

Model name / what it does (for Title and Name)
What the model predicts or computes — in plain language (for Description)
Application areas and relevant keywords (for Tags)

1b. Fetch the source code repository

Use WebFetch on the repository URL (README and root files) to extract:

License — look for a LICENSE file or license field in pyproject.toml / setup.py / package.json
Any additional context for the description or tags

1c. Fetch the valid tag and license lists

Fetch both files at runtime:

https://raw.githubusercontent.com/ersilia-os/ersilia/master/ersilia/hub/content/metadata/tag.txt
https://raw.githubusercontent.com/ersilia-os/ersilia/master/ersilia/hub/content/metadata/license.txt

Both are newline-separated. Keep both lists in memory — you will validate tags and the license against them.

Phase 2 – Propose All Fields and Confirm

Present all proposed values in a single table and wait for the user's feedback before proceeding. Do not open the issue until the user explicitly confirms.

Field	Proposed value
Title	`🦠 Model Request: <Name>`
Name	...
Slug	...
Description	...
Tags	...
Publication	(from --publication argument)
Source Code	(from --source argument)
License	...

Field rules:

Title / Name <Name> should be concise (2–5 words), title-case, describing what the model does. The Name field is the same <Name> without the emoji prefix.

Slug Lowercase, hyphens only, 2–4 words maximum. Keep it short and memorable — it becomes part of the model's permanent identifier. Propose a single best option (e.g. mt-gnn-adme, morgan-fingerprints). If you find yourself using more than 4 words, trim ruthlessly.

Description 200–600 characters (hard limits from the GitHub form). Plain English, focused on what a user gets from running this model on a molecule. Do not start with "This model...". Do not include a character count in the table — just show the description text.

Tags Pick only from the tag list fetched in Phase 1c. Choose 2–4 tags maximum — only the most directly relevant ones. Do not tag everything that loosely applies; prefer precision over coverage. At least one is required.

License Use only values from the license.txt list fetched in Phase 1c. Use None if no LICENSE file is found.

After presenting the table, ask: "Does this look correct? Let me know any changes and I'll open the issue."

Phase 3 – Open the GitHub Issue

Use gh issue create to open the issue on ersilia-os/ersilia. Format the body to match exactly what the GitHub form produces when submitted — each field as a level-3 heading followed by its value:

### Model Name

<name>

### Model Description

<description>

### Slug

<slug>

### Tag

<tag1>, <tag2>

### Publication

<publication-url>

### Source Code

<source-url>

### License

<license>

Use a HEREDOC to pass the body:

gh issue create \
  --repo ersilia-os/ersilia \
  --title "<title>" \
  --label "new-model" \
  --body "$(cat <<'EOF'
<body>
EOF
)"

Phase 4 – Tell the User What Happens Next

After the issue is opened, print the issue URL and explain the next steps:

An Ersilia admin will review and approve the request
Once approved, a new model repository (eosXXXX) is created under ersilia-os
Fork that repository and clone it locally
Run /model-incorporation-metadata to fill in the metadata
Run /model-incorporation-code to wire up the model code
Run /ersilia-model-test to validate the model runs correctly before submitting a PR
Run /model-incorporation-reproduce to verify the model performs as reported in the paper

このリポジトリの他の Skills

同じリポジトリ

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

ersilia-model-test

ersilia-os/ersilia-skills

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.

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-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	model-incorporation-request
description	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".
allowed-tools	["Bash","Read","WebFetch","WebSearch","AskUserQuestion"]

Model Incorporation Request

Your job is to open a model request issue on ersilia-os/ersilia that exactly mirrors the official model request form, using information extracted from the publication and source code repository.

Parse Arguments

--pdf <pdf-path> (required): local path to the publication PDF
--publication <url> (required): URL to the publication (DOI, arXiv, journal)
--source <url> (required): URL to the source code repository (GitHub, GitLab, Zenodo, etc.)

If any argument is missing, ask the user before proceeding.

Phase 1 – Extract Information

1a. Read the PDF

Extract:

Model name / what it does (for Title and Name)
What the model predicts or computes — in plain language (for Description)
Application areas and relevant keywords (for Tags)

1b. Fetch the source code repository

Use WebFetch on the repository URL (README and root files) to extract:

License — look for a LICENSE file or license field in pyproject.toml / setup.py / package.json
Any additional context for the description or tags

1c. Fetch the valid tag and license lists

Fetch both files at runtime:

https://raw.githubusercontent.com/ersilia-os/ersilia/master/ersilia/hub/content/metadata/tag.txt
https://raw.githubusercontent.com/ersilia-os/ersilia/master/ersilia/hub/content/metadata/license.txt

Both are newline-separated. Keep both lists in memory — you will validate tags and the license against them.

Phase 2 – Propose All Fields and Confirm

Present all proposed values in a single table and wait for the user's feedback before proceeding. Do not open the issue until the user explicitly confirms.

Field	Proposed value
Title	`🦠 Model Request: <Name>`
Name	...
Slug	...
Description	...
Tags	...
Publication	(from --publication argument)
Source Code	(from --source argument)
License	...

Field rules:

Title / Name <Name> should be concise (2–5 words), title-case, describing what the model does. The Name field is the same <Name> without the emoji prefix.

License Use only values from the license.txt list fetched in Phase 1c. Use None if no LICENSE file is found.

After presenting the table, ask: "Does this look correct? Let me know any changes and I'll open the issue."

Phase 3 – Open the GitHub Issue

### Model Name

<name>

### Model Description

<description>

### Slug

<slug>

### Tag

<tag1>, <tag2>

### Publication

<publication-url>

### Source Code

<source-url>

### License

<license>

Use a HEREDOC to pass the body:

gh issue create \
  --repo ersilia-os/ersilia \
  --title "<title>" \
  --label "new-model" \
  --body "$(cat <<'EOF'
<body>
EOF
)"

Phase 4 – Tell the User What Happens Next

After the issue is opened, print the issue URL and explain the next steps:

An Ersilia admin will review and approve the request
Once approved, a new model repository (eosXXXX) is created under ersilia-os
Fork that repository and clone it locally
Run /model-incorporation-metadata to fill in the metadata
Run /model-incorporation-code to wire up the model code
Run /ersilia-model-test to validate the model runs correctly before submitting a PR
Run /model-incorporation-reproduce to verify the model performs as reported in the paper