asb-skill-collections

ASB Skill Collections

Evidence-grounded skills and software-tool records for scientific AI agents,
distilled from published method papers and their code by the AgenticScienceBuilder pipeline.

A skill is a short procedure that an AI agent can read and follow. The AgenticScienceBuilder (ASB) pipeline writes each one from a published method paper (journal article or preprint) and, where one exists, its public code repository, anchors it to verbatim evidence from those sources (for repo-oa papers, the repository’s own documentation; CONTENT_POLICY.md), annotates it with EDAM terms, and passes it through a licence and PII gate before release. This repository is the public registry of those collections. It holds the install and search tooling, the governance of the community that curates them, and the release registry. Released content lives in per-domain repositories. The project started at the Dagstuhl Seminar Computational Metabolomics (26181, 26 to 30 April 2026).

Releases

The registry collections.yaml records the released collections of ten domains. Each release is deposited on Zenodo and pinned to its domain repository asb-skills-<domain>, commit and tree digest. The domain repositories are private; the Zenodo record of each release carries the full collection. This repository holds the tooling and the registry.

Domain	Release	Skills	Tools	Workflows	Papers	Version DOI
metabolomics	metabolomics-v3.0.2	11,830	1,989	20	477	10.5281/zenodo.24122117
agentic-ai	agentic-ai-v1.0.1	668	215	2	29	10.5281/zenodo.24122112
astronomy	astronomy-v1.0.1	1,671	415	2	100	10.5281/zenodo.24122111
epigenomics	epigenomics-v2.0.1	2,295	532	2	92	10.5281/zenodo.24122116
genomics	genomics-v1.0.1	3,246	867	2	137	10.5281/zenodo.24122105
metabarcoding	metabarcoding-v1.0.1	803	203	2	29	10.5281/zenodo.24122109
metagenomics	metagenomics-v1.0.1	2,754	717	2	117	10.5281/zenodo.24122106
multi-omics	multi-omics-v1.0.1	787	211	2	29	10.5281/zenodo.24122110
proteomics	proteomics-v1.0.1	558	163	2	28	10.5281/zenodo.24122102
transcriptomics	transcriptomics-v2.0.1	11,256	2,086	2	450	10.5281/zenodo.24122113

The concept DOI of each domain is in collections.yaml. The rest of this file uses metabolomics v3 as its worked example; asbb fetch and asbb install take any registered collection, for example --collection genomics/v1.

Metabolomics v3

Release metabolomics-v3.0.2: 11,830 skills across 1,989 tools, distilled from 477 published method papers (journal articles and preprints), plus 20 composite workflow super-skills that chain the atomic skills into end-to-end pipelines. The release is deposited as 10.5281/zenodo.24122117. Coverage is mostly LC-MS/MS, with LC-MS, GC-MS, mass-spectrometry imaging, ion mobility and lipidomics, some NMR, and multi-omics, statistics and pathway tools.

The collection is released from the private domain repository asb-skills-metabolomics. The marketplace of this repository serves the v3 collection and the v2-derived technique packs from that domain repository.

Layer	Contents	State
ASB-Skills	evidence-grounded procedural skills	released
ASB-Workflows	composite end-to-end pipeline super-skills	released
ASB-Tools	deduplicated software-tool records with EDAM terms and DOIs	released
ASB-Evaluation definitions	definitions for per-paper tasks and claim-retrieval tests	not published; definitions only, with no validated benchmark, reference results or agent-performance leaderboard
ASB-Capsules	raw per-paper pipeline outputs, for full traceability	later

Install

Claude Code (plugin marketplace):

/plugin marketplace add HolobiomicsLab/asb-skill-collections
/plugin install metabolomics@asb-skill-collections
# Or one of the eight technique packs, for example:
/plugin install metabolomics-lc-ms@asb-skill-collections

The other released domains install the same way under their domain name, for example /plugin install genomics@asb-skill-collections. Each marketplace entry points at its private domain repository, so installation needs read access to that repository. The nine domains released on 2026-11-09 were installed this way on 2026-11-10, with Claude Code and with Codex CLI; the metabolomics entry was last installed before its source moved to the domain repository (docs/STATUS.md).

Codex CLI reads the same marketplace file:

codex plugin marketplace add HolobiomicsLab/asb-skill-collections
codex plugin add <domain>@asb-skill-collections

The access requirement is the same. Without access to the private domain repositories, neither route works: download the Zenodo record of the release (version DOIs in the Releases table) and read it as described in AGENTS.md.

Install asbb from this public registry checkout (it is not published on PyPI):

git clone https://github.com/HolobiomicsLab/asb-skill-collections.git
cd asb-skill-collections
uv venv -p 3.12 --allow-existing && source .venv/bin/activate
uv pip install -e .

Chosen leaves without a checkout (asbb fetch, Python 3.12 or later):

asbb fetch <slugs> --collection metabolomics/v3 --dest <directory>

fetch reads collections.yaml and downloads the selected leaves from the domain repository at the pinned commit. Set GITHUB_TOKEN while that repository is private.

A derived selection from a domain checkout (asbb install):

asbb install --repo <domain checkout> --skills <slug-a>,<slug-b> --collection metabolomics/v3 --runtime agents

The human guide is <domain checkout>/collections/metabolomics/v3/USAGE.md in plain text. The complete release is also available from the Zenodo archive. Install routes, measured v2 examples and refusals are in docs/partial-install.md; the agent procedure is in AGENTS.md.

Choose what to install

Install the whole collection, a technique pack, a selection of skills (asbb install --skills, --skills-file or --query), or fetch chosen skills without a checkout (asbb fetch). Commands, outputs and refusals: docs/partial-install.md.

The full metabolomics plugin serves v3: 11,830 skills over 1,989 tools. The eight technique packs are the v2-derived packs shipped by the domain repository. Their measured v2 sizes remain useful for choosing a pack; no v3 full-install size is claimed here.

Install	Technique tag	v2 leaves	Measured v2 size on 2026-10-31
metabolomics-lc-ms	LC-MS	2,617	29 MiB
metabolomics-ms-generic	mass-spectrometry	804	8.5 MiB
metabolomics-ion-mobility	ion-mobility-MS	385	4.3 MiB
metabolomics-gc-ms	GC-MS	367	4.0 MiB
metabolomics-ms-imaging	MS-imaging	291	3.2 MiB
metabolomics-nmr	NMR	276	2.9 MiB
metabolomics-ce-ms	CE-MS	113	1.4 MiB
metabolomics-direct-infusion	direct-infusion-MS	97	1.1 MiB
a selection, asbb install --repo <domain checkout> --skills a,b,c --collection metabolomics/v2 --runtime agents	chosen slugs	10 in the example	188 KiB
a fetch, asbb fetch a,b --collection metabolomics/v2 --dest DIR	chosen slugs	10 in the example	112 KiB

The eight packs install by name with /plugin install <name>@asb-skill-collections. Their sizes are du -sk of the v2 units measured before the domain split. The selection and fetch rows are the 10-skill example of docs/partial-install.md, and a fetch also downloaded the 5.2 MiB (5,430,046 bytes) v2 skills_index.json at measurement time.

Packs overlap: a skill tagged with several techniques is in several packs, so install the full collection or a few packs, not both. The 1,520 technique-agnostic skills (statistics, pathway and generic data-handling procedures) carry no technique tag and are in no pack; they come with the full collection, a selection or a fetch.

Use: search, apply, ground

Search a domain checkout offline, with no API key and the tooling installed from the registry checkout as above. Pass the domain checkout explicitly:

asbb search "untargeted LC-MS/MS annotation" --repo <domain checkout> --collection metabolomics --target workflows
asbb get untargeted-lcmsms-annotation --repo <domain checkout> --collection metabolomics/v2 --target workflows
asbb search --repo <domain checkout> --list-collections

Without installing, python3 -m asb_skill_collections.asbb_cli runs the same commands.

An installed collection searches itself, with no tooling and no network:

python3 "<collection root>/bin/search_skills.py" --query "<task>" -k 10
python3 "<collection root>/bin/search_skills.py" --query "<goal>" --target workflows -k 3
python3 "<collection root>/bin/search_skills.py" --query "<tool or task>" --target tools -k 5

<collection root> is the directory that holds skills_index.json; in an installed plugin it is two directories above the router’s SKILL.md. Written as an absolute path, the command runs from any directory. The routers of the releases of 2026-11-09 print python bin/search_skills.py, relative to the collection root: it fails from any other directory and on a system with only python3, so run the form above instead. The CLI, the router, the MCP server and the collection-level search scripts share one versioned selector; each hit reports its score, matched fields and qualified slug. How offline skill selection works documents the rule, its tie handling and its 22-query measurement.

Apply. Read the skill’s SKILL.md (the read: path of the hit) and follow the procedure. Tool requirements are in its frontmatter and in <domain checkout>/collections/metabolomics/v3/USAGE.md, section 0.

Ground. To check an exact parameter, threshold or claim (the difference between “the skill says about 5 ppm” and “the paper specifies 5 ppm”), ground the skill against its source paper. Grounding is optional. Every released collection ships the grounding map kb_bundle.json; the binder is scripts/perspicacite_kb_bind.py in this repository, and a selection built with asbb install carries a copy. It uses Perspicacité, Holobiomics Lab’s local-first literature RAG engine, with two backends:

• kb: RAG over the paper’s full text and supplementary information. The per-paper KB (asb-paper-<doi>) is created on first use through the Perspicacité HTTP API; no MCP server is required. Needs Perspicacité at PERSPICACITE_BASE (default http://127.0.0.1:8000).
• local: no server. Clones the skill’s source repository and fetches the open-access paper where possible. Needs git and network.

Run python3 scripts/perspicacite_kb_bind.py (prepare, query, local, resolve) with --collection "<collection root>" --skill <slug>; in a selection built with asbb install, its bin/ copy and the /ground command do the same. Full guide: <domain checkout>/collections/metabolomics/v3/USAGE.md, section 5.

What is in the collection

_{The LC-MS view of the collection (the metabolomics-lc-ms pack). The full release covers all techniques.}

File	Contents
leaves/<slug>/SKILL.md	one evidence-grounded skill each (frontmatter: EDAM IRIs, provenance.source_papers DOIs and titles, tools with their roles, metadata.license_tier; verbatim evidence lines in the body). Shipped as data and read on demand, so installing does not load the corpus into the session’s context.
skills/_router/SKILL.md	the one advertised entry, the router <domain>-router
workflows/<slug>/SKILL.md	composite workflows, their index workflows/workflows_index.json and their router workflows/_workflow_router/SKILL.md (not advertised)
tools/<slug>.yaml	deduplicated software-tool records with EDAM terms and source DOIs
skills_index.json, tools_index.json	machine search indexes (EDAM IRI, tool name, keyword)
bin/search_skills.py	the offline search over skills, workflows and tools (standard library only)
kb_bundle.json	skill to source-paper KB slugs and repo_urls (the grounding map)
collection.yaml, corpus.yaml, mapping.json	collection record; per-paper access basis (repo-oa); each leaf mapped to its source build records and DOIs
CITATION.cff	citation

These files are relative to <domain checkout>/collections/metabolomics/v3/; the other released collections have the same layout. No released collection ships the grounding binder or a commands/ directory. The release-gate report and the other receipts are in the domain repository under receipts/<cut-id>/.

Local build-capsule archives and record metadata are packed and screened by scripts/pack_capsules.py, without deposit or upload. What their evaluation definitions contain, counted per domain, and what does not exist is in docs/evaluation-definitions.md.

How it was generated

Skills come from method papers anchored to the computational metabolomics review series (SOURCES.md: sources and inclusion criteria; CONTENT_POLICY.md: legal and open-access policy). The receipts under <domain checkout>/receipts/<cut-id>/ and the Zenodo record carry the release provenance. The method records the exact build command and model routing: Claude Opus 4.8 for outline and card revision, Claude Haiku 4.5 for the other stages, OpenAI text-embedding-3-large and -small for embeddings, each build recorded in build_manifest.json.

Repository family

Repository	Role	Access
asb-skill-collections (this one)	asb_skill_collections tooling, scripts/, tests, governance, registry, catalogue and docs-site	public
AgenticScienceBuilder	the pipeline that generates the collections	private
asb-skills-metabolomics	<domain checkout>/collections/metabolomics/<version>/, <domain checkout>/packs/metabolomics/<technique>/, <domain checkout>/staged-collections/metabolomics/ and receipts; v3 deposited on Zenodo	private
asb-skills-<domain>	one repository per other domain, with <domain checkout>/collections/<domain>/<version>/, <domain checkout>/packs/<domain>/<technique>/, <domain checkout>/staged-collections/<domain>/ and receipts; each release deposited on Zenodo	private
indicium	public standard for a typed scientific claim bound to its evidence; PyPI package indicium-standard 2.0.0	public
indicium-adapters	public core API for domain adapters; PyPI package 0.6.0	public
indicium-adapters-<domain>	per-domain adapters that enrich indicium claims with ontology terms; one repository for each of the ten domains	public
asb-schema	public schemas for ASB task cards, capsules and collections; PyPI package 0.4.0	public
Perspicacite-AI	literature RAG engine used for grounding	public
Mimosa-AI	multi-agent framework for autonomous scientific research	public

collections.yaml pins each published domain release to its repository, commit, collection path and tree digest. Domain and adapter repositories exist for metabolomics and nine further domains (agentic AI, astronomy, epigenomics, genomics, metabarcoding, metagenomics, multi-omics, proteomics, transcriptomics). Each domain has a release recorded in the registry and deposited on Zenodo, and is released from its own domain repository; the domain repositories are private. The legacy epigenomics, transcriptomics and metabolomics v1 trees are recorded in the registry and are not part of any release.

For a new domain, follow Domain onboarding and release.

Attribution and citation

Cite the collection and the original paper behind each skill you use (the DOIs in provenance.source_papers in its SKILL.md).

• Other domains. The concept DOI of each domain and the version DOI of each release are recorded in collections.yaml; the version DOIs are also listed under Releases. The entries below are those of metabolomics.
• Concept DOI, metabolomics, for all its versions: 10.5281/zenodo.20794026.
• Version DOI, v3, release metabolomics-v3.0.2 (10 November 2026): 10.5281/zenodo.24122117; the release is recorded in collections.yaml. The earlier v3 deposits of 9 November 2026, metabolomics-v3.0.1 (10.5281/zenodo.24093587) and metabolomics-v3.0.0 (10.5281/zenodo.24054446), are listed as superseded in the v3 row of the registry.
• Previous version DOI, v2 (22 June 2026): 10.5281/zenodo.20794027. The registry records the domain commit and tree digest for each version.
• Version citation files. The v2 and v3 CITATION.cff files are <domain checkout>/collections/metabolomics/v2/CITATION.cff and <domain checkout>/collections/metabolomics/v3/CITATION.cff.
• Authors. The v2 deposit: AgenticScienceBuilder Community, Louis-Félix Nothias, HolobiomicsLab.cnrs.fr, MetaboLinkAI.net. The concept record in this repository (root CITATION.cff): Louis-Félix Nothias and the AgenticScienceBuilder AI framework, joined by curators (call for curators).
• Roles (roles in collection.yaml, attribution: in each workflow SKILL.md): generator (the ASB pipeline), curators (none yet), promoter (Louis-Félix Nothias), sponsor (CNRS and Université Côte d’Azur, who paid the API cost).

Governance and licensing

Every skill carries a license_tier (in skills_index.json and in its SKILL.md frontmatter, metadata.license_tier) that answers what may I do with the underlying tool?

Tier	Meaning
open	commercial use allowed (MIT, Apache-2.0, GPL, CC-BY, …)
noncommercial	academic or noncommercial use only; confirm permitted use before applying the skill
restricted	licence established and it constrains reuse; check it before commercial use or redistribution
unknown	no licence for the tool was established; describing and using are unaffected; treat it as all rights reserved and never redistribute the tool’s code

The search tools do not filter or rank by tier; each skill hit prints its tier. The router asks the agent to get confirmation of a non-commercial purpose before applying a noncommercial skill (LICENSE_TIERS.md). Code is under Apache-2.0, collection content under CC-BY-4.0; verbatim quotations (evidence_spans) are minimal and attributed, and a rights holder may request removal (LICENSING.md). Other policies are in governance/, starting with MAINTAINERS.md and COI_POLICY.md.

Report, request, propose

Met a problem while using a skill? Four routes, each an issue on the tracker of this public repository:

1. this skill is wrong or could be better: skill feedback or the contribute page;
2. a skill is missing: request it, or propose yours: request a skill, or propose your skill (how community skills are curated);
3. a paper is not referenced: propose it: propose a paper or the paper form;
4. something technical failed: report it (install, plugin, search, CLI, MCP server, site, gates): technical fault.

asbb report <route> drafts any of the four with the collection and the skill filled in, redacts paths and credentials, and prints the text and a prefilled address; it never posts. The domain repositories are private: contributions go through issues here, and a maintainer carries them into the domain repository.

Contributing

• The four routes above are described, with what happens next, in CONTRIBUTING.md.
• Propose or annotate a paper, a collection or a workflow: CONTRIBUTING.md.
• Add papers to a collection. See the contributor proposal rail and the maintainer build, view, cut and candidate rail in Adding papers to a collection. Released collections are listed in collections.yaml; each lives in a private domain repository asb-skills-<domain>. Domain content and candidates belong in the corresponding asb-skills-<domain> checkout; this repository holds tooling, governance and the registry.
• Credit. Merged contributions count on the contributor leaderboard and can lead to co-authorship of the next release DOI (CONTRIBUTION_LOOP.md).
• Before packaging, run python -m scripts.unit_closure from the repository root: it compares each shipped unit’s indexes with its leaves and checks declared metadata.helper files.

Status

• Step 2 of the per-domain split is complete: this master is the registry and tooling repository; released content is in the domain repositories.
• The managed-install and Claude Code measurements predate the new marketplace sources; see docs/STATUS.md for their scope and dates.
• Pending or experimental: the other seven packs, the web UI, runtime adapters other than agents, the MCP server. Not yet published: PyPI, the dataset mirror or a capsule record. The evaluation material is definitions only: no validated benchmark, reference results or agent-performance leaderboard exists. The documentation site is live.
• The w3id.org/holobiomicslab/ and w3id.org/asb identifiers resolve. Dates, measurements and detail per surface: docs/STATUS.md.

Acknowledgements

We thank the participants and organisers of Dagstuhl Seminar 26181, Computational Metabolomics, where this collaboration began. API generation costs for this collection were sponsored by CNRS and Université Côte d’Azur. Maintained by Holobiomics Lab (CNRS, Université Côte d’Azur).