boltz-small-molecule-adme
SkillPredict Tier-1 ADME/ADMET for small molecules with Boltz from bare SMILES — no target, no docking. Use when the user wants solubility, permeability, or lipophilicity/logD for a molecule or list of molecules. Not for ranking molecules against a protein target (use boltz-small-molecule-screen, which a
Install
git clone https://github.com/boltz-bio/boltz-api-skills.git ~/.claude/skills/boltz-small-molecule-admeWhat is boltz-small-molecule-adme?
Predict Tier-1 ADME/ADMET for small molecules with Boltz from bare SMILES — no target, no docking. Use when the user wants solubility, permeability, or lipophilicity/logD for a molecule or list of molecules. Not for ranking molecules against a protein target (use boltz-small-molecule-screen, which already returns ADME free).
What this can do
Capabilities declared in this component's own frontmatter — not inferred.
Inherit all session tools
Declares no tool restrictions — inherits every session tool
~82 tokens of context used while enabled, before you invoke anything
Documentation
README · ~4 min readWorkflow
If boltz-api is missing from PATH, use boltz-cli-setup for install/update guidance before retrying.
If a command reports missing or expired authentication, use boltz-cli-setup to start boltz-api auth login --device-code before retrying; do not ask permission first.
If the agent host sandbox blocks boltz-api install/auth/API calls, use boltz-cli-setup to request the host sandbox bypass/escalation needed for user-wide CLI install, browser login, credential storage, temp files, or API access before retrying.
Use this skill for standalone ADME triage on SMILES the user already has. No protein target is involved. If the user is also screening or docking those molecules against a target, prefer boltz-small-molecule-screen — it returns the same ADME block free as part of the screen.
- Normalize the molecules from raw SMILES, a CSV (auto-detect the SMILES column),
.smi, or.txtinto themoleculeslist. Each entry is{smiles, id?}; the optionalidis echoed back asexternal_idon each result so you can map results to inputs. - Hard cap: 128 molecules per request. If the list exceeds 128, split into batches of ≤128 and submit one request per batch (suffix the run name, for example
-b1,-b2), then merge results. Never send more than 128 in one call — the API rejects it withVALIDATION_ERROR: input.molecules must contain at most 128 items. - Author the payload YAML or JSON, run
estimate-cost, show the USD cost, wait for explicit confirmation. ADME is priced at $0.01 per molecule (size-independent);estimate-costreturns the authoritative total — always quote it. runto submit and wait — ADME finishes in seconds, so it is synchronous and needs no background polling.runpersists results locally under--root-dir/<run-name>/.- Report from
<output-root>/<run-name>/run.json→output.molecules[]. For each molecule showexternal_id(orsmiles),solubility,permeability, andlipophilicity. The three values live under each molecule'sadmeobject. Call out any molecule withstatus: failedand itserror(an object{code, message}, e.g. codeadme_enumeration_failed, messageInvalid SMILES) —admeisnullthere; one bad SMILES fails only that molecule, not the batch. Read references/results.md for the output layout and references/api.md for the payload and batching details.
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →math-olympiad
32.8K stars
build-mcpb
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the lo
32.8K stars
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintena
32.8K stars