Skills drugflow-skills

Multi-flow API workflow skill for this DrugFlow Django repository. Use when an agent needs executable end-to-end API procedures such as login/register, workspace and balance retrieval, job listing, virtual screening, docking, ADMET, rescoring, structure extraction, and molecular factory.

install

source · Clone the upstream repo

git clone https://github.com/openclaw/skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/ashipiling/drugflow-api" ~/.claude/skills/clawdbot-skills-drugflow-skills && rm -rf "$T"

manifest: skills/ashipiling/drugflow-api/SKILL.md

source content

DrugFlow Skills

Route requests to the correct DrugFlow API flow and execute with minimal ambiguity.

Flow Selection

Read references/index.md first.
Match user intent to one flow.
Load only that flow's reference files.
Prefer script execution from
```
scripts/<flow>/
```
when available.

Current Flows

Common APIs: reusable auth/workspace/balance/jobs APIs available.
Virtual screening: complete flow available.
Docking: complete flow available.
ADMET: complete flow available.
Rescoring: complete flow available.
Structure extract: complete flow available (
```
img2mol
```
backend type).
Molecular factory: complete flow available (with atom-selection helpers).

Common APIs Workflow

Read references/flows/common-apis/call-flow.md.
Read references/flows/common-apis/payloads.md.
Reuse
```
scripts/common/drugflow_api.py
```
for:

```
signin
```
```
signup
```

list_workspaces

create_workspace

ensure_workspace

```
get_balance
```
```
list_jobs
```

Use
```
scripts/common/test_common_apis.py
```
for direct smoke tests.

Virtual Screening Workflow

Read references/flows/virtual-screening/call-flow.md.
Read references/flows/virtual-screening/payloads.md.

Use

scripts/virtual-screening/run_vs_flow.py

for end-to-end execution.

Always include
```
ws_id
```
for
```
/api/jobs
```
list/detail.
For
```
/api/jobs
```
create, pass
```
name
```
,
```
type
```
,
```
args
```
(JSON string),
```
ws_id
```
; in non-private mode include
```
expect_tokens
```
and
```
avail_tokens
```
.

Docking Workflow

Read references/flows/docking/call-flow.md.
Read references/flows/docking/payloads.md.
Use
```
scripts/docking/run_docking_flow.py
```
for end-to-end execution.
Create docking jobs through
```
POST /api/jobs
```
with multipart fields
```
pdb
```
,
```
ligands
```
,
```
pdb_content
```
, and
```
args
```
.
Site-driven docking box note: when
```
--site
```
is provided but
```
center/size/radius
```
are omitted, the script auto-derives the docking box from that site in local PDB.
Always include
```
ws_id
```
on job list/detail requests and pass
```
expect_tokens
```
/
```
avail_tokens
```
in non-private mode.

ADMET Workflow

Read references/flows/admet/call-flow.md.
Read references/flows/admet/payloads.md.
Use
```
scripts/admet/run_admet_flow.py
```
for end-to-end execution.
ADMET job type is fixed to
```
admet-dl
```
.
Support two input modes:

direct
```
smiles
```
list
dataset mode via
```
dataset_id + smiles_col
```

For

/api/jobs

create, pass

name

type=admet-dl

args

ws_id

, and in non-private mode

expect_tokens

avail_tokens

Rescoring Workflow

Read references/flows/rescoring/call-flow.md.
Read references/flows/rescoring/payloads.md.
Use
```
scripts/rescoring/run_rescoring_flow.py
```
for end-to-end execution.
Create rescoring jobs through
```
POST /api/jobs
```
with:

```
type=rescoring
```
form fields
```
pdb
```
,
```
ligands
```
,
```
smiles_col
```
```
args.mode=semi
```
and
```
args.rescoring_functions
```

Script enforces input files:
```
--pdb-file
```
must be
```
.pdb
```
,
```
--ligands-file
```
must be
```
.sdf
```
.
Always include
```
ws_id
```
; in non-private mode include
```
expect_tokens
```
and
```
avail_tokens
```
.

Structure Extract Workflow

Read references/flows/structure-extract/call-flow.md.
Read references/flows/structure-extract/payloads.md.

Use

scripts/structure-extract/run_structure_extract_flow.py

for end-to-end execution.

User-facing "结构提取" maps to backend job
```
type=img2mol
```
.

For create, pass

name

type=img2mol

args

(

dataset_id

page_list

ws_id

, and in non-private mode

expect_tokens

avail_tokens

```
dataset_id
```
must be img2mol-compatible and include
```
extras.osskey
```
.

Molecular Factory Workflow

Read references/flows/molecular-factory/call-flow.md.
Read references/flows/molecular-factory/payloads.md.

Use

scripts/molecular-factory/run_molecular_factory_flow.py

```
atom-info
```
```
extract-partial
```
```
draw-atom-index
```
```
create-job
```

Default to non-docking molecular factory unless user explicitly asks for docking:

```
args.need_docking=false
```
```
args.pdb_use.*=false
```

Default generation models:

args.molgen_algos=["Frag-GPT","REINVENT"]

Use helper APIs first to confirm
```
selected_atoms/start_atoms
```
, then submit
```
molecular_factory
```
job.
Always pass
```
ws_id
```
; in non-private mode include
```
expect_tokens
```
and
```
avail_tokens
```
.

Output Contract

Return method + endpoint + required parameters for each step.
Return key ids and state:
```
ws_id
```
,
```
job_id
```
,
```
state
```
, result
```
count
```
.
When running scripts, return command + important outputs.

Expansion Rules

Add new flow docs under

references/flows/<flow>/

with

call-flow.md

and

payloads.md

Add runnable scripts under
```
scripts/<flow>/
```
.
Update references/index.md and this file's
```
Current Flows
```
section.