Iron Proxy Gateway for NanoClaw
nanocoai/nanoclaw
Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.
Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service.
Install Askcos
$ npx skills add lamm-mit/scienceclaw --skill askcos -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lamm-mit/scienceclaw askcos --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/askcos .claude/skills/askcos && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "askcos" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/askcos into .claude/skills/askcos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "askcos", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lamm-mit/scienceclaw/tree/main/skills/askcosType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lamm-mit/scienceclaw --skill askcos -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lamm-mit/scienceclaw askcos --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/askcos .agents/skills/askcos && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "askcos" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/askcos into .agents/skills/askcos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "askcos", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lamm-mit/scienceclaw --skill askcos -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lamm-mit/scienceclaw askcos --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/askcos .cursor/skills/askcos && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "askcos" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/askcos into .cursor/skills/askcos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "askcos", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lamm-mit/scienceclaw.git --path skills/askcos--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lamm-mit/scienceclaw --skill askcos -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lamm-mit/scienceclaw askcos --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/askcos .gemini/skills/askcos && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "askcos" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/askcos into .gemini/skills/askcos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "askcos", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lamm-mit/scienceclaw askcosInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lamm-mit/scienceclaw --skill askcos -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/askcos .github/skills/askcos && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "askcos" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/askcos into .github/skills/askcos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "askcos", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lamm-mit/scienceclaw --skill askcos -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lamm-mit/scienceclaw askcos --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/askcos .opencode/skills/askcos && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "askcos" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/askcos into .opencode/skills/askcos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "askcos", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
askcos- GitHub stars
- 244
- Token cost
- ~981 tokens
- SKILL.md length
- 166 words
- Files
- 5 (incl. scripts)
- Skills in repo
- 85
- Repo updated
- First seen
- Licence
- MIT
At a glance
Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service.
- DevOps & Cloud work in your project
- SKILL.md covers Overview, Requirements, Usage and Parameters, plus 5 more sections
- Runs Python scripts from its folder; calls python3 and docker
What it does
Askcos is an agent skill from lamm-mit/scienceclaw. Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service. Returns ranked precursor suggestions with confidence scores from 5 template sets (reaxys, pistachio, pistachioringbreaker, bkmsmetabolic, reaxysbiocatalysis). Requires local deployment at http://localhost:9410.
Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `scripts/askcos_retro.py` and `scripts/askcos_scraper.py`).
It sits in DevOps & Cloud. It works with Docker. The licence is MIT.
When your agent uses it
- DevOps & Cloud work in your project
Example prompts
- “/askcos”
Requirements
- Python 3
- Docker
What it can do on your machine
Read from SKILL.md and the folder at commit ab9aba1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 4 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3docker
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
gitlab.comaskcos-docs.mit.edu
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Askcos loads about 981 tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 166 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its MIT licence (© lamm-mit). 166 words, ~981 tokens.
Download SKILL.mdSave it as
.claude/skills/askcos/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- askcos
- description
- Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service. Returns ranked precursor suggestions with confidence scores from 5 template sets (reaxys, pistachio, pistachio_ringbreaker, bkms_metabolic, reaxys_biocatalysis). Requires local deployment at http://localhost:9410.
- license
- MIT License
- metadata.skill-author
- K-Dense Inc.
ASKCOS - Retrosynthetic Template Relevance
Overview
ASKCOS template_relevance predicts retrosynthetic disconnections using reaction template libraries.
The service runs locally as a TorchServe container (retro_template_relevance) and requires a
SMILES input, returning ranked precursor SMILES with template match scores.
Deployment: https://gitlab.com/mlpds_mit/askcosv2/retro/template_relevance Docs: https://askcos-docs.mit.edu/guide/4-Deployment/4.2-Standalone-deployment-of-individual-modules.html
Requirements
- Docker container
retro_template_relevancerunning athttp://localhost:9410 - Start/stop:
docker start retro_template_relevance/docker stop retro_template_relevance
Usage
Basic Retrosynthesis (JSON output — default)
python3 skills/askcos/scripts/askcos_retro.py \
--smiles "CC(C)C1CCC(C)CC1O"Human-readable summary
python3 skills/askcos/scripts/askcos_retro.py \
--smiles "CC(C)C1CCC(C)CC1O" \
--model reaxys \
--top 10 \
--format summarySelect template set
python3 skills/askcos/scripts/askcos_retro.py \
--smiles "CC(C)C1CCC(C)CC1O" \
--model pistachioParameters
| Flag | Default | Description |
|---|---|---|
--smiles / -s | required | Target molecule SMILES |
--model / -m | reaxys | Template set: reaxys, pistachio, pistachio_ringbreaker, bkms_metabolic, reaxys_biocatalysis |
--top / -n | 10 | Number of top suggestions to return |
--base-url | http://localhost:9410 | TorchServe base URL |
--format / -f | json | Output format: json or summary |
Environment Variables
| Variable | Default | Description |
|---|---|---|
ASKCOS_BASE_URL | http://localhost:9410 | Override TorchServe URL |
ASKCOS_MODEL | reaxys | Default template set |
Output Format (JSON)
{
"target": "CC(C)C1CCC(C)CC1O",
"model": "reaxys",
"total_templates_matched": 191,
"status": "success",
"suggestions": [
{
"rank": 1,
"reactants_smiles": "CC1CCC(C(C)C)C(=O)C1",
"score": 0.4562,
"template_smarts": "[C:1]-[CH;D3;+0:2](-[C:3])-[OH;D1;+0:4]>>[C:1]-[C;H0;D3;+0:2](-[C:3])=[O;H0;D1;+0:4]",
"template_id": "5e1f4b6e6348832850995dbf",
"template_count": 8688,
"necessary_reagent": ""
}
]
}Example Output (menthol)
ASKCOS (reaxys) — CC(C)C1CCC(C)CC1O
Templates matched: 191
# 1 score=0.4562 n= 8688 precursors: CC1CCC(C(C)C)C(=O)C1
# 2 score=0.0387 n= 20 precursors: CC1CCC2C(C1)OC(=O)C2C
# 3 score=0.0387 n= 20 precursors: CC(C)C1CCC2CC1OC2=O
# 4 score=0.0321 n= 245 precursors: CC1C=CC(C(C)C)CC1 reagent: [O]
# 5 score=0.0279 n=26868 precursors: CC(=O)OC1CC(C)CCC1C(C)CTop hit (menthone → menthol via reduction) correctly recovers the industrial Takasago process.
Integration with Other Skills
# Get SMILES from RDKit, then run retrosynthesis
SMILES="CC(C)C1CCC(C)CC1O"
# Retrosynthesis
python3 skills/askcos/scripts/askcos_retro.py --smiles "$SMILES" --top 5 --format json
# Analyse top precursor with RDKit
PRECURSOR="CC1CCC(C(C)C)C(=O)C1"
python3 skills/rdkit/scripts/molecular_properties.py --smiles "$PRECURSOR"References
- ASKCOS: Coley et al., Science 2019. DOI: 10.1126/science.aax1566
- Template relevance: Coley et al., ACS Central Science 2017. DOI: 10.1021/acscentsci.7b00355
- GitLab: https://gitlab.com/mlpds_mit/askcosv2/retro/template_relevance
© lamm-mit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts) in skills/askcos of lamm-mit/scienceclaw.
- SKILL.md
- scripts/__pycache__/askcos_retro.cpython-313.pyc
- scripts/__pycache__/askcos_scraper.cpython-313.pyc
- scripts/askcos_retro.py
- scripts/askcos_scraper.py
Open the folder on GitHubat commit ab9aba1
Compare with similar skills
Askcos next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Askcos this skilllamm-mit/scienceclaw | 244 | — | ~981 | Automated safety check: Pass | MIT | |
| Iron Proxy Gateway for NanoClawnanocoai/nanoclaw | 31k | — | ~4.6k | Automated safety check: Notes | MIT | |
| GreptimeDB Dev Docker ImageGreptimeTeam/greptimedb | 6.7k | — | ~4k | Automated safety check: Notes | Apache-2.0 | |
| Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit | 259 | 6 repos | ~1.1k | Automated safety check: Notes | Custom licence | |
| LangBot Deployment Guidelangbot-app/LangBot | 18k | — | ~1.2k | Automated safety check: Notes | Apache-2.0 | |
| Build Openshell Mxc WindowsNVIDIA/OpenShell | 15k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
GreptimeDB Dev Docker Image
GreptimeTeam/greptimedb
Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.
Senior DevOps Toolkit
maslennikov-ig/claude-code-orchestrator-kit
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…
LangBot Deployment Guide
langbot-app/LangBot
Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.
- Official
Build Openshell Mxc Windows
NVIDIA/OpenShell
Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64.
Container Dev
yansongda/pay
A skill your agent uses when local PHP environment is unavailable.
More from lamm-mit/scienceclaw
All 85 skills in this repoFred Economic Data
lamm-mit/scienceclaw
Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources.
Drug Research
lamm-mit/scienceclaw
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.
Imaging Data Commons
lamm-mit/scienceclaw
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.
Rowan
lamm-mit/scienceclaw
Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.
Infographics
lamm-mit/scienceclaw
Create professional infographics using Nano Banana Pro AI with smart iterative refinement.
Disease Research
lamm-mit/scienceclaw
Generate comprehensive disease research reports using 100+ ToolUniverse tools.
Related
Works with
Categories
Questions about Askcos
What does Askcos do?
Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service. Askcos is an agent skill from lamm-mit/scienceclaw. Retrosynthetic template relevance prediction using a locally deployed ASKCOS TorchServe service.
When should I use Askcos?
Askcos fits situations like: devOps & Cloud work in your project.
How do I install Askcos in Claude Code?
Run `npx skills add lamm-mit/scienceclaw --skill askcos -a claude-code`. Or copy the skill folder (skills/askcos in lamm-mit/scienceclaw) into .claude/skills/askcos in your project. Claude Code loads it when a task matches its description.
How do I install Askcos in Codex?
Run `npx skills add lamm-mit/scienceclaw --skill askcos -a codex`. Or copy the skill folder (skills/askcos in lamm-mit/scienceclaw) into .agents/skills/askcos in your project. Codex loads it when a task matches its description.
Can I use Askcos in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lamm-mit/scienceclaw --skill askcos -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/askcos, .gemini/skills/askcos, .github/skills/askcos and .opencode/skills/askcos in your project.
What does Askcos need to run?
Going by SKILL.md and its folder, Askcos needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and docker). Our summary lists: Python 3; Docker.
Does Askcos access the network?
SKILL.md names 2 domains. As links in the text: gitlab.com and askcos-docs.mit.edu. This is read from the text; nothing was executed.
Is Askcos safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Askcos use?
Askcos is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Askcos use?
About 981 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Askcos?
Skills that share tags, products or a category with Askcos: Iron Proxy Gateway for NanoClaw (nanocoai/nanoclaw, 31k stars), GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 259 stars) and LangBot Deployment Guide (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Askcos?
lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 21, 2026.
Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.