MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports.
LGPL-3.0-or-laterAuto-check passed
Install Reacnetgenerator
$ npx skills add deepmodeling/reacnetgenerator --skill reacnetgenerator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install deepmodeling/reacnetgenerator reacnetgenerator --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/deepmodeling/reacnetgenerator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reacnetgenerator .claude/skills/reacnetgenerator && 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 "reacnetgenerator" agent skill from https://github.com/deepmodeling/reacnetgenerator/tree/master/skills/reacnetgenerator into .claude/skills/reacnetgenerator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reacnetgenerator", 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/deepmodeling/reacnetgenerator/tree/master/skills/reacnetgeneratorType 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 deepmodeling/reacnetgenerator --skill reacnetgenerator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install deepmodeling/reacnetgenerator reacnetgenerator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/reacnetgenerator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/reacnetgenerator .agents/skills/reacnetgenerator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "reacnetgenerator" agent skill from https://github.com/deepmodeling/reacnetgenerator/tree/master/skills/reacnetgenerator into .agents/skills/reacnetgenerator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reacnetgenerator", 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 deepmodeling/reacnetgenerator --skill reacnetgenerator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install deepmodeling/reacnetgenerator reacnetgenerator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/reacnetgenerator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/reacnetgenerator .cursor/skills/reacnetgenerator && 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 "reacnetgenerator" agent skill from https://github.com/deepmodeling/reacnetgenerator/tree/master/skills/reacnetgenerator into .cursor/skills/reacnetgenerator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reacnetgenerator", 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/deepmodeling/reacnetgenerator.git --path skills/reacnetgenerator--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 deepmodeling/reacnetgenerator --skill reacnetgenerator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install deepmodeling/reacnetgenerator reacnetgenerator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/reacnetgenerator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/reacnetgenerator .gemini/skills/reacnetgenerator && 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 "reacnetgenerator" agent skill from https://github.com/deepmodeling/reacnetgenerator/tree/master/skills/reacnetgenerator into .gemini/skills/reacnetgenerator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reacnetgenerator", 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 deepmodeling/reacnetgenerator reacnetgeneratorInstalls 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 deepmodeling/reacnetgenerator --skill reacnetgenerator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/deepmodeling/reacnetgenerator.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/reacnetgenerator .github/skills/reacnetgenerator && 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 "reacnetgenerator" agent skill from https://github.com/deepmodeling/reacnetgenerator/tree/master/skills/reacnetgenerator into .github/skills/reacnetgenerator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reacnetgenerator", 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 deepmodeling/reacnetgenerator --skill reacnetgenerator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install deepmodeling/reacnetgenerator reacnetgenerator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/deepmodeling/reacnetgenerator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/reacnetgenerator .opencode/skills/reacnetgenerator && 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 "reacnetgenerator" agent skill from https://github.com/deepmodeling/reacnetgenerator/tree/master/skills/reacnetgenerator into .opencode/skills/reacnetgenerator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reacnetgenerator", 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
reacnetgenerator- GitHub stars
- 103
- Used in
- 1 other repo
- Token cost
- ~1.6k tokens
- SKILL.md length
- 620 words
- Files
- 4 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- LGPL-3.0-or-later
At a glance
Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports.
- Works in 4 steps: Use rng-pipeline by default for standard… → Use native reacnetgenerator when the… → Use rng-query when the user already has… → …
- The user wants to analyze LAMMPS dump/xyz/bond trajectories with ReacNetGenerator
- SKILL.md covers 10-second quickstart, What this skill is for, References (read only when… and Tool-selection rule, plus 7 more sections
- Calls uvx
What it does
Reacnetgenerator is an agent skill from deepmodeling/reacnetgenerator. Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports. Use when the user wants to analyze LAMMPS dump/xyz/bond trajectories with ReacNetGenerator. Handles LAMMPS dump quirks like x/y/z vs xs/ys/zs by converting to x/y/z (orthorhombic + triclinic supported via reacnet-md-tools). Can infer atomname order from a LAMMPS data file. Runs via local reacnetgenerator if available or via uvx --from reacnetgenerator .... Writes outputs into out/<inputbasename/ with logs and a summary.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/cli.md`, `references/examples.md` and `references/pbc-and-inputs.md`). Compatibility notes: Requires uv and python3. Usually requires internet access for uvx --from ... resolution unless packages are already cached.
It works with Python. The repository describes itself as: an automatic reaction network generator for reactive molecular dynamics simulation. The licence is LGPL-3.0-or-later.
When your agent uses it
- The user wants to analyze LAMMPS dump/xyz/bond trajectories with ReacNetGenerator
Example prompts
- “/reacnetgenerator”
Requirements
- Compatibility (from SKILL.md): Requires `uv` and `python3`. Usually requires internet access for `uvx --from ...` resolution unless packages are already cached.
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Use rng-pipeline by default for standard LAMMPS dump workflows.
- Use native reacnetgenerator when the user needs official low-level flags not exposed by the wrapper.
- Use rng-query when the user already has .reactionabcd / .species outputs and wants analysis rather than rerunning.
- Use rng-webapp only when the user explicitly wants an interactive local browser UI.
What it can do on your machine
Read from SKILL.md and the folder at commit 9618b85. 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
Shell commands in SKILL.md call:
uvx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uvx, which can reach the network depending on how they are called.
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.
Compatibility
Requires `uv` and `python3`. Usually requires internet access for `uvx --from ...` resolution unless packages are already cached.
From compatibility in the SKILL.md frontmatter.
Context cost
Reacnetgenerator loads about 1.6k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 135 tokens; SKILL.md has 620 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from deepmodeling/reacnetgenerator at commit 9618b85, republished under its LGPL-3.0-or-later licence (© deepmodeling). 620 words, ~1,555 tokens.
Download SKILL.mdSave it as
.claude/skills/reacnetgenerator/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- reacnetgenerator
- description
- Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports. Use when the user wants to analyze LAMMPS dump/xyz/bond trajectories with ReacNetGenerator. Handles LAMMPS dump quirks like x/y/z vs xs/ys/zs by converting to x/y/z (orthorhombic + triclinic supported via reacnet-md-tools). Can infer atomname order from a LAMMPS data file. Runs via local reacnetgenerator if available or via `uvx --from reacnetgenerator ...`. Writes outputs into `out/<input_basename>/` with logs and a summary.
- compatibility
- Requires `uv` and `python3`. Usually requires internet access for `uvx --from ...` resolution unless packages are already cached.
- license
- LGPL-3.0-or-later
- metadata.author
- hcustc-bot
- metadata.version
- 2.3
- metadata.repository
- https://github.com/tongzhugroup/ReacNetGenerator
- metadata.repositories
- https://github.com/tongzhugroup/ReacNetGenerator, https://github.com/hcustc/reacnet-md-tools
ReacNetGenerator
10-second quickstart
- Run a standard LAMMPS dump workflow:
uvx --refresh --from reacnet-md-tools rng-pipeline ...
- Analyze existing outputs (no rerun):
uvx --refresh --from reacnet-md-tools rng-query ...
If you need full official flags (e.g. --cell, --nopbc, --use-ase, --miso, HMM matrices), use native:
uvx --refresh --from reacnetgenerator reacnetgenerator ...
What this skill is for
Use this skill for reactive MD post-processing when the user wants to:
- run ReacNetGenerator on
bond,dump,xyz, orextxyztrajectories - handle common LAMMPS trajectory issues before running analysis
- choose between a high-level wrapper (
reacnet-md-tools) and the nativereacnetgeneratorCLI - inspect generated
.reactionabcd/.speciesoutputs after a run
References (read only when needed)
Read only what is relevant:
- If the user asks about official flags or default values: references/cli.md
- If the user asks about PBC/cell/
--nopbcor input-type choice: references/pbc-and-inputs.md - If the user wants copy-paste commands: references/examples.md
Tool-selection rule
Choose the narrowest tool that solves the user’s request:
- Use
rng-pipelineby default for standard LAMMPS dump workflows. - Use native
reacnetgeneratorwhen the user needs official low-level flags not exposed by the wrapper. - Use
rng-querywhen the user already has.reactionabcd/.speciesoutputs and wants analysis rather than rerunning. - Use
rng-webapponly when the user explicitly wants an interactive local browser UI.
Ask only for the missing inputs
Usually you only need:
- trajectory path(s)
- input type:
bond | dump | xyz | extxyzif not obvious - atom names for
-a/--atomnameunless they can be inferred from a LAMMPS data file - whether the run should be treated as periodic, only if cell information is missing or ambiguous
Do not ask unnecessary questions when the trajectory already contains enough information.
Default execution policy
Preferred default: wrapper CLIs (reacnet-md-tools)
Use reacnet-md-tools for routine runs because it is safer and more agent-friendly:
- handles standard LAMMPS dump workflows
- can infer atom names from nearby
.datafiles - writes outputs into a predictable
out/<basename>/directory - reduces manual CLI assembly errors
When running the wrapper from an agent, prefer uvx so the latest published version is resolved automatically:
uvx --refresh --from reacnet-md-tools rng-pipeline --help
uvx --refresh --from reacnet-md-tools rng-query --helpFallback: native reacnetgenerator
Use native reacnetgenerator when the user explicitly needs official flags such as:
--miso--use-ase--ase-cutoff-mult--ase-pair-cutoffs--nopbc--cell-n/--nproc-s/--selectatoms--matrixa--matrixb--urls
If using native CLI, follow the official flag semantics in references/cli.md.
Decision rules
Show full SKILL.md (253 more words)Show less
Input type
- If the file clearly looks like a LAMMPS dump (
ITEM:blocks), treat it asdump. - If the input is a bond trajectory such as
bonds.reaxc, treat it asbond/lammpsbondfile. - If the input is
.xyz, treat it asxyzunless it is explicitlyextxyz.
PBC / cell
Read references/pbc-and-inputs.md when choosing --cell or --nopbc.
Short version:
- For LAMMPS dump/lammpstrj with valid
BOX BOUNDS, do not ask for--cell. - For XYZ without cell info, ask whether the system should be treated as periodic.
- Use
--nopbconly when the run is truly non-periodic, already unwrapped/reconstructed, or lacks meaningful periodic cell semantics.
HMM
- For a quick first pass, use
--nohmmunless the user explicitly wants HMM behavior. - If the user asks for more faithful / publication-style treatment and knows what HMM means here, allow HMM by omitting
--nohmm.
Post-analysis rule
If the user already has outputs such as:
.reactionabcd.species- generated HTML / SVG / JSON reports
prefer post-analysis over rerunning. Use rng-query first unless the user specifically wants the raw files opened or a browser UI.
Output expectations
For normal runs, make outputs predictable and easy to inspect:
run.log- generated
*.html,*.svg,*.json,*.species,*.reaction* summary.mdif using the wrapper workflow
Working style
- Prefer non-interactive commands unless you truly have a TTY.
- Prefer explicit paths over implicit discovery when multiple candidate files exist.
- Stop and ask if atom-type inference is ambiguous.
- Do not invent unsupported flags; use the official CLI definitions from references/cli.md.
Quick references
- Official CLI coverage: references/cli.md
- Common recipes: references/examples.md
- PBC and input decisions: references/pbc-and-inputs.md
© deepmodeling, LGPL-3.0-or-later. 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 3 other files (references) in skills/reacnetgenerator of deepmodeling/reacnetgenerator.
- SKILL.md
- references/cli.md
- references/examples.md
- references/pbc-and-inputs.md
Open the folder on GitHubat commit 9618b85
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in deepmodeling/reacnetgenerator, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Reacnetgenerator 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 |
|---|---|---|---|---|---|---|
| Reacnetgenerator this skilldeepmodeling/reacnetgenerator | 103 | 1 repos | ~1.6k | Automated safety check: Pass | LGPL-3.0-or-later | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| PDF Processinganthropics/skills | 180k | 48 repos | ~2k | Automated safety check: Pass | Proprietary | |
| NotebookLM Research AssistantPleasePrompto/notebooklm-skill | 7.8k | 13 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Manim Video Productionbrowser-use/video-use | 28k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
PDF Processing
anthropics/skills
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
NotebookLM Research Assistant
PleasePrompto/notebooklm-skill
Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.
Manim Video Production
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
PPT Master
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
Related
Works with
Questions about Reacnetgenerator
What does Reacnetgenerator do?
Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports. Reacnetgenerator is an agent skill from deepmodeling/reacnetgenerator. Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports.
When should I use Reacnetgenerator?
Reacnetgenerator fits situations like: the user wants to analyze LAMMPS dump/xyz/bond trajectories with ReacNetGenerator.
How do I install Reacnetgenerator in Claude Code?
Run `npx skills add deepmodeling/reacnetgenerator --skill reacnetgenerator -a claude-code`. Or copy the skill folder (skills/reacnetgenerator in deepmodeling/reacnetgenerator) into .claude/skills/reacnetgenerator in your project. Claude Code loads it when a task matches its description.
How do I install Reacnetgenerator in Codex?
Run `npx skills add deepmodeling/reacnetgenerator --skill reacnetgenerator -a codex`. Or copy the skill folder (skills/reacnetgenerator in deepmodeling/reacnetgenerator) into .agents/skills/reacnetgenerator in your project. Codex loads it when a task matches its description.
Can I use Reacnetgenerator 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 deepmodeling/reacnetgenerator --skill reacnetgenerator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reacnetgenerator, .gemini/skills/reacnetgenerator, .github/skills/reacnetgenerator and .opencode/skills/reacnetgenerator in your project.
What does Reacnetgenerator need to run?
Going by SKILL.md and its folder, Reacnetgenerator needs the command-line tools its instructions call (uvx). Compatibility (from SKILL.md): Requires `uv` and `python3`. Usually requires internet access for `uvx --from ...` resolution unless packages are already cached..
Does Reacnetgenerator access the network?
SKILL.md contains no URLs. Its commands use uvx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Reacnetgenerator 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. Review the folder before installing.
What licence does Reacnetgenerator use?
Reacnetgenerator is published under the LGPL-3.0-or-later licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Reacnetgenerator use?
About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.
What are the alternatives to Reacnetgenerator?
Skills that share tags, products or a category with Reacnetgenerator: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reacnetgenerator?
deepmodeling (a GitHub organization) maintains it in deepmodeling/reacnetgenerator, which has 103 GitHub stars. The repository was last updated on October 5, 2026.
Source: deepmodeling/reacnetgenerator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.