docs: add ReacNetGenerator agent skill (#2444)

## Summary

- add an Agent Skills documentation page for the existing
`reacnetgenerator` skill
- document the skill list, installation command, minimal verification
task, and the OpenClaw JCTC citation
- include the new page in the main documentation toctree

## Checks

- `uv run --isolated --with sphinx --with myst-parser sphinx-build -W
--keep-going -b html /tmp/rng-agent-skills-check
/tmp/rng-agent-skills-check-build`
- verified the added `agent-skills` toctree target exists

Note: a full `uv run --extra docs sphinx-build ...` project-docs build
is currently blocked by the existing `reacnetgenerator[docs]` dependency
resolution issue: the project advertises `requires-python >=3.7`, while
the configured `myst-nb>=1.0.0rc0` docs dependency no longer resolves
for Python 3.7.

Authored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)

Author: njzjz-bot

docs/agent-skills.md

@@ -0,0 +1,38 @@
+# Agent Skills
+
+ReacNetGenerator provides official [Agent Skills](https://agentskills.io/what-are-skills) to analyze reactive molecular dynamics trajectories using an agent.
+
+## List of skills
+
+- `reacnetgenerator`: Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports. It supports common ReacNetGenerator inputs such as LAMMPS dump trajectories, ReaxFF bond files, and XYZ trajectories, and can help handle trajectory-format details before running the analysis.
+
+## Related reference
+
+The `reacnetgenerator` skill is one of the domain-specific computational chemistry skills described in the following paper:
+
+- Mingwei Ding, Chen Huang, Yibo Hu, Yifan Li, Zitian Lu, Xingtai Yu, Duo Zhang, Wenxi Zhai, Tong Zhu, Qiangqiang Gu, and Jinzhe Zeng. [Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills](https://doi.org/10.1021/acs.jctc.6c00622). _J. Chem. Theory Comput._, 2026, DOI: [10.1021/acs.jctc.6c00622](https://doi.org/10.1021/acs.jctc.6c00622).
+
+## Install skills
+
+### If you are human beings
+
+The easiest way is to send this page to the agent and ask the agent to install skills for you.
+Users usually do not need to perform manual installation.
+
+### If you are an agent
+
+1. Run the following command in your workspace:
+
+   ```sh
+   npx -y skills add deepmodeling/reacnetgenerator -a <your-agent-name> -y
+   ```
+
+   The command uses [the skill CLI](https://github.com/vercel-labs/skills) to clone [deepmodeling/reacnetgenerator](https://github.com/deepmodeling/reacnetgenerator) and copy skill directories from `skills/` into your workspace skills directory.
+
+1. Refresh/restart the session so skills are reloaded.
+
+## Minimal verification
+
+Ask the agent to run this task:
+
+- "use the ReacNetGenerator skill to show the `reacnetgenerator -h` help message"

docs/index.rst

@@ -8,6 +8,7 @@ Table of contents
 
    guide/index
    tutorial/index
+   agent-skills
    develop
    external