Agent Infini Agent Skill
Use the InfiniSynapse CLI (`agent_infini`) for multi-turn AI data-analysis tasks, database/RAG context, and task workspace files. Use when the user mentions InfiniSynapse, agent_infini, database or RAG analysis, or asks to delegate analysis through InfiniSynapse.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/xuzhougeng/wisp-science --skill agent-infiniThe instruction itself
5 sections, as written by the authoragent_infini
agent_infini talks to the InfiniSynapse backend REST API. Use it for database-backed analysis, RAG-backed analysis, multi-turn task conversations, and task workspace files.
Default binary locations:
- Linux/macOS:
~/.infini/bin/agent_infini - Windows:
%USERPROFILE%\.infini\bin\agent_infini.exe
If agent_infini is not on PATH, call the full path.
Credential setup
wisp-science stores the InfiniSynapse API key in Settings -> Credentials and initializes the CLI with:
agent_infini init --api-key "sk-xxx"
If the CLI is missing, install it:
irm https://infinisynapse.cn/cli-install/install.ps1 | iex
curl -fsSL https://infinisynapse.cn/cli-install/install.sh | bash
Do not print API keys or dump config files. If authentication fails, ask the user to update the InfiniSynapse API key in Settings -> Credentials or rerun agent_infini init.
Recommended workflow
- Check the CLI:
agent_infini version - List resources:
agent_infini db lsandagent_infini rag ls - Check enabled context:
agent_infini task context - Enable needed context:
agent_infini db enable <id>oragent_infini rag enable <id> - Start a task:
agent_infini task new "..." - Continue the same task:
agent_infini task ask <taskId> "..." - Inspect outputs:
agent_infini task file <taskId>,preview, ordownload
Commands
agent_infini task new "Analyze user growth trend"
agent_infini task ask <taskId> "Show it as a bar chart"
agent_infini task ls [--page N] [--page-size N] [--search Q]
agent_infini task show <taskId>
agent_infini task context
agent_infini task cancel <taskId>
agent_infini task rm <id1> [id2 ...]
agent_infini task file <taskId>
agent_infini task preview <taskId> <fileName>
agent_infini task download <taskId> <fileName> [-o dir]
agent_infini db ls [--name N] [--type T] [--enabled] [--disabled]
agent_infini db enable <id> [id...]
agent_infini db disable <id> [id...]
agent_infini rag ls [--keyword K] [--enabled] [--disabled]
agent_infini rag enable <id> [id...]
agent_infini rag disable <id> [id...]
Useful global flags:
--json: force JSON output--table: force table output for list commands--api-key <key>: override configured API key for this call--server <url>: override server address--console <url>: override Console API URL--prefer-language <lang>:en,zh_CN,ar,ja,ko,ru
Output and errors
Default output is JSON:
{"success": true, "data": {}}
{"success": false, "error": "error message"}
Common fixes:
- Token expired: update Settings -> Credentials or rerun
agent_infini init - Server unreachable: check network and
--server - Task not found: run
agent_infini task ls - No enabled resources: run
agent_infini task context, then enable DBs/RAGs
Other skills for the same job
different authors, same section of the catalogue
Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.
Python interface to OpenMS for mass spectrometry data analysis. Use for LC-MS/MS proteomics and metabolomics workflows including file handling (mzML, mzXML, mzTab, FASTA, pepXML, protXML, mzIdentML), signal processing, feature detection, peptide identification, and quantitative analysis. Apply when working with mass spectrometry data, analyzing proteomics experiments, or processing metabolomics datasets.
Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.
How to use it
Take xuzhougeng/agent-infini from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.