How to use catalog-input-files
Agent-agnostic skill that catalogs task input files into reusable Markdown structural explanations and a per-task SQLite search index. Supports 30+ formats — delimited tables with automatic delimiter detection, Excel, Parquet/Feather, JSON/YAML/TOML, SQLite, ZIP/TAR/GZIP, XML/HTML, Jupyter notebooks, Stata, RDS/RData, PDF, DOCX, images — plus source-structure extraction for 20+ programming languages. Works with OpenAI Codex, Claude Code, and DeepSeek Harness.
This article is auto-derived from indexed fields (wiki / faq / compatibility_json), not freshly AI-generated.
This article is derived from the plugin's already-indexed fields (wiki / faq / compatibility_json / readme), not freshly generated by AI. Source field is noted at the end of each section.
Quick start
Agent-agnostic skill that catalogs task input files into reusable Markdown structural explanations and a per-task SQLite search index. Supports 30+ formats — delimited tables with automatic delimiter detection, Excel, Parquet/Feather, JSON/YAML/TOML, SQLite, ZIP/TAR/GZIP, XML/HTML, Jupyter notebooks, Stata, RDS/RData, PDF, DOCX, images — plus source-structure extraction for 20+ programming languages. Works with OpenAI Codex, Claude Code, and DeepSeek Harness.
— source: plugins.ai_summary
Install & verify
dsh plugin --profile web add github:Zhiyi-Zhao/codex-catalog-input-files
Run the command above in your DSH Web Profile. Then enable the plugin in the plugin list.
— source: plugins.install
Pitfalls
Review the upstream repo before installing. This guide is auto-derived from indexed fields and may lag the latest release. If anything contradicts the official docs, treat the upstream source as authoritative.
— source: general rule