file_reader
读取与摘要文本类文件(txt、md、json、yaml、csv、log、代码文件等)。PDF 与 Office 文件由专用技能处理。
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
读取与摘要文本类文件(txt、md、json、yaml、csv、log、代码文件等)。PDF 与 Office 文件由专用技能处理。
Use BEFORE reading any data file that could be large (CSV/TSV, Parquet, HDF5, FITS, NetCDF, NDJSON, genomics FASTQ/FASTA/VCF/BAM, GRIB, ROOT, or big text/simulation logs like VASP OUTCAR). Returns a compact memory pointer — header/schema/shape/sample/key numbers — by introspection and sampling in bounded memory, so you never load a file bigger than the context window into the model. Reference data via the pointer; read specific ranges deterministically.
Use whenever you generate a chart, plot, or figure with matplotlib (or seaborn) in this workspace. Applies the Open Science publication figure style so every generated figure is publication-grade and shares one palette with the app's native charts. Not for interactive plotly/HTML — those follow the same palette manually.
Guide for writing effective technical documentation, specs, and markdown files. Use when creating or editing specs, documentation, READMEs, AGENTS.md files, or any markdown content in the codebase.
Create a visual explanation of the current session diff as a single HTML page and show it in a native Glimpse window. Use when the user wants a visual walkthrough of local code changes instead of a plain text diff.
Sanitized video clone workflow preserving login, upload, analysis, rewrite, generation, and manifest actions
Ingest ACL Anthology proceedings (main conferences AND colocated workshops) from ACLPUB or aclpub2 tarballs using bin/ingest.py. USE WHEN ingesting one or more proceedings repos/tarballs into the Anthology — a standalone/main event (create its <event> block), or workshops colocated under a parent event (e.g. acl-2026). Covers locating the ingestion root, pre-flight venue/volume validation (venue IDs, joint venues, ordinal/year venue names, volume-name consistency), running the script with the right flags, committing per volume, and recovering from common errors. DO NOT USE for editing existing volumes, author/name corrections, or website builds.
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.