doc-splitter
Split large documentation (10K+ pages) into focused sub-skills with intelligent routing. Use for massive doc sites like Godot, AWS, or MSDN.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Split large documentation (10K+ pages) into focused sub-skills with intelligent routing. Use for massive doc sites like Godot, AWS, or MSDN.
Aggregate a retort run's findings.jsonl into a machine-readable assessment.json summary with severity counts, penalty score, requirement coverage, and top findings.
Document missing content in media archives with standardized GAP-NOTE markers that guide acquisition and measure completeness
Use when analyzing, validating, or filtering molecular dynamics structures. Provides composition analysis, outlier detection, chemical species identification, charge balance check, distance calculations, property filtering, and probability density analysis. Use when user asks about: structure analysis, data quality, minimum distance, composition, charge balance, outlier detection, or structure filtering.
Use when converting structure files between computational materials science formats. Supports VASP (POSCAR/OUTCAR/XDATCAR), LAMMPS, CP2K, ABACUS, CIF, MTP, ASE trajectory, and extxyz. Use when user asks about: format conversion, file conversion, structure conversion, POSCAR to xyz, OUTCAR to extxyz, LAMMPS dump conversion, or adding group labels.
Use when plotting molecular dynamics simulation results, NEP training data, or transport properties. Supports 31+ plot types including training loss, parity plots, MSD, SDC, RDF, thermodynamic properties, Arrhenius plots, phonon DOS, thermal conductivity, and descriptor visualization. Use when user asks about: plotting, visualization, training results, MSD plot, RDF plot, thermal conductivity, Arrhenius plot, or NEP training visualization.
Direct and produce Chinese-first cinematic motion videos with HyperFrames. Use this skill when the user wants a rendered promo film, article-to-video piece, product launch film, website-to-video piece, keynote reveal, kinetic typography sequence, text/icon transition promo, music-synced motion graphic, HTML/CSS/SVG/GSAP video, short-form vertical video, or a landing page/product story turned into motion. Default to Simplified Chinese, vertical 9:16, and 1080x1920 unless the user or platform clearly requires another format. The skill enforces a two-phase workflow: brief first, confirmation second, then assets, composition, validation, snapshots, render, and review report.
Induct acquired audio/video, transcript sidecars, and source metadata from media-curator into research-complete REF artifacts with timestamp citations and storage policy records
Audit research-corpus induction quality — depth bands (stub/compact/good/full/deep), structural integrity (analysis doc + sidecar + PDF, honoring audit-exclude conventions), and per-source-type required sections (a blog isn't flagged for missing Benchmark Results). Plus additive frontmatter backfill for legacy docs. Runs via `aiwg corpus induction-audit` / `aiwg corpus frontmatter-backfill`.
AUTO-INVOKE when user mentions media curation, discography, archive, music collection, video/audio collection, source acquisition, metadata tagging, transcript, Plex, Jellyfin, MPD. Media-curator framework quick reference — discovery phrases for collection assessment, source discovery, acquisition, transcription, quality filtering, metadata, archive integrity, and research handoff.