Check what's playing on WRHV 88.7 FM (Classical WMHT), fetch recent tracks, build playlist reports, search for pieces, and create or manage Spotify playlists from radio tracks. Triggers on 'Classical 887', 'WRHV', 'what's playing', 'classical radio', 'Hudson Valley radio', 'Spotify playlist from radio'.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Check what's playing on WRHV 88.7 FM (Classical WMHT) — the classical music station in the Hudson Valley. Queries the NPR Composer API for real-time playlist data and provides clickable links to listen on YouTube, Spotify, Apple Music, IMSLP, IDAGIO, Internet Archive, and Musopen.
requests Python package (uv pip install --system requests)spotipy package (uv pip install --system spotipy) + Spotify Developer App credentials# What's playing right now (default)
python3 ~/.claude/skills/classical-887/scripts/classical_887.py
# Last 10 tracks
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --recent 10
# Today's full playlist (pages through all tracks for today)
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --period today
# Last week as Markdown report
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --period week --markdown ~/Desktop/classical-week.md
# Last month as Markdown report
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --period month --markdown ~/Desktop/classical-month.md
# Specific date (Valentine's Day)
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --date 2026-02-14
# Search for a composer across a date range
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --period week --search bach
# Full performer details (album, label, catalog number)
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --recent 5 --verbose
# Raw JSON output
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --now --json
# Create Spotify playlist from today's tracks
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --period today --spotify-playlist
# Add yesterday's tracks to the persistent playlist
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --period yesterday --spotify-playlist
# Custom playlist name from a specific date
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --date 2026-02-14 --spotify-playlist "Valentine's Classical"
# Last week's Bach on Spotify
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --period week --search bach --spotify-playlist "Bach on 88.7"
# Rename the default playlist
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-rename "Hudson Valley Classical"
# Rename a specific playlist with a new description
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-playlist "Bach on 88.7" --spotify-rename "Bach Collection" --spotify-description "Curated Bach from WRHV 88.7 FM"
# View playlist operation log as Markdown
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-log-report
# Audit all owned Spotify playlists
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-audit
# Audit with search filter and sort by track count
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-audit --search "Rediscover*" --sort tracks
# Dry run cleanup (preview only, no deletion)
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-cleanup "Rediscover*"
# Execute cleanup with safety cap
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-cleanup "Rediscover*" --confirm --max 10
# Export playlist tracks to JSON before cleanup
python3 ~/.claude/skills/classical-887/scripts/classical_887.py --spotify-export ~/Desktop/exports --search "Rediscover*"
| Flag | Description | Default |
|---|---|---|
--now | Show what's playing now | On (if no other mode) |
--recent N | Show last N tracks (1–100) | Off |
--date YYYY-MM-DD | Fetch all tracks from a specific date | Off |
--period PERIOD | Fetch tracks from: today, yesterday, week, month | Off |
--search QUERY | Filter results by composer, piece, or performer | Off |
--verbose | Full details (album, label, catalog, all performers) | Off |
--json | Raw JSON output | Off |
--markdown [FILE] | Write Markdown report with clickable links | classical-playlist.md |
--sort FIELD | Sort by: time (newest first), duration (longest), composer (A–Z) | time |
--spotify-playlist [NAME] | Create/append to a Spotify playlist | Classical 88.7 FM |
--spotify-rename NEW_NAME | Rename an existing Spotify playlist (defaults to renaming Classical 88.7 FM unless --spotify-playlist specifies the current name) | Off |
--spotify-description DESC | Set new description when renaming (used with --spotify-rename) | Off |
--spotify-log-report | View the playlist operation log as a Markdown report | Off |
--spotify-audit | List all owned Spotify playlists (combine with --search and --sort) | Off |
--spotify-cleanup PATTERN | Remove playlists matching glob pattern (dry run unless --confirm) | Off |
--spotify-export [DIR] | Export matching playlist tracks to JSON files | . |
--confirm | Execute cleanup (without this, --spotify-cleanup is preview only) | Off |
--max N | Safety cap: max playlists to remove per invocation | No limit |
--spotify-client-id ID | Spotify app client ID (or SPOTIFY_CLIENT_ID env var) | — |
--spotify-client-secret SECRET | Spotify app client secret (or SPOTIFY_CLIENT_SECRET env var) | — |
Default shows: composer, piece, performers, duration, and listen links (YouTube, Spotify, Apple Music, IMSLP, IDAGIO, Internet Archive, Musopen).
Markdown report includes: now-playing header, recent tracks table with 7 platform links, and a composer index.
Every --spotify-playlist operation automatically appends a JSONL entry to ~/.claude/skills/classical-887/playlist-log.jsonl. Each entry records:
View the log as a Markdown report with --spotify-log-report. The log file is append-only and can be queried with standard jq commands:
# Count total operations
wc -l ~/.claude/skills/classical-887/playlist-log.jsonl
# Show all playlist names used
cat ~/.claude/skills/classical-887/playlist-log.jsonl | jq -r '.playlist_name' | sort -u
# Total tracks matched across all operations
cat ~/.claude/skills/classical-887/playlist-log.jsonl | jq '.matched_count' | paste -sd+ | bc
NPR Composer API (api.composer.nprstations.org/v1/widget/), which powers the WMHT playlist widget at classicalwmht.org/playlist.
Full API documentation: references/api-reference.md
WRHV 88.7 FM (Poughkeepsie, NY), simulcast of WMHT-FM 89.1 (Schenectady). Full station details in references/api-reference.md.
If the NPR Composer API is unavailable:
# Check the playlist page directly
firecrawl scrape "https://classicalwmht.org/playlist" --only-main-content
| File | Contents |
|---|---|
references/api-reference.md | NPR Composer API: endpoints, request/response schema, field reference |
references/spotify-setup.md | Spotify Developer App setup, OAuth, env vars, Dev Mode notes |
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Search academic papers, build literature reviews, and synthesize research findings — combines Exa MCP (research_paper category, arxiv filtering) with arxiv-mcp-server for paper discovery, download, and deep analysis. Triggers on academic paper, literature review, research synthesis, arxiv, find papers, scholarly search.
日本語の概要は準備中です。原文の説明を表示しています。
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used when creating, auditing, or maintaining AGENTS.md files and Codex CLI configuration for any project—including initializing AGENTS.md for cross-agent compatibility (Codex, Cursor, Copilot, Devin, Jules, Amp, Gemini CLI), generating config.toml or .rules files, scaffolding .agents/skills/, converting CLAUDE.md to AGENTS.md, or auditing existing agent configs for bloat and staleness. Complementary to codex-orchestrator (which executes subagents; this skill creates the config files they consume).
日本語の概要は準備中です。原文の説明を表示しています。
Academic research skill for Biblical Hebrew, Semitic linguistics, cuneiform studies, and comparative Ancient Near Eastern research. Provides Sefaria API for Hebrew Bible, CDLI/ORACC for cuneiform databases, and web discovery via Omnisearch, Exa, Firecrawl, and Obscura for finding scholarly sources across JSTOR, Perseus, Persée, Google Scholar, and academia.edu. Triggers on Hebrew quotes, cuneiform, Sefaria, ANE research, Minoan, search for scholarship, find papers, literature review, scholarly search, academic search, Genesis/Tehom, Ugaritic, Talmudic sources, extract from PDF, OCR academic.
日本語の概要は準備中です。原文の説明を表示しています。
Build comprehensive ARCHITECTURE.md files following matklad's canonical guidelines — bird's-eye views, ASCII/Mermaid diagrams, codemaps, invariants, and layer boundaries. Triggers on document the architecture, create ARCHITECTURE.md, map this codebase, architectural overview.
日本語の概要は準備中です。原文の説明を表示しています。
Generate physically-based atmospheric scattering shaders — sky domes, planetary atmospheres, LUT-optimized pipelines, depth-aware post-processing. Four modes — sky-dome, atmosphere-post, planet, lut. Triggers on atmospheric scattering, sky shader, sunset rendering, planet atmosphere, Rayleigh scattering, Mie scattering, volumetric sky, sky dome, atmosphere post-processing, aerial perspective, transmittance LUT, sky rendering, realistic sky, planetary rendering.
日本語の概要は準備中です。原文の説明を表示しています。