AGENT SKILL

pp-podscan

Search 51M+ podcast episodes and 4.4M+ podcasts via Podscan — full transcripts, AI-extracted entities, mentions, and brand-safety analysis. Trigger phrases: `search podcast transcripts`, `find podcasts mentioning`, `who's talked about <topic> on podcasts`, `use podscan`.

License 许可
Apache-2.0
最近更新
2026-05-22
Stars
★ 0
Forks
0

01 前言 Front Matter

name
pp-podscan
author
Greg Van Horn
license
Apache-2.0
metadata
{ "openclaw": { "requires": { "bins": [ "podscan-pp-cli" ] } } }
description
Search 51M+ podcast episodes and 4.4M+ podcasts via Podscan — full transcripts, AI-extracted entities, mentions, and brand-safety analysis. Trigger phrases: `search podcast transcripts`, `find podcasts mentioning`, `who's talked about <topic> on podcasts`, `use podscan`.
allowed-tools
Read Bash
argument-hint
<command> [args] | install cli|mcp

02 资源文件 71

03 SKILL.md 正文

Podscan — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the podscan-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. Install via the Printing Press installer:
    npx -y @mvanhorn/printing-press install podscan --cli-only
    
  2. Verify: podscan-pp-cli --version
  3. Ensure $GOPATH/bin (or $HOME/go/bin) is on $PATH.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):

go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/podscan/cmd/podscan-pp-cli@latest

If --version reports "command not found" after install, the install step did not put the binary on $PATH. Do not proceed with skill commands until verification succeeds.

Podscan REST API — search 51M+ podcast episodes and 4.4M+ podcasts. Full transcripts, AI-extracted entities, mentions, brand-safety analysis.

Command Reference

alerts — Manage alerts

  • podscan-pp-cli alerts create — Create a new alert
  • podscan-pp-cli alerts delete — Delete an alert
  • podscan-pp-cli alerts get — Get an alert
  • podscan-pp-cli alerts list — List configured alerts

categories — Manage categories

  • podscan-pp-cli categories — List all podcast categories

episodes — Manage episodes

  • podscan-pp-cli episodes get — Get an episode by ID
  • podscan-pp-cli episodes search — Search episodes by transcript content

exports — Manage exports

  • podscan-pp-cli exports download — Download an export file
  • podscan-pp-cli exports list-episode — List daily episode export files
  • podscan-pp-cli exports list-podcast — List podcast catalog export files

podcasts — Manage podcasts

  • podscan-pp-cli podcasts get — Get a podcast by ID
  • podscan-pp-cli podcasts search — Search podcasts by name or description

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

podscan-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Auth Setup

Store your access token:

podscan-pp-cli auth set-token YOUR_TOKEN_HERE

Or set PODSCAN_BEARER_AUTH as an environment variable.

Run podscan-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

  • Pipeable — JSON on stdout, errors on stderr

  • Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

    podscan-pp-cli alerts list --agent --select id,name,status
    
  • Previewable — --dry-run shows the request without sending

  • Offline-friendly — sync/search commands can use the local SQLite store when available

  • Non-interactive — never prompts, every input is a flag

  • Explicit retries — use --idempotent only when an already-existing create should count as success, and --ignore-missing only when a missing delete target should count as success

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal — piped/agent consumers get pure JSON on stdout.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

podscan-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
podscan-pp-cli feedback --stdin < notes.txt
podscan-pp-cli feedback list --json --limit 10

Entries are stored locally at ~/.podscan-pp-cli/feedback.jsonl. They are never POSTed unless PODSCAN_FEEDBACK_ENDPOINT is set AND either --send is passed or PODSCAN_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

Sink Effect
stdout Default; write to stdout only
file:<path> Atomically write output to <path> (tmp + rename)
webhook:<url> POST the output body to the URL (application/json or application/x-ndjson when --compact)

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.

podscan-pp-cli profile save briefing --json
podscan-pp-cli --profile briefing alerts list
podscan-pp-cli profile list --json
podscan-pp-cli profile show briefing
podscan-pp-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

Code Meaning
0 Success
2 Usage error (wrong arguments)
3 Resource not found
4 Authentication required
5 API error (upstream issue)
7 Rate limited (wait and retry)
10 Config error

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show podscan-pp-cli --help output
  2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
  3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

Install the MCP binary from this CLI's published public-library entry or pre-built release, then register it:

claude mcp add podscan-pp-mcp -- podscan-pp-mcp

Verify: claude mcp list

Direct Use

  1. Check if installed: which podscan-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
  2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
  3. Execute with the --agent flag:
    podscan-pp-cli <command> [subcommand] [args] --agent
    
  4. If ambiguous, drill into subcommand help: podscan-pp-cli <command> --help.

04 同仓库更多 Skills

shekerkamma
shekerkamma/peopletech-marketplace

pp-wikipedia

Printing Press CLI for Wikipedia. Wikipedia REST API. Get article summaries, search, browse related topics, and access on-this-day events. No...

★ 0
shekerkamma
shekerkamma/peopletech-marketplace

pp-trigger-dev

Every Trigger.dev management endpoint, plus offline FTS over runs, span-cost rollups, and zombie-schedule detection no other tool gives you. Trigger phrases: `trigger.dev failed runs`, `trigger.dev cost rollup`, `trigger.dev schedule health`, `audit trigger.dev env vars`, `watch trigger.dev failures`, `use trigger-dev`, `run trigger-dev`.

★ 0
shekerkamma
shekerkamma/peopletech-marketplace

pp-substack

Run your Substack growth loop from the command line — publish, schedule, engage, and measure with cross-table... Trigger phrases: `post a substack note`, `schedule a week of substack notes`, `find substack swap partners`, `which of my notes drove subs`, `what's my engagement reciprocity`, `voice-match a substack note`, `best time to post on substack`, `use substack`, `run substack`.

★ 0
shekerkamma
shekerkamma/peopletech-marketplace

pp-slack

Slack workspace CLI for the terminal. Send messages, search channels and DMs, list conversations, get user/bot/emoji info, analyze channel health, find stale threads, and sync the workspace locally for fast offline queries. Two auth surfaces coexist: SLACK_BOT_TOKEN (xoxb-, for workspace-wide read + post) and SLACK_USER_TOKEN (xoxp-, for user-scoped actions like DM history or search). Use when the user asks to send a Slack message, search Slack, check channel activity, summarize a digest, find who's on a team, find stale threads, analyze channel health, list users / emoji / reminders / pinned items, or wants offline-capable Slack queries.

★ 0
shekerkamma
shekerkamma/peopletech-marketplace

pp-scrape-creators

Every Scrape Creators endpoint, plus offline search, cross-platform compounding, and a local store no other Scrape Creators tool ships with. Trigger phrases: `scrape creators`, `tiktok profile`, `instagram profile`, `youtube channel`, `facebook ad library`, `creator on every platform`, `social media transcript search`, `use scrape-creators`, `run scrape-creators`.

★ 0
shekerkamma
shekerkamma/peopletech-marketplace

pp-postman-explore

The CLI for the public API directory at postman.com/explore — search, rank, and watch community-contributed Postman Collections, agent-native and offline. Trigger phrases: `find a postman collection for`, `what postman collection should i fork for`, `is there a postman collection for`, `browse postman api network`, `compare postman publishers`, `what changed on the postman network`, `use postman-explore`, `run postman-explore`.

★ 0