Pp Autotempest logo

Pp Autotempest

CommunityPopular
mvanhorn
pp-autotempest

Every AutoTempest car-search source in your terminal, with a local store, cross-source VIN dedupe Trigger phrases: `search used cars`, `find a honda civic near me`, `compare car prices across sites`, `what cars dropped in price`, `cheapest source for this VIN`, `use autotempest`, `run autotempest`.

Overview

Publishermvanhorn
Repositoryprinting-press-library
Skill namepp-autotempest
Stars
2K
Forks
614
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mvanhorn on GitHub. Read the source before you install it.

Installation

Install the Pp Autotempest AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git /tmp/printing-press-library
mkdir -p .claude/skills
cp -r /tmp/printing-press-library/cli-skills/pp-autotempest .claude/skills/pp-autotempest
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pp Autotempest in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pp Autotempest on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pp Autotempest is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AutoTempest — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the autotempest-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. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
    bash
    npx -y @mvanhorn/printing-press-library install autotempest --cli-only
  2. Verify: autotempest-pp-cli --version
  3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

bash
go install github.com/mvanhorn/printing-press-library/library/commerce/autotempest/cmd/autotempest-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

AutoTempest already unifies the major used-car marketplaces into one search, but only in a browser. This CLI hits the same aggregated search over plain HTTP, persists listings to a local SQLite store, dedupes the same VIN across sources, and tracks price drops over time. Commands like drops, dedupe, deal, and spread turn one-shot browsing into queryable, compounding car-search state for shoppers and agents.

When to Use This CLI

Use this CLI to search used-car listings across every AutoTempest source from the terminal or an agent, persist them locally, and answer questions the website cannot: what dropped in price, which source lists a VIN cheapest, and whether a price is good versus comparable cars. It is ideal for recurring searches an agent polls and for piping car data as JSON into downstream workflows.

Anti-triggers

Do not use this CLI for:

  • Do not use this CLI to buy, bid on, finance, or contact a seller; it is read-only car search.
  • Do not use it for new-car MSRP or dealer-invoice pricing; it surfaces existing used-car listings only.
  • Do not use it for VIN history or accident reports; it reports listing data, not Carfax-style records.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Local state that compounds

  • drops — Surface listings whose price fell since a prior find or watch run, biggest drop first.

    Reach for this when an agent or shopper needs price movement over time, not a fresh listing dump.

    bash
    autotempest-pp-cli drops "civic-fl" --since 7d --min-drop 500 --agent
  • watch — Register named searches with their filters, then replay them through run so drops and diff have snapshots to compare.

    Reach for this to set up recurring searches an agent can poll; one-off queries use search instead.

    bash
    autotempest-pp-cli watch run --agent

Cross-source intelligence

  • dedupe — Collapse the same physical VIN listed on multiple marketplaces into one row with every source and price, cheapest first.

    Use when the same car appears on eBay and Cars.com and a dealer feed and you need the cheapest source for that exact VIN.

    bash
    autotempest-pp-cli dedupe --select vin,min_price,sources.source,sources.price --agent
  • deal — Rank listings by mechanical price delta from the median of comparable cars (same model, year, mileage band) in your local store.

    Pick this to answer 'is this price actually good vs comparable cars' with a number, not an opinion.

    bash
    autotempest-pp-cli deal "Camry" --select title,price,deal_score --agent
  • spread — Report min, median, and max price per marketplace for a model so you see which sources run cheap or expensive.

    Use when deciding which marketplace to shop for a given model.

    bash
    autotempest-pp-cli spread "F-150" --agent
  • auctions — Filter to eBay auction listings with live current bid and bid count, sortable by bid.

    Use when hunting auction listings rather than fixed-price inventory.

    bash
    autotempest-pp-cli auctions --select title,current_bid,bids,url --agent

Command Reference

makes — List vehicle makes AutoTempest recognizes (slug + display name).

  • autotempest-pp-cli makes — List makes. Use the returned slug (e.g. 'honda') as the --make value for find.

models — List models for a given make (slug + display name + year range).

  • autotempest-pp-cli models <make> — List models for a make. Pass the make slug (e.g. 'honda'); use the returned model slug as --model for find.

sources — List the AutoTempest search sources and their kind.

  • autotempest-pp-cli sources — Two kinds: inline sources (te, hem, cs, cv, cm, eb, ot) return parsed per-car listings; link sources (fbm = Facebook Marketplace, st = SearchTempest / Craigslist) are comparison-link-only because those sites block scraping or require login. find defaults to the 7 inline sources; pass --sites fbm,st to also get their comparison URLs in the comparison_links array.

Finding the right command

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

bash
autotempest-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.

Recipes

Clean-title AWD under budget near me

bash
autotempest-pp-cli find "subaru outback" --zip 33701 --radius 150 --max-price 28000 --title clean --drive awd --json --select title,price_cents,mileage,location,sitecode

Narrows a deeply nested multi-source live result to the fields that matter using --select.

Cheapest source for a specific VIN

bash
autotempest-pp-cli dedupe --select vin,min_price,sources.source,sources.price --json

Shows each physical car once with every marketplace and price it appears at.

What dropped in price this week

bash
autotempest-pp-cli drops "my-search" --since 7d --min-drop 500 --json

Compares local price snapshots to surface motivated sellers.

Is this price good

bash
autotempest-pp-cli deal "tacoma" --select title,price,deal_score --json

Scores each listing against the median of comparable cars in your store.

Auth Setup

No authentication required.

Run autotempest-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:

    bash
    autotempest-pp-cli makes --agent --select id,name,status
  • Previewable--dry-run shows the request without sending

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

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

  • Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

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

json
{
  "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 AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.

Agent Feedback

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

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

Entries are stored locally at ~/.local/share/autotempest-pp-cli/feedback.jsonl. They are never POSTed unless AUTOTEMPEST_FEEDBACK_ENDPOINT is set AND either --send is passed or AUTOTEMPEST_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:

SinkEffect
stdoutDefault; 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.

autotempest-pp-cli profile save briefing --json
autotempest-pp-cli --profile briefing makes
autotempest-pp-cli profile list --json
autotempest-pp-cli profile show briefing
autotempest-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

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

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show autotempest-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

  1. Install the MCP server:
    bash
    go install github.com/mvanhorn/printing-press-library/library/commerce/autotempest/cmd/autotempest-pp-mcp@latest
  2. Register with Claude Code:
    bash
    claude mcp add autotempest-pp-mcp -- autotempest-pp-mcp
  3. Verify: claude mcp list

Direct Use

  1. Check if installed: which autotempest-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:
    bash
    autotempest-pp-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help: autotempest-pp-cli <command> --help.

Frequently asked questions

What does the Pp Autotempest AI skill do?

Every AutoTempest car-search source in your terminal, with a local store, cross-source VIN dedupe Trigger phrases: `search used cars`, `find a honda civic near me`, `compare car prices across sites`, `what cars dropped in price`, `cheapest source for this VIN`, `use autotempest`, `run autotempest`.

Why use Pp Autotempest on TypingMind?

Because you install it once and use it with any model. Pp Autotempest is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pp Autotempest in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-autotempest. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pp Autotempest?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pp Autotempest?

As many as you like. As long as a model supports skills, you can use Pp Autotempest with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pp Autotempest AI skill free?

Yes. It is published on GitHub by mvanhorn under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇