pp-trustpilot
Every Trustpilot review surface, plus the local SQLite database and balanced good-and-bad agent bundle no other... Trigger phrases: `trustpilot reviews for <company>`, `what do customers say about <company>`, `good and bad reviews for <company>`, `trustscore for <company>`, `is <company> trustworthy`, `use trustpilot`, `run trustpilot`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/marketing/trustpilot/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# Trustpilot — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `trustpilot-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install trustpilot --cli-only
```
2. Verify: `trustpilot-pp-cli --version`
3. Ensure the reported install directory is on `$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 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/marketing/trustpilot/cmd/trustpilot-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.
## When to Use This CLI
Reach for Trustpilot CLI when an agent or researcher needs consumer reviews for a company by domain or name. Best fit: enriching a research narrative with a balanced recent good+bad sample, tracking TrustScore drift over time, comparing several companies in one call, or grepping synced reviews for a term (`refund`, `chargeback`) with star and date filters. Pairs cleanly with last30days for story enrichment.
## When Not to Use This CLI
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### last30days agent bridge
- **`top-recent`** — Pulls N freshest 4-5 star reviews and N freshest 1-2 star reviews for a company in one call, so agents can quote a balanced view without two separate scrapes.
_When an agent is summarizing what consumers say about a company in the last 30 days, this is the one command that returns a balanced citable sample._
```bash
trustpilot-pp-cli top-recent thriftbooks.com --window 30d --good 5 --bad 5 --json
```
- **`agent-bundle`** — Returns a single JSON payload with company metadata, TrustScore, Trustpilot's own AI summary, top recent good and bad reviews, and the 5-bin rating histogram — everything an external agent needs in one call.
_If you only call one Trustpilot command from another agent, call this one. It is purpose-built for last30days-style story enrichment._
```bash
trustpilot-pp-cli agent-bundle thriftbooks.com --json --select company.trustScore,company.numberOfReviews,topRecent.good,topRecent.bad,histogram
```
### Local state that compounds
- **`drift`** — Week-over-week TrustScore, 1-star %, 5-star %, and review volume reconstructed from locally synced reviews. Trustpilot exposes only the current TrustScore; this surfaces history.
_Use before claiming a company's reputation is improving or declining; one query gives you the weekly trend with star-mix breakdown._
```bash
trustpilot-pp-cli drift thriftbooks.com --weeks 12 --json
```
- **`compare`** — Side-by-side TrustScore, review velocity, and 1/5-star mix across N companies over a chosen window, all read from the local synced store.
_Best command for landscape analysis before recommending a vendor or writing a comparison piece._
```bash
trustpilot-pp-cli compare thriftbooks.com bookshop.org powells.com --window 90d --json
```
- **`surge`** — Detects statistically significant spikes in total review volume or 1-star volume against a rolling baseline using Z-scores over locally synced rows.
_Run this before publishing on a company; a fresh 1-star surge is the headline you would otherwise miss._
```bash
trustpilot-pp-cli surge thriftbooks.com --baseline 90d --window 7d --stars 1 --json
```
- **`search-reviews`** — Full-text search over synced review titles, bodies, and business replies with star, language, and date filters. FTS5-backed, works offline.
_When the question is 'what did 1-star reviewers say about refunds in the last 90 days', this is the only command that answers it._
```bash
trustpilot-pp-cli search-reviews thriftbooks.com 'refund' --stars 1 --window 90d --lang en --json
```
- **`replies`** — Reply rate by star bucket over synced reviews, plus a listing of unreplied 1-stars when --unreplied is set.
_Companies that ignore 1-stars predict customer-support failure; this is the one-line audit for it._
```bash
trustpilot-pp-cli replies thriftbooks.com --unreplied --stars 1 --json
```
- **`geo`** — Reviewer-country distribution over a window with per-country count, average rating, and 1-star rate.
_Use when sentiment differs by region; the country breakdown is the first signal of a localized incident._
```bash
trustpilot-pp-cli geo thriftbooks.com --window 90d --json
```
- **`whats-new`** — Lists reviews that arrived since the last sync, bucketed by star rating, so an agent can poll for fresh customer feedback without re-fetching everything.
_Best for scheduled agents that want the delta, not the full archive._
```bash
trustpilot-pp-cli whats-new thriftbooks.com --since 2026-05-01 --json
```
### Trustpilot-native enrichment
- **`topics`** — Surfaces Trustpilot's own pre-computed topic AI summaries (e.g., 'shipping', 'price', 'condition') as JSON.
_When you need labeled clusters of what reviewers actually talk about, Trustpilot already did the clustering — this surfaces it._
```bash
trustpilot-pp-cli topics thriftbooks.com --json
```
- **`similar-sweep`** — Takes the 8 'similar businesses' Trustpilot returns for a company, fetches each one's info in parallel, and ranks them by TrustScore and total reviews.
_Auto-discovered competitor set with metrics — perfect for prospecting or a competitor list you didn't curate._
```bash
trustpilot-pp-cli similar-sweep thriftbooks.com --json
```
- **`category-top`** — Ranks the companies in a Trustpilot category by TrustScore (with an optional minimum-review floor).
_When you want 'best online bookstore on Trustpilot with at least 100 reviews', this is the one query._
```bash
trustpilot-pp-cli category-top online-bookstore --limit 25 --min-reviews 100 --json
```
## HTTP Transport
This CLI uses Chrome-compatible HTTP transport for browser-facing endpoints. It does not require a resident browser process for normal API calls.
## Command Reference
**companies** — Search Trustpilot for companies by name and resolve to their canonical domain
- `trustpilot-pp-cli companies <search_build_id>` — Search for companies matching a name; returns identifyingName domains usable with reviews fetch
**reviews** — Fetch Trustpilot reviews for a company
- `trustpilot-pp-cli reviews <review_build_id> <domain>` — Fetch a page of reviews for a company by domain (use 'reviews fetch <domain>' from the CLI). Authenticated via...
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
trustpilot-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.
## ReRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.