pp-trendhunter
Every Trend Hunter feature, plus a local SQLite corpus, FTS5 search, FAQ Q&A extraction, and agent-native JSON no... Trigger phrases: `what's trending on trendhunter`, `search trendhunter for`, `weekly trend digest`, `trend hunter FAQ for`, `rising keywords on trendhunter`, `active trend hunters this month`, `use trendhunter`, `run trendhunter-pp-cli`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/marketing/trendhunter/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/". -->
# Trend Hunter — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `trendhunter-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install trendhunter --cli-only
```
2. Verify: `trendhunter-pp-cli --version`
3. Ensure the reported install directory is on `$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/trendhunter/cmd/trendhunter-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
Use this CLI when you want TrendHunter data inside an agent loop, a script, or a daily routine - rather than clicking the site by hand. It's strongest for week-over-week trend monitoring, FAQ-style trend summaries an LLM can quote, and corpus-wide keyword clustering. It's a free, no-auth scraper; for the official paid API surface, use TrendHunter's commercial offering instead.
## 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.
### Local state that compounds
- **`digest`** — Generate a week-over-week digest of new vs repeat trends in a category with top rising keywords.
_Agents pulling a weekly competitive scan can ask 'what's new in eco this week' without re-clicking 30 cards by hand._
```bash
trendhunter-pp-cli digest --since 7d --category eco --json
```
- **`watch`** — Per-category new-only feed - fills the gap that TrendHunter's RSS is global-only.
_Agents and indie scouts get a clean delta for one vertical without re-processing the global firehose._
```bash
trendhunter-pp-cli watch --category gadgets --since 24h --json
```
- **`cluster`** — Surface rising keyword clusters via FTS5 co-occurrence with a rising-vs-prior-window delta.
_Agents researching an emerging theme see which adjacent keywords are accelerating, not just the headline trends._
```bash
trendhunter-pp-cli cluster --window 30d --min-count 3 --json
```
- **`authors`** — Rank TrendHunter authors and futurists by time-windowed publish rate, not lifetime count.
_Find which trend hunters are currently active in your space, not just who has the biggest historical footprint._
```bash
trendhunter-pp-cli authors --top 20 --since 30d --json
```
- **`inbox`** — Show trends seen since the last invocation of `inbox` - a per-machine cursor table.
_Build it into a Monday-morning routine and only ever see things you haven't seen before._
```bash
trendhunter-pp-cli inbox --json
```
### Agent-native extraction
- **`faq`** — Extract the FAQPage JSON-LD from a trend page into structured Q&A.
_Agents get a ready-to-quote Q&A summary of each trend without prompting another LLM to summarize the article._
```bash
trendhunter-pp-cli faq ai-clone --json
```
- **`brief`** — One-shot agent brief: top-N ranked trends in a category, each with FAQ Q&A and keywords, rendered as JSON or markdown.
_Plugs straight into an agent prompt as ground truth for a market memo, no glue code needed._
```bash
trendhunter-pp-cli brief --category ai --top 10 --format markdown
```
- **`scout`** — Pull top trends in a category, score each by relevance to a business profile, optionally route the scoring through a local LLM.
_Agents researching a vertical get a ranked, business-scoped trend list ready to pipe into the next stage of their pipeline._
```bash
trendhunter-pp-cli scout --category kitchen --business "We sell smart ovens for home cooks" --top 10 --llm
```
### Graph and synthesis
- **`megatrend-map`** — Walk the related-trend graph two levels deep from a starting slug, returning depth-1 and depth-2 related slugs so you can see which free trends cluster around a given concept.
_Evaluators deciding whether a paid megatrend report is worth $295 can see which free trends ladder up to it._
```bash
trendhunter-pp-cli megatrend-map ai-clone --json
```
## Discovery Signals
This CLI was generated with browser-observed traffic context.
- Capture coverage: 11 API entries from 30 total network entries
- Protocols: html (100% confidence), rss (100% confidence)
- Generation hints: Use stdlib HTTP transport (http_transport: standard)., Default UA must imitate Chrome - curl default UA is blocked., Default Accept header must be Chrome-style 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' - bare '*/*' is blocked., RSS feed is global only. Per-category RSS returns valid-but-empty channels; do not call them., Trend pages occasionally redirect to vertical microsites (cleanthesky.com, etc.). Follow redirects; record the canonical /trends/<slug> URL., FAQPage JSON-LD on /trends/<slug> is the highest-density agent-summary surface; extract with the faq command., No clearance cookie, no Surf, no browser sidecar.
## Command Reference
**category** — Category index pages (tech, fashion, food, eco, ai, marketing, design, ...)
- `trendhunter-pp-cli category <category>` — Fetch a TrendHunter category index page (~30 trend cards). The CLI's 'category <name>' command parses this.
**megatrends** — Megatrend / pattern index pages.
- `trendhunter-pp-cli megatrends` — Fetch the megatrend index page.
**popular** — Curated 'popular right now' index.
- `trendhunter-pp-cli popular` — Fetch the popular-trends index page (~30 cards). Run 'popular' to get parsed JSON.
**reports** — Trend report index.
- `trendhunter-pp-cli reports` — Fetch the trend-reports landing page (titles, descriptions, paid PDF links).
**results** — Site search-results endpoint (the framework already provides a hand-built `search` command; this exposes the raw HTML page).
- `trendhunter-pp-cli results` — Run a TrendHunter search and get the result-page HTML. The CLI's 'search <term>' parses this; pass --raw to get HTML.
**rss** — Global RSS feed of the 30 latest trends across the whole site.
- `trendhunter-pp-cli rss` — Fetch the global RSS 2.0 feed (~30 newest trends). Use 'sync' to land these in the local store; this raw endpoint is...
**scoreboard** — Top contributors and trends scoreboard.
- `trendhunter-pp-cli scoreboard` — Fetch the scoreboard page with top contributor handles and recent trends. Run 'scoreboard' to get parsed JSON.
**sitemap** — Master sitemap with 430+ URLs (categories, futurists, contributors, hubs).
- `trendhunter-pp-cli sitemap` — Fetch the sitemap.xml. The CLI's 'catalog refresh' uses this; users should use that instead.
**trends** — Individual trend pages with full metadata, FAQ Q&A, related trends, author, category.
- `trendhunter-pp-cli trends <slug>` — Fetch the full trend page HTML for a slug. The CLI's 'trend show <slug>' parses this; users should use that instead...
**Hand-written commands**
- `trendhunter-pp-cli sync` — Sync the globRelated 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.