Take support ticket clusters, FAQ patterns, product documentation, or feature specs and generate structured help center articles with step-by-step instructions, screenshot placeholders, troubleshooting sections, and related article links. Batch mode generates multiple articles from a ticket export. Pure reasoning skill.
npx gooseworks install --all # then, in Claude Code, Cursor, or Codex: /gooseworks use the help-center-article-generator skill
Turn support tickets into self-serve answers. Takes repeated questions, feature docs, or product specs and generates help center articles that reduce ticket volume.
Built for: Early-stage teams where the same 20 questions make up 80% of support tickets, and nobody has time to write help docs. The goal is to turn one afternoon of article generation into months of ticket deflection.
[Screenshot: description] placeholders)If provided a ticket export, cluster tickets into article topics:
| Type | When to Use | Example |
|---|---|---|
| How-to | "How do I do X?" | "How to set up email integration" |
| Troubleshooting | "X isn't working" | "Fix: emails not sending" |
| Concept/Overview | "What is X?" | "Understanding billing plans" |
| Reference | "What are the options for X?" | "API rate limits and quotas" |
| Getting Started | First-time setup | "Quick start: your first campaign" |
TOPIC CLUSTERS (ranked by ticket frequency):
1. [Topic] — [N tickets] — Type: [How-to]
Common phrasing: "[How customers ask this question]"
Resolution pattern: [What support typically tells them]
2. [Topic] — [N tickets] — Type: [Troubleshooting]
...
3. ...# [Action-oriented title — e.g., "How to Set Up Email Integration"]
[1-2 sentence overview: What this article covers and who it's for]
**Time to complete:** [X minutes]
**Prerequisites:** [What they need before starting — e.g., "Admin access, API key"]
---
## Step 1: [Action verb + what to do]
[1-2 sentences explaining this step]
[Screenshot: Description of what the user should see — e.g., "Settings page with Integrations tab highlighted"]
> **Tip:** [Helpful context or shortcut]
## Step 2: [Action verb + what to do]
[Instructions]
[Screenshot: Description]
## Step 3: [Action verb + what to do]
[Instructions]
---
## Verify It Worked
[How to confirm the setup was successful]
[Screenshot: Description of success state]
---
## Troubleshooting
### [Common problem 1]
**Symptom:** [What the user sees]
**Cause:** [Why this happens]
**Fix:** [Step-by-step resolution]
### [Common problem 2]
**Symptom:** [...]
**Cause:** [...]
**Fix:** [...]
---
## FAQ
**Q: [Common follow-up question]**
A: [Answer]
**Q: [Another common question]**
A: [Answer]
---
## Related Articles
- [[Article title]] — [1-line description of when to read it]
- [[Article title]] — [...]# Fix: [Problem description — e.g., "Emails Not Sending"]
[1-2 sentences: When you'd encounter this problem]
---
## Quick Fix
Try this first (resolves ~80% of cases):
1. [Most common fix — step 1]
2. [Step 2]
3. [Verify]
---
## If That Didn't Work
### Check 1: [First thing to verify]
[How to check + what to look for]
✅ If [expected result] → This isn't the issue. Move to Check 2.
❌ If [unexpected result] → [Specific fix for this case]
### Check 2: [Second thing to verify]
[How to check]
✅ If OK → Move to Check 3.
❌ If not → [Fix]
### Check 3: [Third thing to verify]
[How to check]
✅ If OK → Move to "Still Not Working?"
❌ If not → [Fix]
---
## Still Not Working?
If none of the above resolved your issue:
1. [What information to gather — e.g., "Screenshot of the error message"]
2. [Where to get help — e.g., "Email support@company.com with the above info"]
3. [Expected response time]
---
## Why This Happens
[2-3 sentences explaining the root cause for curious users. Optional but builds trust.]
## Related Articles
- [[Article]] — [Context]# Getting Started with [Feature/Product]
[1-sentence: What you'll accomplish by the end of this guide]
**Time:** [X minutes] | **Difficulty:** [Beginner/Intermediate]
---
## What You'll Need
- [Prerequisite 1]
- [Prerequisite 2]
---
## Step 1: [First thing to do] (2 min)
[Clear instructions]
[Screenshot: Description]
## Step 2: [Second thing] (3 min)
[Instructions]
## Step 3: [Third thing] (2 min)
[Instructions]
---
## You're All Set! 🎉
[What they can now do]
**Next steps:**
- [Logical next action — link to next article]
- [Power user tip — link to advanced article]
- [Join community — link if applicable]For each generated article, verify:
Save to the current working directory as [article-slug].md.
Save all articles to a help-center/ subdirectory in the current working directory, with an _index.md table of contents.
# Help Center — [Product Name]
Generated: [DATE] | Articles: [N]
## Getting Started
- [[getting-started-guide.md]] — First-time setup walkthrough
- [[quick-start.md]] — 5-minute quick start
## How-To Guides
- [[how-to-setup-email.md]] — Set up email integration
- [[how-to-invite-team.md]] — Invite team members
- ...
## Troubleshooting
- [[fix-emails-not-sending.md]] — Emails not sending
- [[fix-login-issues.md]] — Can't log in
- ...
## Reference
- [[api-rate-limits.md]] — API limits and quotas
- [[billing-plans.md]] — Plan comparison and billing FAQ| Component | Cost |
|---|---|
| All article generation | Free (LLM reasoning) |
| Total | Free |
None. Pure reasoning skill — takes raw input and produces structured articles.
Assemble an expert/educator motion-graphic LISTICLE video ad from a config — a spoken authoritative voiceover carries a numbered listicle while N web-animated hyperframe beats (HTML plus the Web Animations API, one branded design system of alternating tiles, big hero numerals, and glass-pill callouts) are rendered frame-by-frame via Playwright and anchored to the VO's word-level timestamps, periodic color-graded B-roll windows give visual breath, and captions burn ONLY inside those B-roll windows (2-word chunks, ASS Format header carrying a Name field so none drop) with the VO mixed under a low music bed. This is the FREE deterministic assembly stage (Playwright beat render plus ffmpeg concat plus window-masked caption burn plus VO-and-music mix plus final composite) — the VO, the music bed, and the stock B-roll come from create-vo-elevenlabs, create-music-elevenlabs, and media-proxy. Use for the vo-anchored-motion-listicle format.
Assemble a stop-motion hand-swatch-cycle product-demo ad from a config — a sequence of still PLATES (one hand swiping a single-barrel cosmetic across a cream skin-patch, the barrel + swatch changing per plate while the hand, background, crop, and lighting stay locked) is PNG→mp4 loop-encoded at each plate's own stop-motion hold (fast motion frames 150–250ms, per-shade ~380ms, hero beats 1100–1800ms), concat-demuxed with HARD cuts into a silent master, closed on a Playwright HTML-rendered branded end card (serif tagline + sans subtitle + real logo SVG over a hero BG, never AI-rendered text), and muxed with a pre-sourced music track playing under the end card with a fade tail (no VO). This is the FREE deterministic assembly stage (loop-encode + concat-demux + end-card render + music mux); the master-anchor plate, shade plates, and end-card BG come from create-image-gpt-image-fal and the track from create-music-elevenlabs. Use for the stopmotion-hand-swatch-cycle format.
Assemble a split-screen creator ad from a config — a two-zone vertical composite where a supplied AI-creator lip-sync take fills the BOTTOM ~48% while real 16:9 product/demo clips run uncropped in the TOP ~52%, each top clip contain-fit with a darkened blurred cover-scale fill of the same clip (never black bars), a 3px brand-color divider between the zones, the creator slice cover-fit per the per-scene VO timing, scenes hard-concatenated with the body audio being the concatenated creator VO slices, an end card held on the last sharp frame ~3s, then the ASSEMBLED cut transcribed with local Whisper (not the raw VO — concat drops inter-scene silence) and word-level captions burned in the chosen style. This is the FREE deterministic assembly + caption stage (two-zone composite + blurred fill + divider + hard-concat + end card + captions); the VO comes from create-vo-elevenlabs, the anchor from create-image-gpt-image-fal, and the whole-VO lip-sync from a paid VEED Fabric 1.0 take (a no-atom upstream input). Use for the split-screen-creator format.