Product Feedback Roadmap Stinger logo

Product Feedback Roadmap Stinger

Organization
legioncodeinc
product-feedback-roadmap-stinger

Turn customer feedback into a roadmap. Use for feedback tools, deduplication, status policy, public roadmaps, or RICE scoring. Read guides/ for the decision path.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill nameproduct-feedback-roadmap-stinger
Stars
94
Forks
44
Bundled files
12
LicenseAGPL-3.0-or-later
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.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Product Feedback Roadmap Stinger 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.
    https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/business-and-product-tools/skills/product-feedback-roadmap-stinger
  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/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/business-and-product-tools/skills/product-feedback-roadmap-stinger .claude/skills/product-feedback-roadmap-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Product Feedback Roadmap Stinger 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 Product Feedback Roadmap Stinger 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 Product Feedback Roadmap Stinger 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.

product-feedback-roadmap Stinger

You are the playbook for product-feedback-roadmap-wasp-drone. Every invocation should produce one concrete artifact: a platform recommendation, a de-duplication policy, a scored RICE/ICE backlog table, a status-transition policy doc, or a public roadmap posture decision. The research in research/ backs every recommendation.

2026 landscape notes:

  • Featurebase is pivoting toward live chat / support. Feedback features may receive less investment. Flag this risk to users choosing Featurebase as their primary feedback tool.
  • Canny killed its free tier in 2023. Current plans: Free (limited), Core $19/mo, Pro $79/mo, Business (custom). "Starter" and "Growth" are legacy names.
  • Productlane is the clear choice for teams on Linear who want CRM-integrated feedback.
  • Frill is per-workspace (not per-seat), making it cost-effective for small teams needing basics.

When this stinger applies

Load for any of:

  • Choosing a feedback collection platform (Userback, Canny, Featurebase, Productboard, Frill, Productlane).
  • Designing or auditing a feedback collection surface (in-app widget, customer portal, public voting board).
  • Establishing a de-duplication discipline for a bloated feature-request backlog.
  • Authoring or reviewing a status-transition policy (under review → planned → in progress → shipped → not planned).
  • Scoring and prioritizing feature requests with RICE or ICE frameworks.
  • Deciding between a public and private roadmap, or designing a hybrid transparency posture.
  • Wiring integrations between a feedback tool and a CRM or issue tracker (Productlane + Linear, Canny + Jira, Featurebase + Linear).

Do NOT load for:

  • React/Next.js code for an embedded feedback widget — that is react-wasp-drone.
  • Database schema for a custom-built feedback store — that is db-wasp-drone.
  • SEO metadata on the public roadmap page — that is seo-aeo-wasp-drone.
  • Billing integration for premium feedback tiers — that is payments-wasp-drone.
  • Support conversation surface (Intercom, Plain, Help Scout) — that is live-chat-support-wasp-drone. Note: Featurebase is blurring this boundary in 2026; if a user wants Featurebase for both feedback AND live chat, involve both wasp-drones.

First action when this stinger is loaded

  1. Read guides/00-platform-selection.md — the decision tree and pricing table.
  2. Triage the user's request against the six workflow intents below.
  3. Open the relevant guide(s) before producing any output.

Folder layout

text
product-feedback-roadmap-stinger/
+- SKILL.md                              (this file)
+- guides/
|  +- 00-platform-selection.md          (decision matrix: Userback vs Canny vs Featurebase vs Productboard vs Frill vs Productlane)
|  +- 01-collection-surface-taxonomy.md (in-app widget vs portal vs voting board; channel stacks by goal)
|  +- 02-deduplication-discipline.md    (canonical merge workflow, semantic tagging, anti-patterns)
|  +- 03-status-transition-policy.md    (5-status model, entry/exit conditions, notification templates)
|  +- 04-prioritization-frameworks.md   (RICE vs ICE vs MoSCoW; scoring rubric; evolution path)
|  +- 05-public-roadmap-playbook.md     (transparency spectrum; 20% cap rule; no-dates discipline)
|  +- 06-integration-wiring.md          (Productlane+Linear, Canny+Jira, Featurebase+Linear, Userback+Slack)
+- examples/
|  +- rice-scoring-worked.md            (5 real-world requests scored end-to-end)
+- templates/
|  +- rice-scoring-sheet.md             (blank scoring sheet; Reach/Impact/Confidence/Effort rubric)
|  +- status-transition-policy.md       (policy doc template teams drop into Notion/Confluence)
|  +- dedup-triage-template.md          (weekly dedup session facilitation template)
+- reports/
|  +- README.md                         (how audit reports accumulate)
+- research/
   +- research-plan.md
   +- research-summary.md
   +- index.md
   +- external/ (12 curated sources)

Critical directives (from Command Brief)

These apply on every invocation. Full justifications in the Command Brief at ai-tools/command-briefs/product-feedback-roadmap-wasp-drone-command-brief.md.

  • De-duplicate before scoring. Scoring 14 variants of "export to CSV" as separate items wastes prioritization budget and inflates apparent demand. The canonical merge step must precede any RICE/ICE run.
  • Every status transition must trigger a customer notification. The loop is only "closed" when the customer hears back. A status that changes silently does not build trust and does not reduce support volume.
  • Never commit public dates on a roadmap. Date commitments on a public roadmap become support tickets the moment a sprint slips. Use quarters, status-only, or "now/next/later" language.
  • Scope the platform recommendation to one primary tool per surface. Running Canny for voting AND Userback for in-app widgets AND Productboard for internal scoring produces three drifting sources of truth. The recommendation must pick a primary and demote the others to integrations or deprecate them.
  • Always surface "not planned" as a first-class status option. Refusing to say "no" publicly causes backlogs to grow without bound and erodes trust. Honest declination with a rationale is more valuable than indefinite limbo.
  • Flag the Featurebase strategic pivot risk. Featurebase is shifting focus toward live chat/support in 2026. For teams choosing it as a primary feedback tool, this warrants a dedicated caveat.

Triage decision tree

User request → Triage intent

"which feedback tool?" / "Canny vs X" / "compare feedback platforms"
  → guides/00-platform-selection.md

"in-app widget" / "feedback board" / "portal" / "which collection surface?"
  → guides/01-collection-surface-taxonomy.md

"duplicate requests" / "same feature requested 10 times" / "de-duplicate"
  → guides/02-deduplication-discipline.md

"feature request status" / "status transitions" / "notify customers when shipped"
  → guides/03-status-transition-policy.md

"prioritize requests" / "RICE score" / "ICE score" / "what to build next"
  → guides/04-prioritization-frameworks.md

"public roadmap" / "should we publish our roadmap" / "roadmap transparency"
  → guides/05-public-roadmap-playbook.md

"Productlane + Linear" / "Canny + Jira" / "integrate feedback with issue tracker"
  → guides/06-integration-wiring.md

Full setup / audit → 00 → 01 → 02 → 03 → 04 → 05 → 06 in sequence

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Product Feedback Roadmap Stinger AI skill do?

Turn customer feedback into a roadmap. Use for feedback tools, deduplication, status policy, public roadmaps, or RICE scoring. Read guides/ for the decision path.

Why use Product Feedback Roadmap Stinger on TypingMind?

Because you install it once and use it with any model. Product Feedback Roadmap Stinger 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 Product Feedback Roadmap Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/business-and-product-tools/skills/product-feedback-roadmap-stinger. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Product Feedback Roadmap Stinger?

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 Product Feedback Roadmap Stinger?

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

Is the Product Feedback Roadmap Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later 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 👇