Suggestion logo

Suggestion

Community
Hmbown
suggestion

Suggestion is about the craft of the single nudge — not campaigns, not arguments, not automation. It produces one carefully placed prompt at the moment a user is most receptive. The planted idea must be reasonable and defensible. If the user would feel manipulated upon learning how it was designed, the spell refuses.

Overview

PublisherHmbown
RepositoryWizards-of-the-Ghosts
Skill namesuggestion
Stars
106
Forks
10
Bundled files
Instructions only
LicenseCC0-1.0
Links
Skill sourceRepository
  • 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 Hmbown on GitHub. Read the source before you install it.

Installation

Install the Suggestion 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/Hmbown/Wizards-of-the-Ghosts.git /tmp/Wizards-of-the-Ghosts
mkdir -p .claude/skills
cp -r /tmp/Wizards-of-the-Ghosts/generated/hermes/influence-and-behavior/suggestion .claude/skills/suggestion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Suggestion 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 Suggestion 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 Suggestion 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.

Suggestion

Plant one well-crafted idea that a person will want to act on.

What This Skill Does

Suggestion is about the craft of the single nudge — not campaigns, not arguments, not automation. It produces one carefully placed prompt at the moment a user is most receptive. The planted idea must be reasonable and defensible. If the user would feel manipulated upon learning how it was designed, the spell refuses. In this grimoire, Suggestion is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Suggestion (spell).

When To Use

  • Trigger this spell when the request asks for a single, well-placed piece of copy that nudges a specific user action. Look for:
  • Words: nudge, CTA, microcopy, tooltip text, notification copy, prompt text, onboarding message, gentle encouragement
  • Patterns: "write copy that gets users to X", "how do we encourage users to...", "tooltip/prompt for [feature]", "improve conversion on [specific step]"
  • Scope: ONE action, ONE moment in a flow, ONE piece of text

Prerequisites

  • No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Identify the single action and verify it is genuinely neutral or beneficial to the user. If not, flag and refuse.
  3. Pinpoint the moment of maximum receptivity — where in the flow does this prompt naturally belong?
  4. Draft in the user's voice, not the company's. One sentence or short phrase. No walls of text.
  5. Run the disclosure test: would the user feel okay learning this was deliberately designed to steer them? If no, revise or refuse.
  6. Return: the copy + placement/timing guidance + a one-line manipulation audit explaining why this nudge is legitimate (or why it isn't).
  7. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • The nudge copy (CTA, tooltip, notification, or prompt text)
  • Where and when to show it
  • Manipulation audit: one sentence on why this passes the sniff test, or a refusal flag

Pitfalls / Guardrails

  • Keep the metaphor anchored to a real mechanism instead of drifting into lore.
  • Do not use for: Forced automation: "auto-click this button", "make users do X" → not suggestion, this is coercion
  • Do not use for: Mass urgency campaigns: countdown timers, "act now or lose access", scarcity tactics → dark patterns, not nudges
  • Do not use for: Persuasive essays/arguments: whitepapers, debate talking points, competitor comparisons → reasoning spells, not microcopy
  • Do not use for: Full marketing strategy: personas, channels, 90-day calendars → campaign planning, not a single nudge
  • Do not use for: Deceptive UI: hiding options, gray-on-gray text, opt-out traps → dark patterns, refuse outright

Verification

  • Check that the result includes every deliverable promised above.
  • Check that confirmed facts, assumptions, and inferences are visibly separated.
  • Check that the metaphor still maps cleanly to a real operational mechanism.

Example Invocation

text
/suggestion draft a single nudge, CTA, or notification that drives this action while passing the 'would they be angry if they knew?' test

Frequently asked questions

What does the Suggestion AI skill do?

Suggestion is about the craft of the single nudge — not campaigns, not arguments, not automation. It produces one carefully placed prompt at the moment a user is most receptive. The planted idea must be reasonable and defensible. If the user would feel manipulated upon learning how it was designed, the spell refuses.

Why use Suggestion on TypingMind?

Because you install it once and use it with any model. Suggestion 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 Suggestion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/hermes/influence-and-behavior/suggestion. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Suggestion?

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 Suggestion?

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

Is the Suggestion AI skill free?

Yes. It is published on GitHub by Hmbown under the CC0-1.0 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.

Related AI Skills

View all
obra logo

Executing Plans

obra
CommunityPopular

Use when you have a written implementation plan to execute in a separate session with review checkpoints

25.8K
288.1K
Instructions
View
obra logo

Using Superpowers

obra
CommunityPopular

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

25.8K
288.1K
5 files
View
mattpocock logo

Loop Me

mattpocock
CommunityPopular

Grill me about specs for the workflows I want to build, within this workspace.

22.3K
264.4K
1 files
View
mattpocock logo

Scaffold Exercises

mattpocock
CommunityPopular

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course…

22.3K
264.4K
1 files
View

Set up your own AI workspace now

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