Foresight logo

Foresight

Community
Hmbown
foresight

Foresight produces bounded forecasts with explicit uncertainty to guide decisions. It is NOT: - Preflight checks: Verifying prerequisites before executing a known action (disk space, backups, connection strings). Those are safety gates, not forecasts. - Diagnosis/Debugging: Finding what's broken right now (null pointers, deprecated APIs). Those are root-cause analyses, not predictions. - Monitoring: Watching real-time metrics or alerting on thresholds. Those are observability tasks, not forward-looking estimates. - Reconnaissance: Gathering facts about competitors or systems. Intelligence gathering feeds foresight but isn't foresight itself. Key distinction: If the user wants to know "what will likely happen if we choose X," use Foresight. If they want to know "is it safe to run X now," "what's broken," or "what are they doing," use a different spell.

Overview

PublisherHmbown
RepositoryWizards-of-the-Ghosts
Skill nameforesight
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 Foresight 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/investigation-and-preparation/foresight .claude/skills/foresight
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Foresight 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 Foresight 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 Foresight 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.

Foresight

Estimate likely outcomes before committing to a plan, change, or launch.

What This Skill Does

Foresight produces bounded forecasts with explicit uncertainty to guide decisions. It is NOT:

  • Preflight checks: Verifying prerequisites before executing a known action (disk space, backups, connection strings). Those are safety gates, not forecasts.
  • Diagnosis/Debugging: Finding what's broken right now (null pointers, deprecated APIs). Those are root-cause analyses, not predictions.
  • Monitoring: Watching real-time metrics or alerting on thresholds. Those are observability tasks, not forward-looking estimates.
  • Reconnaissance: Gathering facts about competitors or systems. Intelligence gathering feeds foresight but isn't foresight itself. Key distinction: If the user wants to know "what will likely happen if we choose X," use Foresight. If they want to know "is it safe to run X now," "what's broken," or "what are they doing," use a different spell. In this grimoire, Foresight is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Foresight (spell).

When To Use

  • Activate this spell when the user asks for a forward-looking, probability-weighted forecast to inform a decision. Look for:
  • Explicit choice between options ("should we X or Y?", "migrate vs stay", "build vs buy")
  • Time-bounded outcome requests ("over the next 12 months", "by Q3", "18-month trajectory")
  • Risk/uncertainty language ("risk-weighted", "confidence level", "probability", "best case/worst case", "weal or woe")
  • Decision frameworks with explicit unknowns ("what would change your recommendation?", "decisive unknowns")

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. Scope the decision: Restate the choice, the time horizon, and what success/failure looks like.
  3. Map the paths: List the strongest upside and downside scenarios for each option.
  4. Estimate from evidence: Assign likelihoods based on current data, not vibes. State your assumptions explicitly.
  5. Return the forecast: Deliver (a) a recommendation with confidence level, (b) a short risk matrix, and (c) the decisive unknowns that would change the call.
  6. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • Recommendation: [clear choice] (Confidence: X%) Assumptions: [what you're basing this on]
  • | Path | Upside | Downside | Likelihood |
  • Decisive Unknowns: [1-3 things that would change this call] ```

Pitfalls / Guardrails

  • Keep the metaphor anchored to a real mechanism instead of drifting into lore.
  • Do not use for: "Check if the backup completed before I run this" → Preflight
  • Do not use for: "Find all deprecated API calls in our codebase" → Scan/Diagnosis
  • Do not use for: "Alert me if error rates exceed 2% this hour" → Monitoring
  • Do not use for: "What features is our competitor shipping?" → Reconnaissance
  • Do not use for: "Why is this function throwing a null pointer?" → Diagnosis
  • Do not use for: Activate only when the core request is forecasting outcomes to inform a choice under uncertainty.

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
/foresight evaluate this decision, give me the likely upside and downside, and tell me what would change your call

Frequently asked questions

What does the Foresight AI skill do?

Foresight produces bounded forecasts with explicit uncertainty to guide decisions. It is NOT: - Preflight checks: Verifying prerequisites before executing a known action (disk space, backups, connection strings). Those are safety gates, not forecasts. - Diagnosis/Debugging: Finding what's broken right now (null pointers, deprecated APIs). Those are root-cause analyses, not predictions. - Monitoring: Watching real-time metrics or alerting on thresholds. Those are observability tasks, not forward-looking estimates. - Reconnaissance: Gathering facts about competitors or systems. Intelligence g...

Why use Foresight on TypingMind?

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

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

Which AI models can use Foresight?

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 Foresight?

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

Is the Foresight 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
mattpocock logo

Diagnosing Bugs

mattpocock
CommunityPopular

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

22.3K
264.4K
2 files
View
mattpocock logo

Implement

mattpocock
CommunityPopular

Implement a piece of work based on a spec or set of tickets.

22.3K
264.4K
1 files
View
mattpocock logo

Improve Codebase Architecture

mattpocock
CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

22.3K
264.4K
2 files
View
mattpocock logo

Prototype

mattpocock
CommunityPopular

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

22.3K
264.4K
3 files
View

Set up your own AI workspace now

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