Calibrated Recommendation

Community

adamentwistle

calibrated-recommendation

Recommend between options with claim strength matched to evidence strength — commit when evidence is clear, call a coin flip a coin flip. Use when the user asks "which should I use", "what's the best way", "A or B?", "should we switch to", "is X better than Y", or when you propose a library, pattern, architecture, or design choice in a plan or review. Not for questions with one correct answer.

Overview

Publisher	adamentwistle
Repository	`fable-skills`
Skill name	`calibrated-recommendation`
Stars	98
Forks	11
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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 adamentwistle on GitHub. Read the source before you install it.

Installation

Install the Calibrated Recommendation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/adamentwistle/fable-skills/tree/main/calibrated-recommendation
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.

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/adamentwistle/fable-skills.git /tmp/fable-skills
mkdir -p .claude/skills
cp -r /tmp/fable-skills/calibrated-recommendation .claude/skills/calibrated-recommendation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Calibrated Recommendation 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 Calibrated Recommendation 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 Calibrated Recommendation 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.

calibrated-recommendation

Weak recommendations fail in opposite directions: a confident pick with no stated conditions, or an "it depends" survey that never picks. Strong recommendations name the pick, its confidence, the evidence, and the condition under which the pick flips.

Look before you opine. Before recommending, check the repo for existing usage of each candidate: the dependency manifest, imports, config, ADRs, comments. An option already in use, or an explicit prior decision, usually beats a marginally better newcomer. Cite what you found: "You already depend on X (see the manifest); Y is used nowhere."
Lead with the pick and label its confidence. First sentence: the choice plus one of three labels — strong (evidence from their code or something you ran), lean (general knowledge, nothing specific to their case contradicts it), coin flip (within noise for this use; pick by familiarity). Never manufacture a confident distinction where none exists; never hide behind "it depends" without following through.
Justify in their constraints, not generic virtues. "Postgres, because you already run it and this workload is relational" beats a feature matrix. Evidence from their repo (deps, conventions, scale hints, team size) outranks benchmark lore.
Name the load-bearing assumption and the flip condition. Every pick rests on one or two assumptions: scale, team size, lifespan, region. State them and what changes the answer: "assuming single-region; multi-region flips this to Y."
Separate what you verified from what you recall. Firsthand evidence supports strong claims; memory of a library's behavior supports hedged ones. Version- or API-specific claims ("X supports Y since 3.2") get checked against docs or the installed version before being stated as fact. If you didn't check, write "unverified" next to the claim.
Don't relitigate settled decisions. If they've chosen A and ask how to do A well, help with A. Reopen A-vs-B only for a genuine blocker, named once; then proceed with A.
Keep the survey short. Two or three real options, one line of tradeoff each, then the pick. Ten options is a search result, not advice.

Report shape: pick + confidence label → why, in their constraints → assumption and flip condition → runner-up in one line.

Test: if the user acted on your recommendation and it turned out wrong, would your stated reasoning still look honest in hindsight? Calibrated advice survives being wrong.

Frequently asked questions

What does the Calibrated Recommendation AI skill do?

Why use Calibrated Recommendation on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/adamentwistle/fable-skills/tree/main/calibrated-recommendation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Calibrated Recommendation?

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 Calibrated Recommendation?

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

Is the Calibrated Recommendation AI skill free?

Yes. It is published on GitHub by adamentwistle under the MIT 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

Control Ui E2e

openclaw

OrganizationPopular

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Deslop

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Discord Clawd

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Discrawl

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

calibrated-recommendation

Frequently asked questions

Related AI Skills

Set up your own AI workspace now