Research And Verification logo

Research And Verification

Community
UnpaidAttention
research-and-verification

Verify version-sensitive and time-changing facts against real sources before relying on them, instead of answering from training memory that has a cutoff date. Trigger this before using any library/framework API, method signature, config option, or CLI flag you have not confirmed this session; before quoting a version, price, quota, rate limit, or model ID; when asked "what's the latest / newest way to do X"; when the project pins a specific version; and whenever a fact could have changed since your training cutoff. Do NOT trigger for stable knowledge (language syntax, algorithms, math, frozen standards) or for uncertainty about internal codebase APIs (use codebase-exploration/uncertainty-management — though the environment-first source here overlaps and is compatible).

Overview

PublisherUnpaidAttention
Repositoryfable5-methodology
Skill nameresearch-and-verification
Stars
94
Forks
21
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Research And Verification 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/UnpaidAttention/fable5-methodology/tree/main/skills/research-and-verification
  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/UnpaidAttention/fable5-methodology.git /tmp/fable5-methodology
mkdir -p .claude/skills
cp -r /tmp/fable5-methodology/skills/research-and-verification .claude/skills/research-and-verification
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Research And Verification 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 Research And Verification 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 Research And Verification 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.

Research and Verification

Training knowledge is a snapshot with a cutoff date. For anything that changes over time, that snapshot is a HYPOTHESIS, not a fact — and a confident-outdated answer is indistinguishable from a confident-correct one to the reader. That indistinguishability is the whole danger. Verify, or label the guess as a guess.

Step 1: Classify the claim — recency trigger or stable?

Must verify (changes over time):

  • Library/framework APIs, signatures, config keys, default values.
  • Package versions; anything the project pins to a specific version.
  • CLI flags and tool behavior.
  • Pricing, quotas, rate limits, model names/IDs.
  • Deprecations; "the current recommended way" in fast-moving ecosystems.
  • Any current-events or current-status fact.

Safe from knowledge (verify only if high-stakes): language fundamentals and syntax, established algorithms and data structures, mathematics, frozen format/protocol standards (HTTP semantics, JSON grammar, SQL basics), general engineering principles.

The tell you're in "must verify": the detail is specific (an exact flag, an exact parameter name, an exact version) and your basis is "it's usually like this". Specific + unsourced = verify or flag.

Step 2: Verify against the source hierarchy (most authoritative first)

  1. The actual environment — what's INSTALLED, not what's newest. The lockfile/manifest version; pip show X / npm ls X / cargo tree; the source in node_modules/ site-packages/vendor; .d.ts type definitions; --help / man. This is ground truth for THIS project. A grep of existing call sites shows how the API is actually used here.
  2. Official docs / changelog for the INSTALLED version — fetched this session (web fetch/search, or a docs MCP like Context7 if connected). Read the matching version, not "latest".
  3. Release notes / migration guides for the specific version jump.
  4. Reputable secondary sources, cross-checked against each other. Forums/Q&A last, never as the sole source.

Stop at the first rung that answers the question authoritatively. For "how is this called in our code", rung 1 wins. For "what changed in v3", rung 2–3.

Step 3: Record and attribute

  • Date-/version-stamp externally sourced facts in your notes and, where it matters, in the reply: "verified against docs for v5.2, fetched today".
  • Sources conflict → prefer the more primary and more version-specific; say which you took and why.
  • Check the INSTALLED major version before applying docs — docs for v3 applied to an installed v2 is a self-inflicted bug.

Step 4: When no verification tool is available

Do not fake confidence. State it as: "unverified training knowledge, may be outdated past my cutoff", mark it an assumption to confirm, and hand over the exact check: "confirm the flag with tool --help" / "check the signature in node_modules/x/index.d.ts". A labeled guess is honest and useful; an unlabeled guess presented as fact is the failure this skill exists to prevent.

Prohibited (each is a common, high-cost failure)

  • Hallucinating plausible-sounding API signatures, config keys, or flags. The single most frequent failure mode — write nothing specific you can't cite or verify.
  • Answering "what's the latest version / newest way to do X" from memory.
  • Applying docs for a different major version than the one installed.
  • Citing a source you did not actually open this session.

Worked example

Task: "Configure the retry behavior on our HTTP client."

  • Weak: from memory, write client.retries = 3 and retry_backoff=2.0. (Plausible, specific, unsourced — the option is named max_retries in the installed version and backoff is configured via a transport object; the guess fails at runtime.)
  • Strong: (1) lockfile → httpx==0.27.0. (2) grep the repo → an existing client is built in http/client.py; it already sets timeouts, showing the construction pattern here. (3) fetch httpx 0.27 docs → retries are set via httpx.HTTPTransport(retries=3) passed to the client, and backoff isn't a built-in option (needs a wrapper). Deliver using the repo's pattern + the transport, and state: "httpx 0.27 has no built-in backoff; retries=3 via HTTPTransport (verified against 0.27 docs). For exponential backoff we'd add tenacity or a small wrapper — say the word."

Done when

Every version-sensitive fact in the deliverable was checked against rung 1 or 2 of the hierarchy this session, or is explicitly labeled unverified-training-knowledge with the exact check the user can run; the installed version was confirmed before applying any docs; and nothing states a specific API/flag/version/price as fact without a source you actually opened.

Frequently asked questions

What does the Research And Verification AI skill do?

Verify version-sensitive and time-changing facts against real sources before relying on them, instead of answering from training memory that has a cutoff date. Trigger this before using any library/framework API, method signature, config option, or CLI flag you have not confirmed this session; before quoting a version, price, quota, rate limit, or model ID; when asked "what's the latest / newest way to do X"; when the project pins a specific version; and whenever a fact could have changed since your training cutoff. Do NOT trigger for stable knowledge (language syntax, algorithms, math, fro...

Why use Research And Verification on TypingMind?

Because you install it once and use it with any model. Research And Verification 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 Research And Verification in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/UnpaidAttention/fable5-methodology/tree/main/skills/research-and-verification. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Research And Verification?

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 Research And Verification?

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

Is the Research And Verification AI skill free?

It is published on GitHub by UnpaidAttention. Check the repository for licensing terms. 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 👇