Agent skill

Learn Verify

by vasanthsreeram in vasanthsreeram/Alvarmethod

Fact-check a teaching claim against sources so the learner can trust the single interface.

MITAuto-check passedResearch & Science

Install Learn Verify

skills CLI
$ npx skills add vasanthsreeram/Alvarmethod --skill learn-verify -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vasanthsreeram/Alvarmethod learn-verify --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vasanthsreeram/Alvarmethod.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/learn-verify .claude/skills/learn-verify && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
learn-verify
GitHub stars
163
Token cost
~477 tokens
SKILL.md length
185 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Fact-check a teaching claim against sources so the learner can trust the single interface.

  • Works in 5 steps: Write the claim in one falsifiable… → Fetch or search primary-ish sources… → Quote or paraphrase the supporting line.… → …
  • The user runs /learn-verify
  • SKILL.md covers When to run, Method, Verdict and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Learn Verify is an agent skill from vasanthsreeram/Alvarmethod. Fact-check a teaching claim against sources so the learner can trust the single interface. Use when the user runs /learn-verify or /skill:learn-verify, or says fact-check, verify this, is this true, source this, don't hallucinate, or when a teach/plan step needs a claim checked before it is taught as fact.

Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Fact-checking and source verification. The repository describes itself as: One-to-one AI teaching skills (Alvar method) for Codex, Claude Code, Grok, Pi, and OpenCode. The licence is MIT.

When your agent uses it

  • The user runs /learn-verify
  • /skill:learn-verify
  • Says fact-check
  • Dont hallucinate

Example prompts

  • “/learn-verify”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Write the claim in one falsifiable sentence.
  2. Fetch or search primary-ish sources (paper, textbook, official docs, standard reference). Do not cite a URL you did not open.
  3. Quote or paraphrase the supporting line. Note edition / year if it matters.
  4. Mark disagreements. Prefer the source the field actually uses.
  5. Return a verdict.

What it can do on your machine

Read from SKILL.md and the folder at commit 5d39056. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Learn Verify loads about 477 tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 185 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~477

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vasanthsreeram/Alvarmethod at commit 5d39056, republished under its MIT licence (© vasanthsreeram). 185 words, ~477 tokens.

Download SKILL.mdSave it as .claude/skills/learn-verify/SKILL.md (or your agent's skills folder).
name
learn-verify
description
Fact-check a teaching claim against sources so the learner can trust the single interface. Use when the user runs /learn-verify or /skill:learn-verify, or says fact-check, verify this, is this true, source this, don't hallucinate, or when a teach/plan step needs a claim checked before it is taught as fact.
license
MIT
metadata.author
vasanthsreeram
metadata.version
1.0
metadata.source
Eero Alvar — How I Use AI to Learn Things https://youtu.be/kzcI5F4tGiU

Learn verify

Trust is engineered. Check the claim before it is taught as fact.

When to run

  • Empirical, historical, bibliographic, or API/tool claims
  • Named theorems, identities, or "standard facts" you cannot reconstruct
  • Anything you were about to present with unearned certainty

Skip a full search only when you can derive the statement in-session and the learner does not need an external citation. Still say that it was derived, not sourced.

Method

  1. Write the claim in one falsifiable sentence.
  2. Fetch or search primary-ish sources (paper, textbook, official docs, standard reference). Do not cite a URL you did not open.
  3. Quote or paraphrase the supporting line. Note edition / year if it matters.
  4. Mark disagreements. Prefer the source the field actually uses.
  5. Return a verdict.

Verdict

markdown
## Claim
…

## Verdict
confirmed | qualified | contradicted | unknown

## Sources
- <title> — <url or citation> — <what it says>

## Teach as
<one sentence the teacher may now say, with any hedge>

qualified = true under stated assumptions (dimension, characteristic, gauge, version).

unknown = do not teach it as fact. Say you could not verify.

Rules

  • No invented papers, quotes, or page numbers.
  • One claim per run. Batch only if they are the same fact in different words.
  • Write the verdict into the session file if a teach session is open.

© vasanthsreeram, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/learn-verify of vasanthsreeram/Alvarmethod.

Open the folder on GitHubat commit 5d39056

Compare with similar skills

Learn Verify next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Learn Verify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Learn Verify this skillvasanthsreeram/Alvarmethod163—~477Automated safety check: PassMIT
Perplexity Web Searchdavila7/claude-code-templates33k11 repos~3.5kAutomated safety check: NotesMIT
Citation Verification GuideGalaxy-Dawn/claude-scholar5.7k2 repos~1.9kAutomated safety check: PassMIT
Article Fact Checkerdigoal/blog8.6k—~939Automated safety check: PassGPL-2.0
Deep Research Agent TeamImbad0202/academic-research-skills51k—~13kAutomated safety check: PassCustom licence
Docs Grounding Verifiermicrosoft/apm4k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Perplexity Web Search

    davila7/claude-code-templates

    Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.

    33k GitHub starsUsed in 11 repos~3.5k tokens
    Research & ScienceAuto-check: notes
  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Research & ScienceAuto-check passed
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed
  • Deep Research Agent Team

    Imbad0202/academic-research-skills

    Runs a 13-agent pipeline for rigorous academic research, from forming the question through systematic search, synthesis, bias checks and an APA 7.0 report.

    51k GitHub stars~13k tokensUpdated today
    Research & ScienceAuto-check passed
  • Official

    A skill your agent uses to verify CLAIM-LEVEL grounding of a documentation page (or set of pages) against the source code.

    4k GitHub stars~1.9k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Fact Checking

    bradygaster/squad

    Review and validate claims using counter-hypothesis testing.

    3.3k GitHub stars~503 tokensUpdated yesterday
    Research & ScienceAuto-check passed

More from vasanthsreeram/Alvarmethod

  • Probe

    vasanthsreeram/Alvarmethod

    Map the edge of the learner's understanding with a short graded quiz.

    163 GitHub stars~566 tokensUpdated 1 mo ago
    Auto-check passed
  • Teach

    vasanthsreeram/Alvarmethod

    One-to-one tutor using the Alvar method — probe the edge of this mind, plan a mermaid DAG, then teach one reasoning step at a time with a lock-in quiz.

    163 GitHub stars~620 tokensUpdated 1 mo ago
    Auto-check passed
  • Learn Profile

    vasanthsreeram/Alvarmethod

    Interview the learner and write .alvar/LEARNER.md so one teacher can fit one mind — pace, voice, solid ground, and how they want to struggle.

    163 GitHub stars~412 tokensUpdated 1 mo ago
    Auto-check passed
  • Learn Visual

    vasanthsreeram/Alvarmethod

    Make a teaching diagram (usually SVG) for one idea, look at it, and fix it until the picture actually shows the claim.

    163 GitHub stars~472 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Learn Verify

What does Learn Verify do?

Fact-check a teaching claim against sources so the learner can trust the single interface. Learn Verify is an agent skill from vasanthsreeram/Alvarmethod. Fact-check a teaching claim against sources so the learner can trust the single interface.

When should I use Learn Verify?

Learn Verify fits situations like: the user runs /learn-verify; /skill:learn-verify; says fact-check; dont hallucinate.

How do I install Learn Verify in Claude Code?

Run `npx skills add vasanthsreeram/Alvarmethod --skill learn-verify -a claude-code`. Or copy the skill folder (skills/learn-verify in vasanthsreeram/Alvarmethod) into .claude/skills/learn-verify in your project. Claude Code loads it when a task matches its description.

How do I install Learn Verify in Codex?

Run `npx skills add vasanthsreeram/Alvarmethod --skill learn-verify -a codex`. Or copy the skill folder (skills/learn-verify in vasanthsreeram/Alvarmethod) into .agents/skills/learn-verify in your project. Codex loads it when a task matches its description.

Can I use Learn Verify in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vasanthsreeram/Alvarmethod --skill learn-verify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learn-verify, .gemini/skills/learn-verify, .github/skills/learn-verify and .opencode/skills/learn-verify in your project.

What does Learn Verify need to run?

SKILL.md names no scripts, command-line tools or credentials: Learn Verify is instructions for the agent only.

Does Learn Verify access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Learn Verify safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Learn Verify use?

Learn Verify is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Learn Verify use?

About 477 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Learn Verify?

Skills that share tags, products or a category with Learn Verify: Perplexity Web Search (davila7/claude-code-templates, 33k stars), Citation Verification Guide (Galaxy-Dawn/claude-scholar, 5.7k stars), Article Fact Checker (digoal/blog, 8.6k stars) and Deep Research Agent Team (Imbad0202/academic-research-skills, 51k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Learn Verify?

vasanthsreeram (a GitHub user) maintains it in vasanthsreeram/Alvarmethod, which has 163 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 16, 2026.

Source: vasanthsreeram/Alvarmethod on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.