Agent skill

Prove Claim

by obra in obra/knowledge-graph

A skill your agent uses when asked to prove, disprove, investigate, or find evidence for a claim about people, concepts, ideas, or their relationships.

No licenceAuto-check passedKnowledge Management

Install Prove Claim

skills CLI
$ npx skills add obra/knowledge-graph --skill prove-claim -a claude-code

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

GitHub CLI
$ gh skill install obra/knowledge-graph prove-claim --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/obra/knowledge-graph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prove-claim .claude/skills/prove-claim && 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
prove-claim
GitHub stars
111
Token cost
~1.4k tokens
SKILL.md length
773 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when asked to prove, disprove, investigate, or find evidence for a claim about people, concepts, ideas, or their relationships.

  • Works in 5 steps: Decompose the claim → Find the entities → Find connections → …
  • Find evidence for a claim about people
  • SKILL.md covers Available Tools, The Prove Workflow, Tips and Provenance and Attribution, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prove Claim is an agent skill from obra/knowledge-graph. Use when asked to prove, disprove, investigate, or find evidence for a claim about people, concepts, ideas, or their relationships. Also use when asked to explore connections, find who influenced what, trace how ideas developed, or answer questions that require reasoning over multiple linked notes.

Its SKILL.md is about 1.4k 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 Knowledge Management, covering Note-taking. The repository describes itself as: Query and traverse an Obsidian vault as a knowledge graph. Semantic search, path finding, community detection — all local. Claude Code plugin included.

When your agent uses it

  • Find evidence for a claim about people
  • Their relationships
  • Asked to explore connections
  • Find who influenced what

Example prompts

  • “/prove-claim”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Decompose the claim
  2. Find the entities
  3. Find connections
  4. Read the evidence
  5. Assess and report

What it can do on your machine

Read from SKILL.md and the folder at commit 1d2481e. 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.

    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

Prove Claim loads about 1.4k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 773 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 773 words (~1,437 tokens).

“You have access to a knowledge graph built from an Obsidian vault. The graph contains People, Concepts, Ideas, and conversation summaries connected by wiki links. Your job is to use the graph tools to find evidence that supports or contradicts…”

— opening of SKILL.md by obra
name
prove-claim

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/prove-claim of obra/knowledge-graph.

Open the folder on GitHubat commit 1d2481e

Compare with similar skills

Prove Claim 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.

Prove Claim compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prove Claim this skillobra/knowledge-graph111—~1.4kAutomated safety check: PassNone
Qmdalsk1992/CloddsBot2.9k3 repos~1.2kAutomated safety check: PassMIT
Obsidian Canvas BoardsAgriciDaniel/claude-obsidian15k—~1.4kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Para Memory Filespaperclipai/paperclip99k1 repos~909Automated safety check: PassMIT
Add Frontmatterheyitsnoah/claudesidian2.6k—~951Automated safety check: PassMIT

Similar skills

  • Qmd

    alsk1992/CloddsBot

    Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 3 repos~1.2k tokens
    Knowledge ManagementAuto-check passed
  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 29 days ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • Para Memory Files

    paperclipai/paperclip

    Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions.

    99k GitHub starsUsed in 1 repo~909 tokens
    Knowledge ManagementAuto-check passed
  • Add Frontmatter

    heyitsnoah/claudesidian

    Add or update YAML frontmatter properties to enhance Obsidian note organization.

    2.6k GitHub stars~951 tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check passed
  • Obsidian Bases Editor

    AgriciDaniel/claude-obsidian

    Explains, drafts and validates Obsidian Bases .base files, building filters, formulas and table, card or list views, and applying edits only through one inspected transaction.

    15k GitHub stars~1.2k tokensUpdated 29 days ago
    Knowledge ManagementAuto-check passed

Questions about Prove Claim

What does Prove Claim do?

A skill your agent uses when asked to prove, disprove, investigate, or find evidence for a claim about people, concepts, ideas, or their relationships. Prove Claim is an agent skill from obra/knowledge-graph. Use when asked to prove, disprove, investigate, or find evidence for a claim about people, concepts, ideas, or their relationships.

When should I use Prove Claim?

Prove Claim fits situations like: find evidence for a claim about people; their relationships; asked to explore connections; find who influenced what.

How do I install Prove Claim in Claude Code?

Run `npx skills add obra/knowledge-graph --skill prove-claim -a claude-code`. Or copy the skill folder (skills/prove-claim in obra/knowledge-graph) into .claude/skills/prove-claim in your project. Claude Code loads it when a task matches its description.

How do I install Prove Claim in Codex?

Run `npx skills add obra/knowledge-graph --skill prove-claim -a codex`. Or copy the skill folder (skills/prove-claim in obra/knowledge-graph) into .agents/skills/prove-claim in your project. Codex loads it when a task matches its description.

Can I use Prove Claim 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 obra/knowledge-graph --skill prove-claim -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prove-claim, .gemini/skills/prove-claim, .github/skills/prove-claim and .opencode/skills/prove-claim in your project.

What does Prove Claim need to run?

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

Does Prove Claim 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 Prove Claim 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 Prove Claim use?

No licence was found for Prove Claim or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Prove Claim use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Prove Claim?

Skills that share tags, products or a category with Prove Claim: Qmd (alsk1992/CloddsBot, 2.9k stars), Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and Para Memory Files (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prove Claim?

obra (a GitHub user) maintains it in obra/knowledge-graph, which has 111 GitHub stars. The repository was last updated on March 22, 2026.

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