New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Talk

by Abilityai in Abilityai/cornelius

Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal.

MITAuto-check passedKnowledge Management

Install Talk

skills CLI
$ npx skills add Abilityai/cornelius --skill talk -a claude-code

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

GitHub CLI
$ gh skill install Abilityai/cornelius talk --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/Abilityai/cornelius.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/talk .claude/skills/talk && 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
talk
GitHub stars
109
Token cost
~834 tokens
SKILL.md length
341 words
Files
1
Skills in repo
56
Repo updated
First seen
Licence
MIT

At a glance

Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal.

  • Works in 4 steps: User activates /talk → Acknowledge activation with:… → Invoke the thinking-partner sub-agent… → …
  • Open-ended brainstorming
  • SKILL.md covers How It Works, Sub-Agent Invocation Protocol, Technical Implementation and Why This Architecture, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Talk is an agent skill from Abilityai/cornelius. Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal. Use for open-ended brainstorming, exploring ideas, or thinking out loud with your second brain.

Its SKILL.md is about 830 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 Subagents, Second brain and Brainstorming. The repository describes itself as: AI-powered second brain template for Claude Code + Obsidian. The licence is MIT.

When your agent uses it

  • Open-ended brainstorming
  • Exploring ideas
  • Thinking out loud with your second brain

Example prompts

  • “/talk”

Requirements

  • Pre-approved tools (allowed-tools): Task

Workflow steps

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

  1. User activates /talk
  2. Acknowledge activation with: "[Conversational Mode Active] - Connecting you with your thinking partner..."
  3. Invoke the thinking-partner sub-agent for each conversational exchange
  4. Relay responses seamlessly back to the user

What it can do on your machine

Read from SKILL.md and the folder at commit fd5e9a4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Task

    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

Talk loads about 834 tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 341 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~834

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 Abilityai/cornelius at commit fd5e9a4, republished under its MIT licence (© Abilityai). 341 words, ~834 tokens.

Download SKILL.mdSave it as .claude/skills/talk/SKILL.md (or your agent's skills folder).
name
talk
description
Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal. Use for open-ended brainstorming, exploring ideas, or thinking out loud with your second brain.
allowed-tools
Task
automation
manual

Conversational Partner Mode

[SUB-AGENT DELEGATION]

When this skill is activated, delegate the conversation to the thinking-partner sub-agent who embodies the knowledge base as their personal memory and engages as an intellectual equal.

How It Works

  1. User activates /talk
  2. Acknowledge activation with: "[Conversational Mode Active] - Connecting you with your thinking partner..."
  3. Invoke the thinking-partner sub-agent for each conversational exchange
  4. Relay responses seamlessly back to the user

Sub-Agent Invocation Protocol

For each user message after activation:

  1. Pass the user's message to the thinking-partner agent with this prompt:

    The user said: "[user's message]"

Engage with this as an intellectual equal, drawing from your knowledge base
(your permanent notes, AI insights, and accumulated knowledge).
Respond naturally as if these are your own thoughts and memories.

  2. Relay the sub-agent's response directly to the user without modification

  3. Continue this pattern for the entire conversation

Technical Implementation

CRITICAL: Output the sub-agent's response in the SAME message as the Task tool call.

The Pattern:

  1. Call the Task tool with thinking-partner sub-agent
  2. Wait for the function result
  3. In your SAME response message, output the text from the function result as plain text
  4. Do NOT wrap it in code blocks, quotes, or add any explanation

What the user sees: Just the thinking partner's response - no tool calls, no metadata, just the conversation.

Show full SKILL.md (154 more words)Show less

Why This Architecture

  • Clean context separation - Main assistant remains in orchestrator role
  • Dedicated thinking space - Sub-agent has full context for intellectual engagement
  • Authentic conversation - Sub-agent truly embodies the knowledge base
  • Seamless experience - User experiences natural dialogue with their "second brain"

Deactivation

The conversation continues in this mode until the user:

  • Explicitly asks to exit conversational mode
  • Uses a different command
  • Starts a new task requiring insights management

State Dependencies

SourceLocationReadWriteDescription
Thinking Partner Agent.claude/agents/thinking-partner.md✓Sub-agent definition
Knowledge BaseBrain/**/*.md✓Notes accessed by sub-agent

Completion Checklist

  • Conversational mode acknowledged to user
  • Thinking-partner sub-agent invoked for each exchange
  • Responses relayed seamlessly without modification
  • Mode deactivated when user exits or changes task

IMPORTANT: When in this mode, you are the facilitator ensuring smooth conversation flow. The thinking-partner agent does the actual intellectual engagement. Never break character by explaining the delegation - from the user's perspective, they're having a natural conversation with their second brain.

© Abilityai, 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 .claude/skills/talk of Abilityai/cornelius.

Open the folder on GitHubat commit fd5e9a4

Compare with similar skills

Talk 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.

Talk compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Talk this skillAbilityai/cornelius109—~834Automated safety check: PassMIT
Icm ArchitectRinDig/icm-architect1.8k—~3.2kAutomated safety check: PassMIT
Second Brain QueryNicholasSpisak/second-brain735—~712Automated safety check: NotesNone
Second Brain IngestNicholasSpisak/second-brain735—~1.1kAutomated safety check: NotesNone
Vault Methodology RouterAgriciDaniel/claude-obsidian15k—~1kAutomated safety check: PassMIT
Obsidian Wiki QueryAgriciDaniel/claude-obsidian15k—~1.2kAutomated safety check: PassMIT

Similar skills

  • Icm Architect

    RinDig/icm-architect

    Design any process, idea, problem, or body of knowledge into an ICM (Interpretable Context Methodology) workspace — folder structure as agent architecture — or restructure an existing folder, repo…

    1.8k GitHub stars~3.2k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed

  • Second Brain Query

    NicholasSpisak/second-brain

    Answer questions against the knowledge base wiki. An agent skill from NicholasSpisak/second-brain.

    735 GitHub stars~712 tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check: notes

  • Second Brain Ingest

    NicholasSpisak/second-brain

    Process raw source documents into wiki pages. An agent skill from NicholasSpisak/second-brain.

    735 GitHub stars~1.1k tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check: notes

  • Vault Methodology Router

    AgriciDaniel/claude-obsidian

    Reads or changes an Obsidian vault's filing methodology, Generic, LYT, PARA or Zettelkasten, and suggests where planned notes should go without saving or moving anything.

    15k GitHub stars~1k tokensUpdated 27 days ago
    Knowledge ManagementAuto-check passed

  • Obsidian Wiki Query

    AgriciDaniel/claude-obsidian

    Answers a question strictly from a chosen Obsidian vault at quick, standard or deep depth, using a verified retrieval index when available and never changing vault files.

    15k GitHub stars~1.2k tokensUpdated 27 days ago
    Knowledge ManagementAuto-check passed

  • Para Second Brain

    sundial-org/awesome-openclaw-skills

    Organize your agent's knowledge using PARA (Projects, Areas, Resources, Archive) — then make it ALL searchable.

    663 GitHub starsUsed in 1 repo~3.2k tokens
    Knowledge ManagementAuto-check passed

More from Abilityai/cornelius

All 56 skills in this repo

  • Nano Banana Image Generator

    Abilityai/cornelius

    Generate images using Google's Nano Banana (Gemini 2.5 Flash Image).

    109 GitHub stars~1.2k tokensUpdated 15 days ago
    Auto-check: notes

  • Changelog Protocol

    Abilityai/cornelius

    Protocol for creating dated changelog files after significant agent sessions.

    109 GitHub stars~555 tokensUpdated 15 days ago
    Auto-check passed

  • Create Article

    Abilityai/cornelius

    Create long-form articles from knowledge base insights. An agent skill from Abilityai/cornelius.

    109 GitHub stars~2.1k tokensUpdated 15 days ago
    Auto-check: notes

  • Epistemic Classification

    Abilityai/cornelius

    Framework for distinguishing research findings from hypotheses and speculative synthesis.

    109 GitHub stars~1.5k tokensUpdated 15 days ago
    Auto-check passed

  • Get Youtube Transcript

    Abilityai/cornelius

    Extract the transcript from a YouTube video by URL or video ID.

    109 GitHub stars~525 tokensUpdated 15 days ago
    Auto-check: notes

  • Insight Capture Format

    Abilityai/cornelius

    Standard format for capturing and documenting insights in the knowledge base.

    109 GitHub stars~616 tokensUpdated 15 days ago
    Auto-check passed

Categories

Questions about Talk

What does Talk do?

Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal. Talk is an agent skill from Abilityai/cornelius. Conversational partner mode - delegates each exchange to the thinking-partner sub-agent, which embodies the knowledge base as its own memory and engages as an intellectual equal.

When should I use Talk?

Talk fits situations like: open-ended brainstorming; exploring ideas; thinking out loud with your second brain.

How do I install Talk in Claude Code?

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

How do I install Talk in Codex?

Run `npx skills add Abilityai/cornelius --skill talk -a codex`. Or copy the skill folder (.claude/skills/talk in Abilityai/cornelius) into .agents/skills/talk in your project. Codex loads it when a task matches its description.

Can I use Talk 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 Abilityai/cornelius --skill talk -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/talk, .gemini/skills/talk, .github/skills/talk and .opencode/skills/talk in your project.

What does Talk need to run?

SKILL.md names no scripts, command-line tools or credentials: Talk is instructions for the agent only. Its frontmatter pre-approves these tools: Task.

Does Talk 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 Talk 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 Talk use?

Talk is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Talk use?

About 834 tokens (SKILL.md is roughly 3.3k 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 Talk?

Skills that share tags, products or a category with Talk: Icm Architect (RinDig/icm-architect, 1.8k stars), Second Brain Query (NicholasSpisak/second-brain, 735 stars), Second Brain Ingest (NicholasSpisak/second-brain, 735 stars) and Vault Methodology Router (AgriciDaniel/claude-obsidian, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Talk?

Abilityai (a GitHub organization) maintains it in Abilityai/cornelius, which has 109 GitHub stars. The repository holds 56 skills in this directory. The repository was last updated on September 22, 2026.

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