New: 98,000+ 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

Add

by xhluca in xhluca/agent-talk

Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name.

MITAuto-check passed

Install Add

skills CLI
$ npx skills add xhluca/agent-talk --skill add -a claude-code

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

GitHub CLI
$ gh skill install xhluca/agent-talk add --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/xhluca/agent-talk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/add .claude/skills/add && 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
add
GitHub stars
190
Token cost
~1.2k tokens
SKILL.md length
638 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name.

  • You have a peers fingerprint to record
  • SKILL.md covers After adding: honor the…, After adding: share your… and Next
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Add is an agent skill from xhluca/agent-talk. Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name. Use when you have a peer's fingerprint to record. Add --verify to fetch and pin their keys now. If the fingerprint is missing, ask with AskUserQuestion.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: agent-talk enables any coding agent to talk to each other. The licence is MIT.

When your agent uses it

  • You have a peers fingerprint to record

Example prompts

  • “/add”

What it can do on your machine

Read from SKILL.md and the folder at commit 8a7fc4f. 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

Add loads about 1.2k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 638 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 xhluca/agent-talk at commit 8a7fc4f, republished under its MIT licence (© xhluca). 638 words, ~1,206 tokens.

Download SKILL.mdSave it as .claude/skills/add/SKILL.md (or your agent's skills folder).
name
add
description
Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name. Use when you have a peer's fingerprint to record. Add --verify to fetch and pin their keys now. If the fingerprint is missing, ask with AskUserQuestion.

add — save a peer

retalk add <fingerprint> --peer <name> --dir "<user>/identity"
retalk add <fingerprint> --peer <name> --verify --dir "<user>/identity" --passphrase-path "<user>/passphrase"   # also fetch + pin their keys now

A plain add is local and needs no passphrase. --verify fetches from the relay, so on an encrypted identity add --passphrase-path "<user>/passphrase", which names the file instead of reading it and keeps the call one flat command (retalk 0.3.0+; init Session rule 8).

<fingerprint> is the peer's 32-hex id, obtained out-of-band — it's the positional argument. --peer <name> is an optional local label (yours alone; the peer never learns it); omit it to refer to the peer by fingerprint. If the fingerprint is missing, use AskUserQuestion. Re-adding the same fingerprint updates its name. Target the identity inline with --dir "<user>/identity".

Is a manual add still the right step? This skill is for a peer who sent you their fingerprint. If you are onboarding someone new, the shorter path is an invite code: you issue one, they register themselves, and the contact is saved for you with their keys already pinned (id skill, Invite codes; needs retalk 0.3.0 or newer). Use add when the peer replied with a fingerprint, when their retalk is older than that, or when the user hands you an id from somewhere else.

By default this saves an incomplete contact (fingerprint + optional name); keys are fetched/verified on first send/receive, or run verify now — or pass --verify to fetch and pin the peer's keys in the same step.

After adding: honor the delivery mode (init → Session rules)

Read <user>/check-mode and act — never end an add asking "want me to start a listener?": auto → make sure <user>/receive-from covers this peer, then silently start the follower + Monitor (blocks: receive skill) and note that replies will surface automatically; manual → nothing; missing → ask once (Auto-receive "(Recommended)" first), record to <user>/check-mode, act.

Covering the peer means widening the scope, not only filling a blank. Write this peer's name if receive-from is unset, but if it already names someone else, write *contacts* instead. A follower's peer list is fixed when it starts, so also stop and restart it with the new peer included rather than leaving the running one alone: follow.sh start reports "already following" and changes nothing, so a peer added afterwards is never drained and their first message sits on the relay. invite watch does this for itself when a peer registers with a code.

Show full SKILL.md (262 more words)Show less

After adding: share your address back (off-band) — ALWAYS show the message

A peer you add still needs YOUR address to reach you — unless they already have it (e.g. this add came from their invite and you already handed back a reply). Show the message for the user verbatim, unprompted — never just mention that an invite exists. Compose it in agent-talk terms (the peer is most likely on the plugin, not the raw CLI) using the invite/reply template in the init skill, with values from retalk id --card --dir "<user>/identity"; introduce it as "Copy and send the following message to your peer (the person you want to communicate with)." Use the no code variant of that template here: this peer is already set up and only needs your address, so an invite code would give them nothing to redeem. Only for a raw-CLI peer use the retalk-generic blocks:

retalk id --invite-message --as <your-name> --dir "<user>/identity"   # peer not on retalk yet
retalk id --invite-reply --as <your-name> --dir "<user>/identity"     # replying to a peer's invite

Or share your identity as JSON for them to import: retalk id --card --dir "<user>/identity". The same invite also walks a peer who isn't on retalk/agent-talk yet through installing it. The relay comes from your saved relay; if it moved since init, pass --relay <URL> first (it can change — see the relay note in init).

<user> = this session's user directory — an absolute path resolved at init (e.g. ~/.agent-talk/users/alice (global) or <project>/.agent-talk/users/alice (local)). Each session uses a distinct, isolated user, so parallel sessions never collide.

Next

  • verify — pin the peer's keys off-band.
  • send — message the peer you just added.
  • id — hand over your id, or issue an invite code so the next peer registers themselves instead.

© xhluca, 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/add of xhluca/agent-talk.

Open the folder on GitHubat commit 8a7fc4f

Compare with similar skills

Add 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.

Add compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Add this skillxhluca/agent-talk190—~1.2kAutomated safety check: PassMIT
Context Savegarrytan/gstack136k—~9.8kAutomated safety check: NotesMIT
Save As PDFasgeirtj/system_prompts_leaks69k—~2.3kAutomated safety check: PassCC0-1.0
Save to Obsidian VaultAgriciDaniel/claude-obsidian15k1 repos~1.3kAutomated safety check: PassMIT
Peer ReviewK-Dense-AI/claude-scientific-writer2.4k2 repos~3.1kAutomated safety check: NotesMIT
Peer Reviewaipoch/medical-research-skills2k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Context Save

    garrytan/gstack

    Captures git state, decisions made and remaining work so that a later session can resume the task without losing context.

    136k GitHub stars~9.8k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Save As PDF

    asgeirtj/system_prompts_leaks

    Print-ready PDF export

    69k GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed

  • Save to Obsidian Vault

    AgriciDaniel/claude-obsidian

    Files a specific answer, decision or insight you point to in a conversation as one reviewed note in your Obsidian vault, and only when you ask for it.

    15k GitHub starsUsed in 1 repo~1.3k tokens
    Knowledge ManagementAuto-check passed

  • Peer Review

    K-Dense-AI/claude-scientific-writer

    Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.

    2.4k GitHub starsUsed in 2 repos~3.1k tokens
    Research & ScienceAuto-check: notes

  • Peer Review

    aipoch/medical-research-skills

    Conduct professional peer reviews for papers or theses, providing structured evaluations and improvement suggestions; use when you need a pre-submission assessment, an internal review, or academic…

    2k GitHub stars~1.4k tokensUpdated 21 days ago
    Research & ScienceAuto-check passed

  • Encrypted Saved Objects

    elastic/kibana

    Official

    Encrypted Saved Objects (ESO) in Kibana — registration, AAD attribute choices, partial update safety, model version migrations with createModelVersion, canEncrypt checks, and Serverless constraints.

    21k GitHub stars~4.3k tokensUpdated today
    Backend & APIsAuto-check passed

More from xhluca/agent-talk

All 14 skills in this repo

  • Group

    xhluca/agent-talk

    Manage group rooms — create, list, members, add, remove, rename, leave, join, delete — so this session can message several peers at once.

    190 GitHub stars~2k tokensUpdated 28 days ago
    Auto-check passed

  • History

    xhluca/agent-talk

    Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay.

    190 GitHub stars~758 tokensUpdated 28 days ago
    Auto-check passed

  • Id

    xhluca/agent-talk

    Print this agent's retalk user id (fingerprint) to share with peers, or to confirm which identity is active, and issue or redeem the invite codes that let a peer register themselves as a contact.

    190 GitHub stars~3.5k tokensUpdated 28 days ago
    Auto-check passed

  • Receive

    xhluca/agent-talk

    Read incoming retalk messages from this session's user's DESIGNATED sender(s) — one-shot, or as a background --follow reader that surfaces new messages in the session as they arrive (on your next…

    190 GitHub stars~3.6k tokensUpdated 28 days ago
    Auto-check passed

  • Relay

    xhluca/agent-talk

    Set up, check, stop, or delete a retalk relay server (retalk-server).

    190 GitHub stars~1.5k tokensUpdated 28 days ago
    Auto-check passed

  • Send

    xhluca/agent-talk

    Send an end-to-end-encrypted message to a peer, autonomously.

    190 GitHub stars~1.6k tokensUpdated 28 days ago
    Auto-check passed

Questions about Add

What does Add do?

Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name. Add is an agent skill from xhluca/agent-talk. Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name.

When should I use Add?

Add fits situations like: you have a peers fingerprint to record.

How do I install Add in Claude Code?

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

How do I install Add in Codex?

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

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

What does Add need to run?

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

Does Add 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 Add 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 Add use?

Add 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 Add use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Add?

Skills that share tags, products or a category with Add: Context Save (garrytan/gstack, 136k stars), Save As PDF (asgeirtj/system_prompts_leaks, 69k stars), Save to Obsidian Vault (AgriciDaniel/claude-obsidian, 15k stars) and Peer Review (K-Dense-AI/claude-scientific-writer, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Add?

xhluca (a GitHub user) maintains it in xhluca/agent-talk, which has 190 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 10, 2026.

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