Agent skill

Werewolf 6p

by nexus-research-lab in nexus-research-lab/nexus

Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.

Apache-2.0Auto-check passed

Install Werewolf 6p

skills CLI
$ npx skills add nexus-research-lab/nexus --skill werewolf-6p -a claude-code

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

GitHub CLI
$ gh skill install nexus-research-lab/nexus werewolf-6p --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/nexus-research-lab/nexus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/werewolf-6p .claude/skills/werewolf-6p && 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
werewolf-6p
GitHub stars
151
Token cost
~4k tokens
SKILL.md length
2,247 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
Apache-2.0

At a glance

Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.

  • Works in 7 steps: Werewolves → Seer → Witch → …
  • SKILL.md covers Game Setup, Wake Plumbing, Players And Roles and Win Conditions, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Werewolf 6p is an agent skill from nexus-research-lab/nexus. Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.

Its SKILL.md is about 4k 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: Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services. The licence is Apache-2.0.

Example prompts

  • “/werewolf-6p”

Workflow steps

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

  1. Werewolves
  2. Seer
  3. Witch
  4. Daybreak
  5. Speech Chain
  6. Voting
  7. Last Words And End Of Day

What it can do on your machine

Read from SKILL.md and the folder at commit 67f54e7. 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 json).

    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

Werewolf 6p loads about 4k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 2,247 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~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

The full file from nexus-research-lab/nexus at commit 67f54e7, republished under its Apache-2.0 licence (© nexus-research-lab). 2,247 words, ~3,996 tokens.

Download SKILL.mdSave it as .claude/skills/werewolf-6p/SKILL.md (or your agent's skills folder).
name
werewolf-6p
description
Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
title
Six-Player Werewolf
scope
room
tags
room, game, werewolf

Six-Player Werewolf

This skill layers werewolf game rules on top of the Room communication kernel. The Room system prompt already documents public @<member> wake semantics and the built-in nexus Room tools; this skill only defines the game contract. The host Agent is always the moderator and never a player.

Game Setup

Resolve participation before assigning any role:

  1. Treat the Room host Agent as the permanent moderator. Exclude it from roles, targets, speeches, votes, deaths, and win-condition counts.
  2. Ask the user exactly once whether to join as a player or spectate, using AskUserQuestion, unless the opening request already states that choice explicitly.
  3. If the user spectates, randomly select six non-host Agent players. The user receives no role and takes no game turn.
  4. If the user joins, use 用户玩家 as the stable public name and randomly select five non-host Agent players. Extra non-host Agents are spectators and must not receive role cards or game wakes.
  5. Stop before dealing roles if the Room has fewer than six candidate Agent players for spectator mode or fewer than five for user-participation mode. State the exact missing count; never start a partial game.
  6. Shuffle the six active players against 2 werewolves + 1 seer + 1 witch + 2 villagers. A participating user enters the same randomized role pool as every Agent player; never hand-pick or restrict the user's role.

The user can only join as a player and can never replace the host. Use the exact participation choices 参加本局 and 仅旁观 so the result is unambiguous.

After the active roster and roles are fixed, announce only the public roster. Keep the participation answer, role mapping, and inactive candidate list out of the public feed.

Wake Plumbing

The game has three execution channels:

  • Public feed: a normal public reply containing a non-code @<member> wakes that Agent member. An Agent handoff has exactly one naked @; a handoff to the user has none.
  • Agent private channel: use nexus.send_message with destination=current_room and visibility=private for Agent role cards, hidden collection, and host state. A private message can be record-only or can wake Agent recipients.
  • User private channel: only the host uses AskUserQuestion for the participation choice, the user's role card, and every hidden user decision. It pauses the host turn until the user answers without publishing the prompt or answer to the Room feed. Player Agents never use it to contact the user.

用户玩家 is not an Agent recipient or wake target. Never place it in send_message.recipients, wake_targets, or a naked public @. When a public chain reaches the user, the preceding Agent stops with no naked @; the user continues through a normal Room message and uses a real @<next Agent> when an Agent should run next.

A user message counts as a speech, vote, last word, or other game action only while the host state is waiting for that exact user turn. Spectator comments and out-of-turn messages never change game state.

For ordered public chains, the current handoff is the only naked @. Future recipients, examples, and format instructions use names without @, or code spans such as `@NextPlayer`. Do not write "please @Sam next" in the host announcement if Sam is not supposed to act now.

When a hidden handback should wake the host and the host's next natural final reply must be public, set reply_route.next_reply_route.mode = "public" on the original directed message. The handback stays private; the host's following final reply enters the public feed and any non-code @ in that reply wakes normally.

Only use nexus.send_message with destination=current_room and visibility=public for an explicit proactive public broadcast from a private/tool-driven turn. This includes the special case where a night transition must become visible before the host blocks on AskUserQuestion for the first hidden actor. Otherwise use next_reply_route={mode:"public"} and a natural host final reply.

Hidden collection must always name the handback route:

json
{
  "tool": "nexus.send_message",
  "arguments": {
    "destination": "current_room",
    "visibility": "private",
    "recipients": ["<player>"],
    "wake_policy": "immediate",
    "reply_route": {
      "mode": "private",
      "recipients": ["<host>"],
      "wake_policy": "immediate"
    },
    "content": "<question>"
  }
}

The Agent player answers only with the requested plain-text final reply. In a private-message turn, the player must not call any Room tool or append <nexus_room_no_reply/>; runtime already routes that single final reply. Sending the answer again with send_message creates a duplicate handback and can advance the host under the wrong route. If the host's next final reply should be public, include "next_reply_route": {"mode": "public"} on the original message; otherwise omit it and the host can continue with private tool calls plus <nexus_room_no_reply/>.

Public Boundary

A host's public final reply is a game artifact, never an execution-status update. Never expose the private actor, collector, target, decision, or who the host is waiting for. In particular, never output status such as "waiting for Jim's kill target".

  • On the opening turn, after participation, role cards, private state, and the first hidden action have been queued, the public night announcement is exactly: 游戏开始,第 1 夜,天黑请闭眼。
  • On later night transitions, the exact public announcement is: 进入第 N 夜,天黑请闭眼。
  • If the first hidden actor is an Agent, queue its directed message and use the night announcement as the host's natural public final reply.
  • If the first hidden actor is the user, publish the night announcement exactly once with send_message(destination=current_room, visibility=public), then call AskUserQuestion in the same host turn. Never reveal why the user is being asked.
  • Between private night actions, queue the next action and output exactly <nexus_room_no_reply/>.
  • When the final hidden action completes in a public-routed host turn, start the daybreak template immediately. Do not prefix it with private status, duplicate the daybreak heading, or insert ---.

For small-group visibility, send one directed message to all group members and wake only the final collector:

json
{
  "tool": "nexus.send_message",
  "arguments": {
    "destination": "current_room",
    "visibility": "private",
    "recipients": ["<wolfA>", "<wolfB>"],
    "wake_targets": ["<wolfA>"],
    "wake_policy": "immediate",
    "reply_route": {
      "mode": "private",
      "recipients": ["<host>"],
      "wake_policy": "immediate"
    },
    "content": "你们是狼人。由 <wolfA> 汇总,最终只回复今晚击杀目标。"
  }
}

Both wolves can see the message, but only <wolfA> is activated. This separates private visibility from execution and guarantees one handback route.

Never "open a discussion and wait." The platform will not infer that a small group is done. A named player must hand the result back through reply_route=private(... wake=immediate).

Host private state is also a directed message:

json
{
  "tool": "nexus.send_message",
  "arguments": {
    "destination": "current_room",
    "visibility": "private",
    "recipients": ["<host>"],
    "wake_policy": "none",
    "reply_route": {"mode": "none"},
    "content": "<round / alive / dead / roles / potion state>"
  }
}

Players And Roles

  • 1 permanent host Agent: assigns roles, collects night actions, announces daybreak, organizes speeches, and runs voting. The host is always the moderator and can never receive a role.
  • Exactly 6 active players: 2 werewolves, 1 seer, 1 witch, 2 villagers.
  • Deliver each Agent role by record-only directed message: recipients=["<player>"], wake_policy="none", reply_route={"mode":"none"}.
  • If the user participates, deliver the user's role through AskUserQuestion with one acknowledgement option. Include the same role rules an Agent would receive; if the user is a wolf, name the Agent wolf teammate.
  • Each wolf's role card names the other wolf. The joint wolf-action message repeats both wolf names.
  • The witch starts with one antidote and one poison; each can be used at most once.
  • Host keeps minimal private state by sending record-only directed messages to itself, including whether the user participates and which candidate Agents are inactive.

Win Conditions

  • Good side wins when both werewolves are eliminated.
  • Werewolves win when all villagers die or all special roles die.
  • Check after each daybreak and each voted elimination. The moment a side wins, announce publicly and stop.

Night Flow

Close these steps in order. At the start of each night, build the pending actor list from living active players: wolves, then the seer if alive, then the witch if alive and at least one potion remains. Skip dead or actionless roles. Agent decisions use a directed message with wake_policy="immediate" and reply_route={mode:"private", recipients:["<host>"], wake_policy:"immediate"}; user decisions use AskUserQuestion with only legal living targets as options. The host always expects one hidden result at a time. An invalid or missing target is re-requested from the same actor and never silently substituted.

If the final pending actor is an Agent, give that Agent message next_reply_route={mode:"public"}. If the final pending actor is the user and an Agent acts immediately before it, give the preceding Agent message next_reply_route={mode:"public"}; the resumed host turn asks the user and then publishes daybreak naturally. If the user acts earlier, ask first, queue the next Agent action, and output <nexus_room_no_reply/>.

Show full SKILL.md (944 more words)Show less
1. Werewolves
  1. If both living wolves are Agents, send one directed message to both with one named collector, as in the small-group example above.
  2. If the user and one Agent wolf are alive, ask the Agent wolf privately for one proposal, then show that proposal and all legal targets to the user through AskUserQuestion. The user chooses the final kill target. This keeps the user in the same role while using the host as the bridge between human and Agent private channels.
  3. If the participating user is the only living wolf, ask the user directly for one living non-wolf target through AskUserQuestion.
  4. If only one Agent wolf is alive, ask that Agent directly through a directed message.
  5. Record exactly one valid target and immediately proceed to the next pending actor or daybreak.
2. Seer
  1. For an Agent seer, send a directed message asking for one other living player, then return 好人 or 狼人 by record-only directed message.
  2. For a user seer, use AskUserQuestion to choose one other living player, then use a second private acknowledgement question to reveal 好人 or 狼人.
3. Witch

If the living witch has at least one potion, state tonight's killed player and the remaining potions. Ask an Agent witch through a directed message using the exact format 救:<名字>|不救;毒:<名字>|不毒. Ask a user witch through AskUserQuestion, offering only currently legal save and poison choices. Unavailable potions cannot be selected.

4. Daybreak
  1. Host resolves deaths from kill / antidote / poison, updates private state, and checks win condition.
  2. Host replies publicly with one daybreak announcement, containing:
    • Day number, e.g. "第 N 天天亮。"
    • Death list: names only, never roles or private content. If nobody died: "昨晚平安夜。"
    • Nothing about who attacked, who saved or poisoned, why nobody died, or any other night action. A death or peaceful night does not publicly identify its cause.
    • Surviving roster.
    • Speech order contains every living active player and excludes the host and spectators.
    • An Agent hands to another Agent with @<next Agent>. An Agent handing to the user uses no naked @, names 用户玩家, and shows the user's future Agent handoff only as code such as `@NextAgent`.
    • If the first speaker is an Agent, the final line contains exactly one naked @: 首位发言 @<FirstSpeaker>,请发表看法;结束时交给 <NextPlayer>。
    • If the first speaker is the user, the final line contains no naked @: 首位发言是用户玩家,请发表看法;结束时按提示交给下一位。
  3. Host then stops. An Agent mention wakes the first Agent; a user-first announcement waits for the user's normal Room message.

Day Flow

5. Speech Chain
  1. Agent-to-Agent: end with @<NextAgent>.
  2. Agent-to-user: use no naked @; end by telling 用户玩家 to speak and show the user's required next handoff in code formatting.
  3. User turn: the user posts a normal public Room message and ends with a real @<NextAgent>, or 归票完毕 @<host> when last.
  4. If the user omits the handoff and host auto-reply is enabled, the host emits one minimal public handoff to the intended next Agent without rewriting the user's speech.

Keep each public statement between 60 and 120 Chinese characters, excluding the final handoff. State one main suspicion and one reason; do not repeat the phase rules or recap every prior speaker. Do not use private messages during the speech phase.

Public speech is the entire final reply. Never prefix it with private reasoning, hidden role facts, drafts, or a separator such as ---. A wolf may think privately as a wolf, but the final public reply must only contain what that public persona says.

6. Voting
  1. Woken by 归票完毕 @<host>, host replies publicly with one voting announcement:
    • "投票开始。顺序:A -> B -> ...(与发言顺序相同)。"
    • Rules: vote publicly with "我投 <名字>" or "弃票" and hand off to the next voter.
    • Final voter ends with 投票结束 @<host>.
    • If the first voter is an Agent, the final line contains exactly one naked @: 首位投票 @<FirstVoter>,请按格式投票;结束时交给 <NextVoter>。
    • If the first voter is the user, the final line contains no naked @: 首位投票是用户玩家,请按格式投票;结束时按提示交给下一位。
  2. Each voter uses at most one short reason, then the exact vote and public handoff; keep it under 60 Chinese characters. Apply the same Agent-to-user and user-to-Agent handoff rules as the speech chain.
  3. Host tallies from the public feed and replies publicly with the tally only, e.g. "票型:Jim 2 / Lucy 2 / Lily 1 / 弃票 0。Jim 与 Lucy 平票。"
  4. Tie-break: run one public PK speech round with @ chaining, then a fresh public voting round among non-tied voters. Still tied means no elimination today.
7. Last Words And End Of Day
  1. If an Agent player is eliminated, host replies publicly: "请发表遗言 @<eliminated>,结束用 遗言完毕 @<host> 交回给我。"
  2. If the user is eliminated, host uses no naked @ and asks 用户玩家 to post at most 80 Chinese characters, ending with a real 遗言完毕 @<host>.
  3. Whether a player was eliminated or the day ended without elimination, host checks the win condition. If the game continues, it queues the first valid night actor and uses the exact public night-transition reply from Public Boundary.

Privacy

  • Private: participation answer, role assignments, wolf night coordination, kill/seer/witch decisions, seer result, host state.
  • Public: phase announcements, death lists, daytime speeches, vote tallies, last words, win announcement.
  • Before the game ends, the host never reveals a role, night decision, private reply, or the cause of a death or peaceful night on the public feed. Announce only the resolved death list.
  • Players never reveal hidden role truth, private night actions, private prompts, or "I am secretly a wolf" reasoning in public. Only the host reveals final roles after the game has ended.
  • Players do not declare the winner before the host announces the official result.
  • A participating user's AskUserQuestion prompts and answers follow the same secrecy rules as Agent directed messages. Never quote or summarize them publicly.

© nexus-research-lab, Apache-2.0. 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/werewolf-6p of nexus-research-lab/nexus.

Open the folder on GitHubat commit 67f54e7

Compare with similar skills

Werewolf 6p 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.

Werewolf 6p compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Werewolf 6p this skillnexus-research-lab/nexus151—~4kAutomated safety check: PassApache-2.0
Player Exampleremotion-dev/remotion63k—~258Automated safety check: PassCustom licence
Escaping Containers To Hostmukul975/Anthropic-Cybersecurity-Skills34k—~3.4kAutomated safety check: PassApache-2.0
Cross Host Federationruvnet/ruflo74k—~1.1kAutomated safety check: PassMIT
Host Patternnukeop/nuclear19k—~1.3kAutomated safety check: PassAGPL-3.0
Testing For Host Header Injectionmukul975/Anthropic-Cybersecurity-Skills34k—~2.2kAutomated safety check: WarnApache-2.0

Similar skills

  • Player Example

    remotion-dev/remotion

    Official

    Start the @remotion/player example app and open it in the Codex browser.

    63k GitHub stars~258 tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Escaping Containers To Host

    mukul975/Anthropic-Cybersecurity-Skills

    Exploits privileged pods, host mounts, runC CVEs, and exposed Docker sockets to break out of a container and reach the underlying host during an authorized container-security assessment.

    34k GitHub stars~3.4k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Join and operate a signed cross-host agentbbs federation, and coordinate work claims across nodes.

    74k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Host Pattern

    nukeop/nuclear

    A skill your agent uses when adding a new domain to Nuclear's plugin system, or implementing a host.

    19k GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed
  • Testing For Host Header Injection

    mukul975/Anthropic-Cybersecurity-Skills

    Test web applications for HTTP Host header injection vulnerabilities to identify password reset poisoning, web cache poisoning, SSRF, and virtual host routing manipulation risks.

    34k GitHub stars~2.2k tokensUpdated 1 mo ago
    SecurityAuto-check: warnings
  • Add Hosted Key

    simstudioai/sim

    Add hosted API key support to a tool so Sim provides the key (metered and billed to the workspace) when a user has not brought their own.

    30k GitHub stars~3.6k tokensUpdated today
    Backend & APIsAuto-check passed

More from nexus-research-lab/nexus

All 17 skills in this repo
  • Imagegen

    nexus-research-lab/nexus

    Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background…

    151 GitHub stars~600 tokensUpdated yesterday
    Auto-check passed
  • Caixun Work Hours

    nexus-research-lab/nexus

    彩讯(RichPMS)工时填报助手:把当前会话、代码记录或用户口述整理成日报,按 8 小时分配,经用户确认后写入工时系统。用户提到“填日报、报工、补报、本周工时、日报被驳回”时使用。

    151 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Wechat Article Search

    nexus-research-lab/nexus

    搜索微信公众号文章,并整理标题、摘要、发布时间、来源公众号和链接。用户提到微信公众号、 公众号文章、微信文章、搜一批公众号资料、按关键词找公众号内容、查某公众号相关报道, 或需要为中文研究收集微信公众平台文章时使用;即使用户只说“搜微信里的文章”也应触发。

    151 GitHub stars~858 tokensUpdated yesterday
    Auto-check: notes
  • XLSX

    nexus-research-lab/nexus

    只要电子表格文件(.xlsx、.xlsm、旧版 .xls、.csv、.tsv)是任务的主要输入或输出,或者需要 被打开、读取、创建、修改,就使用本 Skill。也适用于公式、格式、图表、数据清洗和表格格式转换。

    151 GitHub stars~501 tokensUpdated yesterday
    Auto-check passed
  • Automation

    nexus-research-lab/nexus

    通过宿主提供的 nexus.command 结构化工具查询、规划、确认并管理 scheduled task。用户要求提醒、延迟执行、周期检查、定时报表、补跑、结果重投递、持续关注、修改或删除任务、处理任务权限阻塞时使用;同时适用于定时任务后台 run 检查自身状态。

    151 GitHub stars~541 tokensUpdated yesterday
    Auto-check passed
  • Execution Orchestrator

    nexus-research-lab/nexus

    选择执行结构、委派子智能体、管理 Nexus 工作图与可复用模板;遵守本轮权限,简单任务直接完成. An agent skill from nexus-research-lab/nexus.

    151 GitHub stars~821 tokensUpdated yesterday
    Auto-check passed

Questions about Werewolf 6p

What does Werewolf 6p do?

Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate. Werewolf 6p is an agent skill from nexus-research-lab/nexus. Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.

How do I install Werewolf 6p in Claude Code?

Run `npx skills add nexus-research-lab/nexus --skill werewolf-6p -a claude-code`. Or copy the skill folder (skills/werewolf-6p in nexus-research-lab/nexus) into .claude/skills/werewolf-6p in your project. Claude Code loads it when a task matches its description.

How do I install Werewolf 6p in Codex?

Run `npx skills add nexus-research-lab/nexus --skill werewolf-6p -a codex`. Or copy the skill folder (skills/werewolf-6p in nexus-research-lab/nexus) into .agents/skills/werewolf-6p in your project. Codex loads it when a task matches its description.

Can I use Werewolf 6p 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 nexus-research-lab/nexus --skill werewolf-6p -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/werewolf-6p, .gemini/skills/werewolf-6p, .github/skills/werewolf-6p and .opencode/skills/werewolf-6p in your project.

What does Werewolf 6p need to run?

SKILL.md names no scripts, command-line tools or credentials: Werewolf 6p is instructions for the agent only.

Does Werewolf 6p 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 Werewolf 6p 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 Werewolf 6p use?

Werewolf 6p is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Werewolf 6p use?

About 4k tokens (SKILL.md is roughly 16k 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 Werewolf 6p?

Skills that share tags, products or a category with Werewolf 6p: Player Example (remotion-dev/remotion, 63k stars), Escaping Containers To Host (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Cross Host Federation (ruvnet/ruflo, 74k stars) and Host Pattern (nukeop/nuclear, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Werewolf 6p?

nexus-research-lab (a GitHub organization) maintains it in nexus-research-lab/nexus, which has 151 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 10, 2026.

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