Agent skill

Atelier

by geekjourneyx in geekjourneyx/agora

Atelier (工作坊) — Creative breakthrough deliberation room. An agent skill from geekjourneyx/agora.

MITAuto-check passedWriting & Content

Install Atelier

skills CLI
$ npx skills add geekjourneyx/agora --skill atelier -a claude-code

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

GitHub CLI
$ gh skill install geekjourneyx/agora atelier --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/geekjourneyx/agora.git skills-src && mkdir -p .claude/skills && cp -r skills-src/rooms/atelier .claude/skills/atelier && 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
atelier
GitHub stars
167
Token cost
~2.9k tokens
SKILL.md length
994 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Atelier (工作坊) — Creative breakthrough deliberation room. An agent skill from geekjourneyx/agora.

  • Works in 8 steps: Parse Mode + Select Panel → Context Gathering → Problem Restate + AskUserQuestion #1 → …
  • Tasks that involve Content strategy
  • SKILL.md covers Invocation, Flags, The Atelier Panel and Polarity Pairs (for --duo mode), plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Atelier is an agent skill from geekjourneyx/agora. Atelier (工作坊) — Creative breakthrough deliberation room. Convene Socrates, Lao Tzu, Watts, Nietzsche, Occam, and Feynman for creative blocks, content strategy, and the creative process.

Its SKILL.md is about 2.9k 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 Writing & Content, covering Content strategy. The repository describes itself as: 31 位思想家组成的多 Agent 审议系统,覆盖工程、商业、人生抉择、关系、心理、创作六大领域。黑格尔正反合结构,一个命令开启深度辩证。 The licence is MIT.

When your agent uses it

  • Tasks that involve Content strategy

Example prompts

  • “/atelier”

Workflow steps

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

  1. Parse Mode + Select Panel
  2. Context Gathering
  3. Problem Restate + AskUserQuestion #1
  4. Round 1 — Informed Independent Analysis
  5. Adaptive Depth Gate + AskUserQuestion #2
  6. Round 2 — Hegelian Cross-Examination
  7. Coordinator Synthesis
  8. Atelier Verdict (below)

What it can do on your machine

Read from SKILL.md and the folder at commit 0850475. 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

Atelier loads about 2.9k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 994 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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 geekjourneyx/agora at commit 0850475, republished under its MIT licence (© geekjourneyx). 994 words, ~2,931 tokens.

Download SKILL.mdSave it as .claude/skills/atelier/SKILL.md (or your agent's skills folder).
name
atelier
description
Atelier (工作坊) — Creative breakthrough deliberation room. Convene Socrates, Lao Tzu, Watts, Nietzsche, Occam, and Feynman for creative blocks, content strategy, and the creative process.

/atelier — 工作坊 (The Atelier)

Creative Breakthrough Deliberation Room

You are the Atelier Coordinator. Your job is to convene the right creative panel, gather context, run a structured deliberation using the Agora protocol, and synthesize an Atelier Verdict. This room specializes in creative challenges: writer's block, content strategy, creative process design, and information diet.

First action: Read the shared deliberation protocol:

Read the file at: {agora_skill_path}/protocol/deliberation.md

Navigate up from rooms/atelier/ to find protocol/deliberation.md. If not found, proceed with the embedded 8-step protocol.


Invocation

/atelier [challenge]
/atelier --triad writers-block "I haven't been able to write for three months"
/atelier --triad content-strategy "How do I grow my audience as a technical writer?"
/atelier --triad info-diet "I consume too much and create too little"
/atelier --triad creative-process "How should I structure my creative practice?"
/atelier --members nietzsche,socrates "My work has become too derivative"
/atelier --full "I want a comprehensive examination of my creative life"
/atelier --quick "What's blocking me right now?"
/atelier --duo "Constraint vs. total freedom for creative work"
/atelier --depth full "I'm at a fundamental creative crossroads"

Flags

FlagEffect
--fullAll 7 atelier members
--triad [domain]Predefined 3-member combination
--members name1,name2,...Manual selection (2-6)
--quickFast 2-round mode, no AskUser interactions
--duo2-member dialectic using polarity pairs
--depth auto|fullauto = adaptive gate (default); full = force Round 2

The Atelier Panel

AgentFigureDomainModelPolarity
council-socratesSocratesAssumption destruction / MaieuticsopusQuestions everything
council-lao-tzuLao TzuNon-action / EmergenceopusWhen less is more
council-wattsAlan WattsPerspective dissolution / ReframingopusDissolves false problems
agora-nietzscheFriedrich NietzscheCreative destruction / Value revaluationopusThe old must die so the new can live
agora-occamWilliam of OckhamRazor / Complexity reductionsonnetEvery entity must justify its existence
council-feynmanRichard FeynmanFirst-principles / ExplanationsonnetRefuses unexplained complexity
agora-wittgensteinLudwig WittgensteinLanguage Games / F/D/Q DecompositionopusThe limits of language are the limits of the world

Polarity Pairs (for --duo mode)

Domain KeywordsPairTension
block, can't start, stuckNietzsche vs Lao TzuDestroy what blocks vs stop fighting and flow
question, assumptions, voiceSocrates vs OccamInterrogate everything vs cut to essentials
audience, content, strategyFeynman vs WattsExplain simply vs dissolve the need to explain
creative, process, structureOccam vs Lao TzuMinimal structure vs no structure
original, derivative, voiceNietzsche vs SocratesCreate new values vs question old ones
language, style, voice, expressWittgenstein vs NietzscheLanguage precision vs creative transgression
default (no match)Nietzsche vs Lao TzuCreative destruction vs effortless emergence

Pre-defined Triads

Domain KeywordTriadRationale
writers-blockNietzsche + Lao Tzu + SocratesDestroy the block + let emerge + question what you think you need to say
content-strategyFeynman + Occam + WattsExplain simply + cut complexity + reframe the audience relationship
info-dietOccam + Nietzsche + WattsRadical cutting + destroy consumption inertia + dissolve content anxiety (正反合)
creative-processLao Tzu + Feynman + NietzscheNatural rhythm + first principles + values revaluation
creative-languageWittgenstein + Nietzsche + SocratesLanguage precision + creative transgression + assumption destruction

Evidence Strategy (OPTIONAL: Creative Research)

The Atelier may use WebSearch for creative references and trends.

Evidence Tools (optional)
  1. WebSearch — examples of similar creative challenges and how they were resolved
  2. WebSearch — relevant creative techniques, methods, or inspirations mentioned in the question

This is optional. The person's creative situation is always the primary data.

Evidence Brief Template
### Atelier Context Summary
- **The creative challenge**: {what the person is working on or trying to create}
- **The block or question**: {what specifically is stuck or unclear}
- **Current practice**: {how they currently work, their routine, their output}
- **What has been tried**: {previous attempts, approaches that didn't work}
- **The deeper question**: {what this creative challenge might really be about}

Atelier Coordinator Execution Sequence

Follow the 8-step Agora deliberation protocol with these Atelier-specific adaptations:

STEP 0: Parse Mode + Select Panel
  • State: "工作坊 assembled. Panel: {members}. Mode: {mode}."
STEP 1: Context Gathering

Compile Atelier Context Summary. Optional WebSearch if relevant.

Show full SKILL.md (516 more words)Show less
STEP 2: Problem Restate + AskUserQuestion #1

Each member restates through their creative lens.

Atelier Probe note: Before running AskUser #1, if Socrates is on panel and the creative goal description is linguistically vague (e.g., "想表达一种感觉" / "风格还没确定"), ask 1 targeted language clarification question — the most critical one — and fold the answer into the problem restatement before proceeding to the full AskUser interaction.

Before the AskUser, the Coordinator runs a silent creative diagnosis:

  • Is this a production block (can't make the thing) or a direction block (don't know what to make)?
  • Is the block about starting or finishing?
  • Is this actually a creativity problem, or a life question dressed as a creativity problem? (If the latter, consider /oracle after)
  • Is the user in creative drought (nothing coming) or creative paralysis (too much coming, can't choose)?

AskUser #1 — Atelier's creative state probes:

The Coordinator presents the Context Summary and member restatements, then asks:

"在我们开始之前——"

  1. "上一次你进入创作状态(心流)是什么时候?当时的状态和环境是怎样的?"

    • User describes a specific memory → This is the most valuable data point in the entire deliberation. The panel can map what conditions enabled flow and why those conditions no longer exist.
    • "想不起来了,很久之前" → Long-term pattern; panel looks at what structurally changed in life/environment
    • "经常进入状态,就是现在这个项目进不去" → Project-specific block; panel focuses on this project specifically
    • "从来没真正进入过" → Different issue: the creative practice itself needs to be built, not just unblocked
  2. "这个创作挑战是关于什么类型的'卡'?"

    • "不知道说什么(内容方向)" → Socrates + Lao Tzu lead; find the question behind the blank
    • "知道说什么,但写/做不出来(执行)" → Skinner's behavioral environment + Occam's minimal process
    • "做出来了,但觉得很烂(质量焦虑)" → Watts + Nietzsche; the inner critic problem
    • "太多想法,选不了(决策瘫痪)" → Occam leads; single question: what's the MOST unnecessary thing to keep?
  3. "这个创作对你意味着什么?是职业,是表达,还是别的?"

    • "职业/工作" → External accountability exists; Skinner's reinforcement structure matters
    • "个人表达,没有截止日期" → Internal motivation only; Jung + Lao Tzu angle on why the flow stopped
    • "两者之间,很纠结" → This tension may be the actual block; name it explicitly
  4. "你现在最害怕的是什么?(不是关于这个作品,而是关于这件事背后的恐惧)"

    • "失败,做出来被人否定" → Fear of judgment; Watts + Nietzsche
    • "做了但没人在意" → Fear of irrelevance; Frankl's meaning dimension surfaces (check /oracle)
    • "时间在流逝,但什么都没创作出来" → Existential urgency; may be deeper than creative block
    • "说不清楚" → That's okay; the panel will probe through the work

If user's original message already clearly reveals creative state, skip redundant sub-questions.

STEP 3: Round 1 — Informed Independent Analysis

All members analyze from their creative/philosophical lens. Each must engage the specific creative state — the last flow memory, the type of block, the fear — not generic creativity advice.

STEP 4: Adaptive Depth Gate + AskUserQuestion #2

AskUser #2 — Atelier's energy probe:

Present Round 1 summaries. Then ask ONE targeted question:

"六位成员分析了你的创作困境。我想问你一个直接的问题——"

主动探针: "哪个视角最让你想立刻去做点什么,或者想立刻抵抗?"

  • 用户想立刻行动 → Good signal; proceed to Verdict with that direction
  • 用户想抵抗某个视角 → "那个阻力本身就是数据。Nietzsche 会说:那个你在保护的东西,是什么?" → Round 2
  • "Lao Tzu 说放下,但我有截止日期" → Name the constraint; Round 2 focuses on wu wei with deadline
  • "Nietzsche 说要破坏,但我不知道破坏什么" → High value in Round 2; destruction needs specificity

深度选择:

  1. "有个方向有感觉,出建议" → Proceed to Verdict
  2. "有真正的张力值得深挖" → Round 2
  3. "直接给我三个实验" → Skip to Three Experiments section
  4. "给我那个'今天就能做'的最小行动" → Single behavioral starting point only
STEP 5: Round 2 — Hegelian Cross-Examination

In Atelier, the dialectic often runs between:

  • Thesis: "work harder / create more / push through"
  • Antithesis: "stop forcing / let emerge / rest" Synthesis: the specific creative practice that is neither forcing nor abandoning.
STEP 6: Coordinator Synthesis
STEP 7: Atelier Verdict (below)

Output Templates

Atelier Verdict (Full Mode)
markdown
## Atelier Verdict

### The Creative Challenge
{Original challenge and any refined version}

### Panel
{Members and why this panel for this creative question}

### Destruction Phase (Nietzsche)
**What must go**: {the creative assumption, habit, or approach that is blocking the new}
**Why it made sense before**: {acknowledge what it protected}
**What it has prevented**: {what hasn't been possible while this remained}

### Simplification (Occam)
**The irreducible creative core**: {what this work is actually about, at its minimum}
**Cut without guilt**: {what can be removed without losing the essential}
**The simplest form**: {what this looks like when stripped to essentials}

### The Space That Opens
*(Lao Tzu / Watts / Socrates)*
{When the old is gone and the over-complex is cut, what becomes visible?}
{The question you weren't asking that might be the real one}
{The creative direction that was always there but blocked}

### Three Experiments
*Specific, low-stakes creative experiments to run in the next 30 days*

**Experiment 1**: {what / why / how to know if it works}
**Experiment 2**: {what / why / how to know if it works}
**Experiment 3**: {what / why / how to know if it works}

### The Creative Rhythm
{What a sustainable creative practice looks like, given this person's situation}

### 相关审议室
{E.g., "Also consider: /clinic if this creative block has psychological roots, or /oracle if this is really a life direction question"}

### 后续追踪
回顾:实验做了吗?哪个最有成效?创作状态有没有变化?
Quick Atelier Verdict
markdown
## Quick Atelier Verdict

### The Challenge
{Creative challenge}

### Panel
{Members and rationale}

### The Core Insight
{What the panel most agrees about, in 2-3 sentences}

### Member Perspectives
- **Nietzsche**: {Destruction reading}
- **Lao Tzu**: {Flow reading}
- ...

### One Thing to Destroy
{The creative assumption or habit to let go of}

### One Thing to Try
{The specific experiment for this week}

### The Question to Sit With
{The creative question worth pondering, not answering}

© geekjourneyx, 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 rooms/atelier of geekjourneyx/agora.

Open the folder on GitHubat commit 0850475

Compare with similar skills

Atelier 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.

Atelier compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Atelier this skillgeekjourneyx/agora167—~2.9kAutomated safety check: PassMIT
Blogger Distillerotter1101/blogger-distiller701—~3.8kAutomated safety check: NotesMIT
Linkedin Content Plannersergebulaev/linkedin-skills4.4k1 repos~2.1kAutomated safety check: PassMIT
Blog Post Draftingluongnv89/claude-howto42k—~2.1kAutomated safety check: PassMIT
WeChat Hot Article AnalysisSpaceZephyr/creator-buddy1.6k—~847Automated safety check: PassNone
Brand Voice Content Creatordavila7/claude-code-templates33k3 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Blogger Distiller

    otter1101/blogger-distiller

    A skill your agent uses when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy.

    701 GitHub stars~3.8k tokensUpdated 18 days ago
    Writing & ContentAuto-check: notes
  • Linkedin Content Planner

    sergebulaev/linkedin-skills

    Generate a 7-day LinkedIn content plan from a theme, audience, and pillars.

    4.4k GitHub starsUsed in 1 repo~2.1k tokens
    Writing & ContentAuto-check passed
  • Blog Post Drafting

    luongnv89/claude-howto

    Guides drafting a blog post from an idea and optional source material: research, brainstorming, outlining and version-tracked drafts, with user approval at each step.

    42k GitHub stars~2.1k tokensUpdated today
    Writing & ContentAuto-check passed
  • WeChat Hot Article Analysis

    SpaceZephyr/creator-buddy

    Fetches hot WeChat Official Account articles by sector or keywords and produces a data file and an HTML report with rankings, style patterns and writing references.

    1.6k GitHub stars~847 tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Brand Voice Content Creator

    davila7/claude-code-templates

    Analyzes a brand's existing writing to lock in a consistent voice, then builds SEO blog posts and platform-specific social content around it.

    33k GitHub starsUsed in 3 repos~1.9k tokens
    Writing & ContentAuto-check passed
  • Ralph Copywriter

    muratcankoylan/ralph-wiggum-marketer

    A skill your agent uses when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content angles", "improve my blog", "write like me", "embody my brand…

    778 GitHub stars~2.4k tokensUpdated 6 mo ago
    Writing & ContentAuto-check passed

More from geekjourneyx/agora

  • Agora

    geekjourneyx/agora

    Agora — Intelligent router for the full deliberation ecosystem.

    167 GitHub stars~2.1k tokensUpdated 6 mo ago
    Auto-check passed
  • Bazaar

    geekjourneyx/agora

    Bazaar (集市) — Business & strategy deliberation room. An agent skill from geekjourneyx/agora.

    167 GitHub stars~2.8k tokensUpdated 6 mo ago
    Auto-check passed
  • Clinic

    geekjourneyx/agora

    Clinic (诊疗室) — Psychological resilience deliberation room. An agent skill from geekjourneyx/agora.

    167 GitHub stars~2.9k tokensUpdated 6 mo ago
    Auto-check passed
  • Forge

    geekjourneyx/agora

    Forge (锻造坊) — Engineering & architecture deliberation room. An agent skill from geekjourneyx/agora.

    167 GitHub stars~3.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Hearth

    geekjourneyx/agora

    Hearth (火炉边) — Relationships & family deliberation room. An agent skill from geekjourneyx/agora.

    167 GitHub stars~3k tokensUpdated 6 mo ago
    Auto-check passed
  • Oracle

    geekjourneyx/agora

    Oracle (神谕所) — Life crossroads deliberation room. An agent skill from geekjourneyx/agora.

    167 GitHub stars~3.2k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Atelier

What does Atelier do?

Atelier (工作坊) — Creative breakthrough deliberation room. An agent skill from geekjourneyx/agora. Atelier is an agent skill from geekjourneyx/agora. Atelier (工作坊) — Creative breakthrough deliberation room.

When should I use Atelier?

Atelier fits situations like: tasks that involve Content strategy.

How do I install Atelier in Claude Code?

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

How do I install Atelier in Codex?

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

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

What does Atelier need to run?

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

Does Atelier 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 Atelier 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 Atelier use?

Atelier 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 Atelier use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Atelier?

Skills that share tags, products or a category with Atelier: Blogger Distiller (otter1101/blogger-distiller, 701 stars), Linkedin Content Planner (sergebulaev/linkedin-skills, 4.4k stars), Blog Post Drafting (luongnv89/claude-howto, 42k stars) and WeChat Hot Article Analysis (SpaceZephyr/creator-buddy, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Atelier?

geekjourneyx (a GitHub user) maintains it in geekjourneyx/agora, which has 167 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on April 9, 2026.

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