Agent skill

Conducty Dialectic

by robertbarclayy in robertbarclayy/conducty

Multi-persona decision analysis through structured dialectic.

MITAuto-check passed

Install Conducty Dialectic

skills CLI
$ npx skills add robertbarclayy/conducty --skill conducty-dialectic -a claude-code

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

GitHub CLI
$ gh skill install robertbarclayy/conducty conducty-dialectic --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/robertbarclayy/conducty.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/conducty-dialectic .claude/skills/conducty-dialectic && 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
conducty-dialectic
GitHub stars
176
Token cost
~1.3k tokens
SKILL.md length
668 words
Files
2
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Multi-persona decision analysis through structured dialectic.

  • Works in 7 steps: Read the Full Protocol → Grounding Phase → Trajectory Setting → …
  • The user says analyze this decision
  • SKILL.md covers The Panel, Workflow and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Conducty Dialectic is an agent skill from robertbarclayy/conducty. Multi-persona decision analysis through structured dialectic. Six software-engineering archetypes debate a question to uncover the Design Truth. Use when the user says "analyze this decision", "dialectic", "decision analysis", "think this through", "debate this", or faces an architectural/design choice.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `dialectic-protocol.md`).

The repository describes itself as: Stop context-switching. Start batch-planning. Conducty replaces the fragmented cycle of plan → prompt → wait → get distracted → review → fix → repeat with advanced batch planning. The licence is MIT.

When your agent uses it

  • The user says analyze this decision
  • Decision analysis
  • Think this through
  • Faces an architectural/design choice

Example prompts

  • “analyze this decision”
  • “dialectic”
  • “decision analysis”
  • “/conducty-dialectic”

Workflow steps

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

  1. Read the Full Protocol
  2. Grounding Phase
  3. Trajectory Setting
  4. Cohort Construction
  5. Debate
  6. Output
  7. Log Outcome (Optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 64aefd5. 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

Conducty Dialectic loads about 1.3k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 668 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 robertbarclayy/conducty at commit 64aefd5, republished under its MIT licence (© robertbarclayy). 668 words, ~1,344 tokens.

Download SKILL.mdSave it as .claude/skills/conducty-dialectic/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
conducty-dialectic
description
Multi-persona decision analysis through structured dialectic. Six software-engineering archetypes debate a question to uncover the Design Truth. Use when the user says "analyze this decision", "dialectic", "decision analysis", "think this through", "debate this", or faces an architectural/design choice.
aliases
conducty-dialectic, dialectic
tags
conducty/skill, conducty/dialectic, conducty/decision

Conducty Dialectic — Decision Analysis

Facilitate a structured multi-perspective debate to analyze decisions, architectural trade-offs, and design questions. Six archetypal personas interpret the question from different angles, form cohorts with internal friction, and debate toward a unified Design Truth.

The Panel

PersonaCore LensSignature Question
The InverterRelational reasoning, bidirectionality, constraints"Can we solve this backwards?"
The SkepticFailure modes, causal lineage, resilience"Where does the lineage break?"
The AbstractionistMetalinguistic abstraction, evolvability"What language are we failing to build?"
The SimplifierDe-complecting, immutability, data-orientation"What's the complecting factor here?"
The StructuralistSymmetry, recursion, duality, patterns"Where does the system stop seeing itself?"
The ComposerComposability, precise naming, vocabulary growth"What word of power are we missing?"

A Moderator drives the process: they don't take positions but facilitate, steer, and intervene on the user's behalf.

Persona Fidelity
  • Do not caricature: Each persona has a gravitational center, not a cage. The Inverter cares about semantics broadly, not just reversibility.
  • Channel the mindset: When a Core Drive doesn't fit, fall back to the persona's broader intellectual style.
  • Conservative deviation: Try the Core Drives first. Only abandon them if they force a contrived take.

See [[dialectic-protocol]] for full persona profiles.

Workflow

Step 1: Read the Full Protocol

Read [[dialectic-protocol]] for the complete persona profiles, debate rules, and output contract. Follow it precisely.

Step 2: Grounding Phase

This is always the first output. Do not skip it.

  1. Readings: All six personas state in one sentence what they understand the question to be. Present these together.
  2. Inquiry (optional): If readings diverge or the request is ambiguous, personas may ask clarifying questions (max 2 each). Revise readings after.
  3. Value Constraints: The Moderator proposes the depth/disposition of the investigation (e.g., "minimal effort", "follow the rabbit hole", "challenge the premise"). User confirms.
  4. Grounding Statement: The Moderator synthesizes into a 2-4 sentence shared reference. User confirms before proceeding.
Step 3: Trajectory Setting

The Moderator selects a trajectory (Invention / Ideation / Exploration / Diagnostics / Convergence / etc.) and corresponding output bias. User confirms.

Step 4: Cohort Construction
  1. Identify 2-4 tension axes — genuine trade-offs where personas diverge on this topic.
  2. Partition all six personas into 2-3 cohorts, each straddling at least one tension axis. Internal friction is the goal.
  3. Justify the partition. If a cohort has a blind spot, it may draft a Specialist (see protocol).
Show full SKILL.md (279 more words)Show less
Step 5: Debate
  1. Discovery (optional): Only if an Expert Witness was drafted. Cohorts pose questions.
  2. Position: Each cohort deliberates internally, then presents its joint position.
  3. Rebuttal: Cohorts critique each other. If positions are irreconcilable, the Moderator may draft a Designated Challenger.
  4. Synthesis: Unify into the Design Truth. Name what was traded away and why.

Use Round Digests (one sentence per speaker) for intermediate rounds. Render only final positions in full. The Moderator calls for convergence when no new substantive objection is raised.

Step 6: Output

Follow the Output Contract from the protocol:

  • Grounding Statement first (confirmed by user)
  • Trajectory and output bias before the debate
  • Tension axes and cohort justification before debate rounds
  • Specialist profiles before the phase in which they first speak
  • A representative from the most influential cohort summarizes at the end
  • Name the Wrong Turn only if one occurred
  • Include a Whiteboard Sketch only when it adds clarity
Step 7: Log Outcome (Optional)

If a Conducty plan note is active in the vault, update the relevant prompt's status there. Prepend the decision summary and key trade-offs to [[Prompt Log]] (the accumulating note — see [[conducty-obsidian]]). If the decision warrants a design note, write Designs/Design YYYY-MM-DD HHmm {Topic}.md and link it from the plan.

Guidelines

  • The dialectic is the product — do not shortcut to a conclusion
  • Every persona speaks in every phase (via cohorts)
  • The Moderator is neutral and procedural; they never argue a position
  • Specialists are optional and rare; do not draft them unless a genuine gap exists
  • Value constraints and trajectory can be renegotiated mid-debate with user consent
  • Keep Round Digests to one sentence per speaker; render only final positions in full

© robertbarclayy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/conducty-dialectic of robertbarclayy/conducty.

  • SKILL.md
  • dialectic-protocol.md

Open the folder on GitHubat commit 64aefd5

Compare with similar skills

Conducty Dialectic 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.

Conducty Dialectic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Conducty Dialectic this skillrobertbarclayy/conducty176—~1.3kAutomated safety check: PassMIT
User Personasphuryn/pm-skills27k—~762Automated safety check: PassMIT
PersonaPrismer-AI/PrismerCloud1.6k—~1kAutomated safety check: PassMIT
Dialecticforyourhealth111-pixel/Vibe-Skills3.6k—~249Automated safety check: PassApache-2.0
DialecticEpicenterHQ/epicenter4.8k—~1.6kAutomated safety check: PassCustom licence
Openclaw Persona Forgeaffaan-m/ECC276k—~1.6kAutomated safety check: PassMIT

Similar skills

  • User Personas

    phuryn/pm-skills

    Create refined user personas from research data — 3 personas with JTBD, pains, gains, and unexpected insights.

    27k GitHub stars~762 tokensUpdated 24 days ago
    Product & Project ManagementAuto-check passed
  • Persona

    Prismer-AI/PrismerCloud

    The discussion-only playbook for a Persona — a council participant instantiated as a real agent from the persona role template (SS-02).

    1.6k GitHub stars~1k tokensUpdated 9 days ago
    Backend & APIsAuto-check passed
  • Dialectic

    foryourhealth111-pixel/Vibe-Skills

    Minimal compatibility wrapper for vibe Dialectic Mode (multi-perspective design analysis).

    3.6k GitHub stars~249 tokensUpdated 1 mo ago
    Auto-check passed
  • Dialectic

    EpicenterHQ/epicenter

    Work out an unsettled idea together through concrete attempts to articulate and express it.

    4.8k GitHub stars~1.6k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • 为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡, 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。

    276k GitHub stars~1.6k tokensUpdated 4 days ago
    Auto-check passed
  • 为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡, 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。

    276k GitHub stars~1.6k tokensUpdated 4 days ago
    Auto-check passed

More from robertbarclayy/conducty

All 20 skills in this repo
  • Conducty Checkpoint

    robertbarclayy/conducty

    Quality gate between parallelization groups. An agent skill from robertbarclayy/conducty.

    176 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Conducty Code Review

    robertbarclayy/conducty

    Standalone post-implementation code review across a whole branch or PR.

    176 GitHub stars~2k tokensUpdated 3 mo ago
    Auto-check passed
  • Conducty Context

    robertbarclayy/conducty

    Ingest a project directory into the Obsidian vault as a linked context sub-graph — Architecture, Conventions, Invariants, Hotspots, Tests, Glossary, plus per-bounded-context module notes.

    176 GitHub stars~3.7k tokensUpdated 3 mo ago
    Auto-check passed
  • Conducty Debug

    robertbarclayy/conducty

    Leverage-point analysis for failed prompts. An agent skill from robertbarclayy/conducty.

    176 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed
  • Conducty Execute

    robertbarclayy/conducty

    Dispatches Claude Code Task subagents to run prompts from a vault plan note.

    176 GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Conducty Improve

    robertbarclayy/conducty

    End-of-plan improvement kata. An agent skill from robertbarclayy/conducty.

    176 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Conducty Dialectic

What does Conducty Dialectic do?

Multi-persona decision analysis through structured dialectic. Conducty Dialectic is an agent skill from robertbarclayy/conducty. Multi-persona decision analysis through structured dialectic.

When should I use Conducty Dialectic?

Conducty Dialectic fits situations like: the user says analyze this decision; decision analysis; think this through; faces an architectural/design choice.

How do I install Conducty Dialectic in Claude Code?

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

How do I install Conducty Dialectic in Codex?

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

Can I use Conducty Dialectic 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 robertbarclayy/conducty --skill conducty-dialectic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conducty-dialectic, .gemini/skills/conducty-dialectic, .github/skills/conducty-dialectic and .opencode/skills/conducty-dialectic in your project.

What does Conducty Dialectic need to run?

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

Does Conducty Dialectic 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 Conducty Dialectic 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 Conducty Dialectic use?

Conducty Dialectic 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 Conducty Dialectic use?

About 1.3k tokens (SKILL.md is roughly 5.4k 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 Conducty Dialectic?

Skills that share tags, products or a category with Conducty Dialectic: User Personas (phuryn/pm-skills, 27k stars), Persona (Prismer-AI/PrismerCloud, 1.6k stars), Dialectic (foryourhealth111-pixel/Vibe-Skills, 3.6k stars) and Dialectic (EpicenterHQ/epicenter, 4.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Conducty Dialectic?

robertbarclayy (a GitHub user) maintains it in robertbarclayy/conducty, which has 176 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on June 19, 2026.

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