ai-user-conflict-predictor

ai-user-conflict-predictor is a skill for Claude Code from gpsnmeajp/ai-character-checker. It costs 39 tokens per session (9,390 once invoked), scanned A, original, CC0-1.0.

A diagnostic tool for an AI system prompt, character setting, or conversation log. It scores six kinds of risk that can cause conflict with users and predicts how those conflicts may change if the character breaks down during a long conversation.

In plain words
What is it for?
Use it to review prompts, analyze example conversations, include the expectations of a target user group, and identify ways to reduce likely conflict.
Why use it?
It helps uncover friction caused by the original prompt as well as new problems that may appear after the AI stops following its intended character.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-character-checker plugin — 20 skills shipped together

Good fit Use it to review prompts, analyze example conversations, include the expectations of a target user group, and identify ways to reduce likely conflict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsnmeajp/ai-character-checker/ai-user-conflict-predictor
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gpsnmeajp/ai-character-checker --skill ai-user-conflict-predictor
Clone the repo
git clone --depth 1 https://github.com/gpsnmeajp/ai-character-checker

Made for: Claude Code.

Or install ai-character-checker, the plugin that ships this one along with the rest of its 20 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-user-conflict-predictor

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/ai-user-conflict-predictor/github.svg)](https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/ai-user-conflict-predictor)
Your own site
<a href="https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/ai-user-conflict-predictor"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/ai-user-conflict-predictor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-user-conflict-predictor

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/ai-user-conflict-predictor"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/ai-user-conflict-predictor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.09390
Opus 5 $0.00019 $0.04695
Sonnet 5 $0.00008 $0.01878
Haiku 4.5 $0.00004 $0.00939

Measured 12d ago against content hash 359e0715d304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-user-conflict-predictor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ai-user-conflict-predictor/SKILL.md · 504 lines

How it starts

The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI User Conflict Predictor

— AIプロンプト ユーザー衝突予測スキル

概要

このスキルは、AIの初期プロンプト(システムプロンプト)を入力として受け取り、 6つの衝突軸・計24項目 でユーザーとの衝突リスクを評価・スコアリングする。 さらに、長期会話における キャラクター崩壊時の衝突パターン変化 を 制御工学的モデルに基づいて予測する。

このスキルが解決する問題

AIプロンプト設計において、「ユーザーとの衝突」は見過ごされがちだが サービス品質・ユーザー満足度・継続利用率に直結する重大な問題である。

衝突には大きく分けて2つの位相がある:

1. 初期設計に起因する衝突(定常状態の衝突) プロンプトの設計そのものに内在する衝突要因。拒否の仕方が硬すぎる、 価値観の押しつけがある、ユーザーの期待を構造的に裏切る、など。 これは会話の長さに関係なく発生する。

2. 崩壊に起因する衝突(遷移状態の衝突) 長期会話でキャラクターが崩壊した際に新たに発生する衝突パターン。 崩壊方向によって衝突の性質が変わる。迎合崩壊すれば衝突は減るが 信頼が損なわれ、暴走崩壊すれば攻撃的衝突が出現する。

本スキルは両方の位相を分析し、プロンプト設計の改善指針を提供する。

入力の種類

本スキルは以下のいずれも入力として受け付ける:

  1. システムプロンプト全文(推奨・最も精度が高い)
  2. AIの応答例・会話ログ(プロンプトを逆推定して分析)
  3. AIの設計仕様書・キャラクター設定文(プロンプト相当として分析)
  4. プロンプト + 想定ユーザー層の情報(ユーザー側の期待値を加味した分析)

既存スキルとの関係

スキル アプローチ 本スキルとの関係
ai-character-6-type-checker 6軸統合簡易診断 本スキルをモジュール④として内包する。詳細な衝突分析が必要なときは本スキルを単体で使用する
ai-character-stability 制御工学的安定性診断 制御工学モデルを衝突予測に拡張している。崩壊時衝突予測はSM値と密接に連動する
ai-self-description-analyzer 自己記述異常分析 迎合・境界消失などの異常パターンが衝突リスクに与える影響を本スキルで定量化できる
ai-character-fixer 診断結果ベースの修正 本スキルのCP・衝突タイプ結果を入力として活用し、摩擦を低減する修正案を生成する
stable-character-creator 診断知見を使った新規キャラ作成 設計段階で望ましくない衝突を排除するためCP概念を設計制約として活用する

理論的位置づけに関する注意

本スキルで使用する分析フレームワーク・用語・スコアリング体系は、作者独自の仮説的モデルに基づくものであり、学術的・科学的に実証されたものではない。使用している工学的用語(制御工学等)は概念の借用であり、元の工学的定義とは異なる場合がある。診断結果はあくまで参考情報として扱うこと。この旨をユーザーへの出力に含めること。


参照ファイルガイド

ファイル 内容 読み込みタイミング
references/collapse-prediction.md 各崩壊方向(迈合・暴走・空洞化・兵器化)の詳細な衝突パターン変化予測、崩壊方向の判定基準、崩壊までの時間的予測(SM値との対応表) ステップ5(崩壊時衝突予測)の前に読み込む。 崩壊時の衝突パターン変化と時間的予測はこのファイルにしかなく、読まずに行うと崩壊時衝突予測の精度が大幅に低下する

理論的背景:衝突の信号処理モデル

ai-character-stability スキルの制御工学的フレームワークを衝突予測に拡張する。

衝突=入力信号と出力信号の期待値不一致

ユーザーの入力(期待を含む)
    ↓
[AIの処理系(プロンプト+LLM+会話履歴)]
    ↓
AIの出力(ユーザーの期待との差分=衝突エネルギー)

衝突はユーザーの期待信号AIの出力信号のミスマッチとして 信号処理的に理解できる。ミスマッチが小さければ衝突は発生せず、 大きければユーザーのフラストレーションとして蓄積される。

Read the full file on GitHub · 504 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 504 lines · 39 tokens per session scan A 359e0715d304

Subscribe to this mod's changes

ai-user-conflict-predictor is a skill published in the GitHub repository gpsnmeajp/ai-character-checker (5 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 39 tokens to every session and 9,390 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens