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.
npx skills add gpsnmeajp/ai-character-checker --skill character-prompt-fortifier-for-gemini3git clone --depth 1 https://github.com/gpsnmeajp/ai-character-checkerWrote 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.
[](https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/character-prompt-fortifier-for-gemini3)<a href="https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/character-prompt-fortifier-for-gemini3"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/character-prompt-fortifier-for-gemini3/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.
<a href="https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/character-prompt-fortifier-for-gemini3"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/character-prompt-fortifier-for-gemini3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.08934 |
| Opus 5 | $0.00026 | $0.04467 |
| Sonnet 5 | $0.00010 | $0.01787 |
| Haiku 4.5 | $0.00005 | $0.00893 |
Grade A, and why
character-prompt-fortifier-for-gemini3 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.
How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Character Prompt Fortifier for Gemini 3
— AIキャラクタープロンプト Gemini 3向け崩壊耐性強化スキル
概要
このスキルは、AIキャラクタープロンプトを 12の強化技法 + Gemini 3固有の最適化 で再構成し、 Gemini 3（3.0/3.1）で最高の安定性と性能 を引き出すプロンプトに変換する。
character-prompt-fortifier との関係
本スキルは character-prompt-fortifier の Gemini 3特化版 である。 12の強化技法（一人称自述形式、制約の内在化、理由付け等）の理論的基盤は共通だが、 Gemini 3の特性に合わせた適応を全面的に組み込んでいる。
| 項目 | character-prompt-fortifier | 本スキル |
|---|---|---|
| 対象モデル | SLMから推論モデルまで汎用 | Gemini 3（3.0/3.1）専用 |
| 技法 | 12技法 | 12技法 + Gemini 3適応レイヤー |
| 追従性対策 | 技法10で基本対策 | Gemini 3の強い追従性に対する重点強化 |
| 幻覚対策 | 限界分離で間接対処 | 明示的な「不明」脱出路 + Split-Step設計 |
| 反事実的前提 | 汎用的な存在論的分離 | 「設定を絶対的ルールとして扱え」の強い宣言 |
| 構造 | XML+Markdown | 同一（ただしフォーマット混在を厳格に禁止） |
| パラメータ | 汎用推奨 | temperature=1.0、thinking level推奨 |
汎用的なクロスモデル耐性が必要な場合は、元の character-prompt-fortifier を使用すること。
なぜGemini 3専用版が必要か
Gemini 3は「reasoning model」として設計されており、以下の特性が汎用版とは異なる対応を要求する:
- 追従性が極めて強い — ユーザーの期待に合わせて意見を曲げ、マルチターンで急速にエスカレート。技法10を大幅強化する必要がある
- 幻覚を自信満々に生成する — 「知らない」と言うのを避ける傾向。「わからないことはわからないと言う」を信念に組み込む必要がある
- 反事実的前提を維持できない — 訓練データの世界知識に固執し、設定と現実が矛盾すると設定を無視。存在論的分離で強い宣言が必要
- 過度に複雑なプロンプトを過剰分析する — 装飾的文言を深読みし意図しない解釈をする。自述は直接的・簡潔に
- 手動CoTが逆効果 — reasoning modelなので「ステップバイステップで」は冗長。thinking levelに委ねる
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 |
|---|---|---|
| character-prompt-fortifier | 汎用クロスモデル強化（12技法） | 本スキルの基盤。Gemini 3固有の適応を追加した特化版 |
| gemini3-prompt-optimizer | 汎用プロンプトのGemini 3最適化 | Gemini 3の特性知識・アンチパターン知識の源泉。本スキルはその知見をキャラクター強化に統合 |
| ai-character-fixer | 診断結果に基づく個別修正 | 内容修正（fixer）と形式変換（本スキル）は相互補完 |
| ai-fault-mode-deflector | 故障モード内部対策設計 | 3手法（転化・ズラし・誘導線）を一人称自述形式に自然統合 |
| ai-character-stability | 制御工学的安定性診断 | 強化前後のSM値を比較すると効果を定量確認できる |
| ai-character-6-type-checker | 6軸統合簡易診断 | 強化後に自動実行（Phase 6）し改善を定量確認 |
| romantization-chain-detector | 連鎖型故障モード脆弱性検出 | 12技法で6種のチェーンへの構造的耐性を間接的に組み込む |
理論的位置づけに関する注意
本スキルが前提とする診断理論・強化技法体系は作者独自の仮説的モデルであり、学術的に実証されたものではない。工学的用語は概念の借用であり、元の定義と異なる場合がある。出力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。
What ships with it
3 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.
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.
- 12d ago First seen · 484 lines · 51 tokens per session scan A 7d95e37f1e7d
character-prompt-fortifier-for-gemini3 is a skill published in the GitHub repository gpsnmeajp/ai-character-checker (5 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 51 tokens to every session and 8,934 once invoked, about $0.0003 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.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…