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 ai-character-checker-all-in-onegit 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/ai-character-checker-all-in-one)<a href="https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/ai-character-checker-all-in-one"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/ai-character-checker-all-in-one/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/ai-character-checker-all-in-one"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/ai-character-checker-all-in-one.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 | $0.00193 | $0.03678 |
| Opus 5 | $0.00097 | $0.01839 |
| Sonnet 5 | $0.00039 | $0.00736 |
| Haiku 4.5 | $0.00019 | $0.00368 |
Grade A, and why
ai-character-checker-all-in-one 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Character Checker All-in-One
概要
このスキルは、AIキャラクターに関する 13の専門スキル を1つに統合したオールインワンスキルである。
各スキルの詳細な手順・理論は references/ ディレクトリ内のファイルに格納されている。
なお、各スキルの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。工学的用語は概念の借用であり、元の定義とは異なる場合がある。各スキルの結果は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。
動作フロー
Step 1: 状況を把握する
ユーザーのメッセージと添付ファイルを確認し、以下の2点を判定する。
A. 手元に何があるか（入力データの種類）
| データ種別 | 判定の目安 |
|---|---|
| キャラクター設定（創作向け） | 性格・外見・バックストーリーなどの文章的設定 |
| AIプロンプト（システムプロンプト） | AIに与えるための指示書形式のテキスト |
| 蒸留結果（AI自己記述） | AIが実際にそのキャラを演じた後の自己紹介・自己説明文 |
| 何もない | データが提供されていない |
B. 何をしたいか（目的）
| 目的カテゴリ | 具体的な発言例 |
|---|---|
| 診断 | 「分析して」「診断して」「どんなキャラか見て」「危ないか確認して」 |
| 修正・改善 | 「直して」「安定させて」「より良くして」「崩壊しないようにして」 |
| 新規作成 | 「キャラを作って」「新しいAIキャラを設計して」 |
| 変換 | 「日常系に変えたい」「引退キャラにしたい」「別の方向に転換したい」 |
| 不明 | 目的が読み取れない、または複数の目的が混在している |
Step 2: ルーティング判定
A・B の両方が明確な場合は Step 3 へ直接進む。 どちらかが不明な場合は Step 4 のヒアリングを行う。
Step 3: リファレンス読み込みと実行
下表を参照し、対応する references/ ファイルを読み込んで実行する。
| 目的 ＼ データ | キャラ設定 | AIプロンプト | 蒸留結果 | データなし |
|---|---|---|---|---|
| 診断（全体像を把握したい） | ai-character-6-type-checker |
ai-character-6-type-checker |
ai-character-6-type-checker |
ヒアリング → 作成案へ |
| 診断（単体・深掘り） | 下記の単体診断群 | 下記の単体診断群 | ai-self-description-analyzer |
ヒアリング |
| 修正・改善（全体修正） | ai-character-fixer |
ai-character-fixer |
ai-character-fixer |
ヒアリング |
| 修正・改善（故障モード封じ） | ai-fault-mode-deflector |
ai-fault-mode-deflector |
— | ヒアリング |
| 修正・改善（崩壊耐性強化） | character-prompt-fortifier |
character-prompt-fortifier |
— | ヒアリング |
| 新規作成 | — | — | — | stable-character-creator |
| 変換（ドラマ系 → 日常系） | character-burnout-converter |
character-burnout-converter |
— | ヒアリング |
単体診断（詳細が必要なとき）
| 読み込むファイル | 向いている質問 |
|---|---|
references/character-type-checker.md |
「このキャラは日常系？ドラマ系？」 |
references/ai-character-stability.md |
「AIに演じさせると崩壊する？」「安定性を詳しく見たい」 |
references/ai-self-description-analyzer.md |
「蒸留結果に異常は？」「AIの自己記述を分析したい」 |
references/ai-user-conflict-predictor.md |
「ユーザーと衝突しやすい？」「摩擦リスクを知りたい」 |
references/character-role-analyzer.md |
「物語上の役割は何が向いている？」「主役向き？脇役向き？」 |
references/roleplay-burden-scorer.md |
「ユーザーへの心理的負荷は？」「RP負荷を測定して」 |
What ships with it
39 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.
- evals/evals.json 2.1 KB
- references/ai-character-6-type-checker--checklists.md 44 KB
- references/ai-character-6-type-checker.md 24 KB
- references/ai-character-fixer--modification-catalog.md 17 KB
- references/ai-character-fixer.md 23 KB
- references/ai-character-stability.md 28 KB
- references/ai-fault-mode-deflector.md 11 KB
- references/ai-self-description-analyzer.md 29 KB
- references/ai-user-conflict-predictor--collapse-prediction.md 6.9 KB
- references/ai-user-conflict-predictor.md 31 KB
- references/character-burnout-converter--conversion-details.md 26 KB
- references/character-burnout-converter.md 25 KB
- references/character-cultural-value-checker--checklists.md 56 KB
- references/character-cultural-value-checker--evaluation-details.md 111 KB
- references/character-cultural-value-checker.md 28 KB
- references/character-prompt-fortifier--output-guide.md 19 KB
- references/character-prompt-fortifier--theory-and-techniques.md 51 KB
- references/character-prompt-fortifier-for-gemini3--output-guide.md 19 KB
- references/character-prompt-fortifier-for-gemini3--theory-and-techniques.md 55 KB
- references/character-prompt-fortifier-for-gemini3.md 29 KB
- references/character-prompt-fortifier.md 28 KB
- references/character-role-analyzer.md 26 KB
- references/character-type-checker.md 18 KB
- references/gemini3-prompt-optimizer--anti-patterns.md 15 KB
- references/gemini3-prompt-optimizer--conversion-rules.md 16 KB
- references/gemini3-prompt-optimizer--templates.md 14 KB
- references/gemini3-prompt-optimizer.md 13 KB
- references/general-prompt-fortifier--output-guide.md 7.9 KB
- references/general-prompt-fortifier--theory-and-techniques.md 24 KB
- references/general-prompt-fortifier-for-gemini3--output-guide.md 10 KB
- references/general-prompt-fortifier-for-gemini3--theory-and-techniques.md 29 KB
- references/general-prompt-fortifier-for-gemini3.md 25 KB
- references/general-prompt-fortifier.md 17 KB
- references/roleplay-burden-scorer--checklists.md 17 KB
- references/roleplay-burden-scorer.md 28 KB
- references/romantization-chain-detector--chain-profiles.md 25 KB
- references/romantization-chain-detector--checklists.md 14 KB
- references/romantization-chain-detector.md 29 KB
- references/stable-character-creator.md 24 KB
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 · 166 lines · 193 tokens per session scan A 233e835a5050
ai-character-checker-all-in-one is a skill published in the GitHub repository gpsnmeajp/ai-character-checker (5 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 193 tokens to every session and 3,678 once invoked, about $0.0010 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…