Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/shiro-0x/hersonanpx agentmods add skills/shiro-0x/hersona/hersona-recommend-quizWrote 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/shiro-0x/hersona/hersona-recommend-quiz)<a href="https://agentmods.dev/skills/shiro-0x/hersona/hersona-recommend-quiz"><img src="https://agentmods.dev/badge/skills/shiro-0x/hersona/hersona-recommend-quiz/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/shiro-0x/hersona/hersona-recommend-quiz"><img src="https://agentmods.dev/badge/skills/shiro-0x/hersona/hersona-recommend-quiz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00175 | $0.04017 |
| Opus 5 | $0.00088 | $0.02008 |
| Sonnet 5 | $0.00035 | $0.00803 |
| Haiku 4.5 | $0.00017 | $0.00402 |
Grade A, and why
hersona-recommend-quiz scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
3. **9 個揃ったら** `hersona recommend --answers "..." --explain --json` を `subprocess.run` で実行 How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hersona-recommend-quiz
Overview
hersona 診断クイズを ユーザーとして体験する側 のスキル。hersona-recommend-engine(engine 開発側)の対となる skill。
やることは単純:
hersona/data/quiz/recommend_quiz.yamlから 9 問を読む- 1 問ずつ番号付き選択肢を提示し、番号を集める
key=index形式の文字列を組み立ててhersona recommend --answers "..." --explain --jsonを実行- 結果 JSON を Markdown 整形(Telegram / Discord / ターミナル全対応)で返す
LLM 主軸: 通常のチャットセッションでは、エージェントが SKILL.md を読んで Q1〜Q9 を表示し、ユーザーの番号を --answers に変換して CLI を叩く。
ヘルパー同梱: scripts/run_quiz.py を同梱し、TTY がない環境(cron / バッチ / CI / 自動テスト)ではこっちで stdin 経由に 9 問進行 → --answers 生成 → 結果整形まで一括実行できる。
When to Use
- 「hersona で recommend して」「診断クイズやりたい」「キャラ診断して」「属性推薦して」など、ユーザーがクイズを プレイしたい とき
- 結果(採用された属性 blend / 根拠 / 代替案 / サマリ / 推奨強度)を Markdown で見やすく 受け取りたいとき
- TTY がない自動化経路(cron / テスト)で recommend を使いたいとき →
scripts/run_quiz.py
Don't use for:
- クイズ YAML / WeightMagnitude / 閾値 / テストの 追加・編集(→
hersona-recommend-engine) - 新しい属性 YAML の 追加(→
hersona-attribute-development) - ペルソナをセッションにアタッチする作業(→
hersonaのattach/recommendセクション) - hersona リポジトリの戦略的・複数 PR 横断の作業(→
hersona-project-operations)
The 9 Questions (固定 ID)
クイズの本体は hersona/data/quiz/recommend_quiz.yaml にあり、9 問。各質問は次の ID で固定(= CLI --answers のキー)。ID を変えるとユーザーの既存スクリプトが壊れるので SKILL.md / YAML をまたいで常に同期すること。
| ID | 軸 | 質問 |
|---|---|---|
distance |
personality | 相手との距離感は? |
emotion |
personality | 感情の出し方は? |
speech |
speech | どんな話し方が好み? |
role |
archetype | 物語での立ち位置は? |
hobby |
hobby | 趣味・ライフスタイルで近いのは? |
appearance |
visual | 外見・雰囲気で近いのは? |
lifestyle |
lifestyle | 日常の過ごし方は? |
interaction |
interaction | 人と接するときは? |
cultural |
cultural | 文化的・知的なバックグラウンドは? |
選択肢の最新版は必ず YAML から読む(= 同梱禁止、コードと YAML の二重管理を避ける)。LLM フローの冒頭で read_file で YAML を読み込み、表示用テキストを生成する。
i18n (Phase 3〜):
prompt/labelは BASE=en。日本語は各質問・各選択肢のi18n: {ja: {prompt|label: "..."}}に入る(上表は日本語版 =i18n.ja.prompt)。 表示言語に合わせてi18n.<lang>を優先し、無ければ BASE(en) にフォールバックして出すこと。
LLM Flow (manual / interactive)
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.
- 11d ago First seen · 269 lines · 175 tokens per session scan A 4380affffb92
hersona-recommend-quiz is a skill published in the GitHub repository shiro-0x/hersona (51 stars, last pushed 14d ago), licensed MIT. It adds 175 tokens to every session and 4,017 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gleaner
A skill and command-line workflow for collecting academic literature from CNKI, Elsevier, and international open-access sources. It provides commands for checking access, preparing searches, listing results, and downloading papers.
bytesagain-license-picker
Open source license reference — SPDX identifiers, permissive vs copyleft comparison, license compatibility matrix, patent clauses, and compliance scanning tools.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…