{"eval":{"version":"openagentskill-skill-eval-v1","slug":"coji-natural-japanese","name":"natural-japanese","generated_at":"2026-09-06T23:23:34.548Z","task_input":"Evaluate natural-japanese before installing it in an AI agent workflow","status":"review","score":77,"risk_level":"medium","decision":{"recommendation":"manual_review","reason":"Require human approval before installing into a real workspace.","auto_install_allowed":false,"policy":"review","human_review_required":true},"task_fit":{"score":84,"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"install":{"command":"npx skills add coji/natural-japanese --skill natural-japanese","ready":true,"policy":"review","safety_label":"Review before install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add coji-natural-japanese"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"natural-japanese\" agent skill from https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"coji-natural-japanese\",\"task\":\"Install natural-japanese\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"natural-japanese\" as a Claude Code skill from https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"coji-natural-japanese\",\"task\":\"Install natural-japanese\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"natural-japanese\" from https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"coji-natural-japanese\",\"task\":\"Install natural-japanese\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}]},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","evidence":{"stars":"967 GitHub stars","repoActivity":"967 stars, 20 forks","lastPushed":"2d since push","license":"MIT","repository":"https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese","install":"npx skills add coji/natural-japanese --skill natural-japanese","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"}},"audit":{"score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration.","The skill is highly detailed and complex, which might be overwhelming for some users, but the quick/full mode distinction helps manage complexity.","Quality score needs review"]},"safety_gate":{"score":67,"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","blocked":false,"permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration."]},"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":84,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate natural-japanese before installing it in an AI agent workflow","automation","Browser automation workflows; Claude Code teams; teams that value GitHub adoption signals"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add coji/natural-japanese --skill natural-japanese"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add coji/natural-japanese --skill natural-japanese"]},{"id":"trust_score","label":"Trust score","status":"warn","score":76,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","967 GitHub stars","MIT"]},{"id":"audit_score","label":"Audit score","status":"pass","score":83,"required_for_auto_install":true,"detail":"Safe to try","evidence":["The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration."]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":67,"required_for_auto_install":true,"detail":"Usable candidate, but the agent should surface permission and audit notes before installation.","evidence":["Require human approval before installing into a real workspace.","The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration."]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":86,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT","evidence":["MIT"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":100,"required_for_auto_install":false,"detail":"2d since push","evidence":["2d since push"]},{"id":"permission_surface","label":"Permission surface","status":"pass","score":86,"required_for_auto_install":true,"detail":"filesystem or document access","evidence":["Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["bytedance-ui-tars-desktop","n8n-io-n8n","harry0703-moneyprinterturbo","arendst-tasmota"]}],"blockers":[],"warnings":["Trust score: Good trust signals with a few areas worth checking before rollout.","Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.","The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration.","The skill is highly detailed and complex, which might be overwhelming for some users, but the quick/full mode distinction helps manage complexity.","Quality score needs review"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration.","The skill is highly detailed and complex, which might be overwhelming for some users, but the quick/full mode distinction helps manage complexity.","Quality score needs review","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"alternatives":[{"slug":"bytedance-ui-tars-desktop","name":"UI-TARS Desktop","url":"https://www.openagentskill.com/skills/bytedance-ui-tars-desktop","stars":36958,"install_command":"npx skills add bytedance/UI-TARS-desktop","trust_score":85,"audit_score":90},{"slug":"n8n-io-n8n","name":"n8n","url":"https://www.openagentskill.com/skills/n8n-io-n8n","stars":194085,"install_command":"npx skills add n8n-io/n8n","trust_score":85,"audit_score":89},{"slug":"harry0703-moneyprinterturbo","name":"MoneyPrinterTurbo","url":"https://www.openagentskill.com/skills/harry0703-moneyprinterturbo","stars":88538,"install_command":"npx skills add harry0703/MoneyPrinterTurbo","trust_score":90,"audit_score":92},{"slug":"arendst-tasmota","name":"Tasmota","url":"https://www.openagentskill.com/skills/arendst-tasmota","stars":24730,"install_command":"npx skills add arendst/Tasmota","trust_score":92,"audit_score":94}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"coji-natural-japanese","name":"natural-japanese","description":"仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。","category":"automation","url":"https://www.openagentskill.com/skills/coji-natural-japanese","repository":"https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese","github_repo":"coji/natural-japanese"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add coji/natural-japanese --skill natural-japanese","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add coji-natural-japanese"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"natural-japanese\" agent skill from https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"coji-natural-japanese\",\"task\":\"Install natural-japanese\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"natural-japanese\" as a Claude Code skill from https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"coji-natural-japanese\",\"task\":\"Install natural-japanese\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"natural-japanese\" from https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われた/疑われた）、読みにくい・わかりにくい文章の改善依頼（語順がおかしい、一文が長い、何が言いたいか分からない、読点の位置がおかしい等）、note記事やブログ記事・エッセイの新規執筆（任意のテーマをゼロから書く・書き起こす依頼を含む）、既存文章のリライト・推敲、AI臭さの診断・採点（「この文章AIが書いた？」「AI臭さをスコアで出して」「どれくらいAIっぽいか判定して」という書き換えを伴わない依頼）、自分の文体を学ばせたい・プロファイル化したいという要望（過去の文章を読ませて自分らしく書いてほしいという依頼も含む）にも対応する。禁止語の除去、リズムの単調さ・段落構造の均質さ・英語統語の直訳調に加え、語順・読点・一文一義・主語述語の距離といった読みやすさの原則にも対応する。技術文書の章構成やMarkdownフォーマットの整形自体（一文一行化・引用ブロック・脚注記法など）は対象外——それは別スキルの領域であり、本スキルは文章の自然さ・読みやすさ・わかりやすさに特化する。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"coji-natural-japanese\",\"task\":\"Install natural-japanese\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/coji-natural-japanese/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/coji-natural-japanese"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"967 GitHub stars","repoActivity":"967 stars, 20 forks","lastPushed":"2d since push","license":"MIT","repository":"https://github.com/coji/natural-japanese/tree/main/skills/natural-japanese","install":"npx skills add coji/natural-japanese --skill natural-japanese","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["automation","agent-skill"],"known_risks":["The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration.","Quality score needs review"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration.","The skill is highly detailed and complex, which might be overwhelming for some users, but the quick/full mode distinction helps manage complexity.","Quality score needs review"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":77,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2d since push","risk":"Safe to try"},"alternative_skills":[{"slug":"bytedance-ui-tars-desktop","name":"UI-TARS Desktop","url":"https://www.openagentskill.com/skills/bytedance-ui-tars-desktop","stars":36958,"install_command":"npx skills add bytedance/UI-TARS-desktop","trust_score":85,"audit_score":90},{"slug":"n8n-io-n8n","name":"n8n","url":"https://www.openagentskill.com/skills/n8n-io-n8n","stars":194085,"install_command":"npx skills add n8n-io/n8n","trust_score":85,"audit_score":89},{"slug":"harry0703-moneyprinterturbo","name":"MoneyPrinterTurbo","url":"https://www.openagentskill.com/skills/harry0703-moneyprinterturbo","stars":88538,"install_command":"npx skills add harry0703/MoneyPrinterTurbo","trust_score":90,"audit_score":92},{"slug":"arendst-tasmota","name":"Tasmota","url":"https://www.openagentskill.com/skills/arendst-tasmota","stars":24730,"install_command":"npx skills add arendst/Tasmota","trust_score":92,"audit_score":94}],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill relies on external tools (uv, Python) and may download a ~1GB model for the 'exp' diagnostic mode, which requires user consent and could be a minor security consideration.","The skill is highly detailed and complex, which might be overwhelming for some users, but the quick/full mode distinction helps manage complexity.","Quality score needs review","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Evaluate natural-japanese before installing it in an AI agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 83/100 Safe to try","Safety: 67/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"coji-natural-japanese (natural-japanese)","install_command":"npx skills add coji/natural-japanese --skill natural-japanese","risk_summary":"Safe to try; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"coji-natural-japanese","task":"Evaluate natural-japanese before installing it in an AI agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/coji-natural-japanese","api":"https://www.openagentskill.com/api/agent/skills/coji-natural-japanese","audit":"https://www.openagentskill.com/skills/coji-natural-japanese/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=coji-natural-japanese&task=Evaluate%20natural-japanese%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20natural-japanese%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Evaluate%20natural-japanese%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/coji-natural-japanese/install","manifest":"https://www.openagentskill.com/api/registry/manifest/coji-natural-japanese"}},"endpoints":{"web":"https://www.openagentskill.com/skills/coji-natural-japanese","api":"https://www.openagentskill.com/api/agent/skills/coji-natural-japanese","eval":"https://www.openagentskill.com/api/agent/evals?slug=coji-natural-japanese","audit":"https://www.openagentskill.com/skills/coji-natural-japanese/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20natural-japanese%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium"}},"meta":{"endpoint":"/api/agent/evals","mode":"skill_eval","purpose":"Pre-install eval contract for a single skill. Agents should read this before installing a reusable skill.","generated_at":"2026-09-06T23:23:34.548Z"}}