cc-viewer 1.6.232 → 1.6.233

package/concepts/th/CustomUltraplanExpert.md

@@ -0,0 +1,165 @@
+# Custom UltraPlan Expert — คู่มือการเขียน
+
+## สองช่องป้อนข้อมูลทำหน้าที่อะไร
+
+- **ชื่อผู้เชี่ยวชาญ (Expert name)**: ป้ายที่แสดงบนปุ่มบทบาทในแถวตัวเลือก UltraPlan (สูงสุด 30 อักขระ) เป็นเพียงชื่อสำหรับแสดงผลและจะ**ไม่**ถูกส่งไปยัง Claude Code
+- **เนื้อหา prompt (Prompt body)**: คำสั่งบทบาทของคุณ ขณะส่ง cc-viewer จะ**ห่อหุ้มอัตโนมัติ**ด้วยแท็ก `<system-reminder>...</system-reminder>` พร้อมส่วนหัวขอบเขต `[SCOPED INSTRUCTION]` ดังนั้น**เขียนเฉพาะเนื้อหา**เท่านั้น — อย่าเพิ่มแท็ก `<system-reminder>` ด้วยตัวเอง
+
+---
+
+## เทมเพลตผู้เชี่ยวชาญหน้าตาเป็นอย่างไร?
+
+ผู้เชี่ยวชาญในตัวทุกตัว (Code Expert / Research Expert) เป็นบล็อก `<system-reminder>` ที่ฉีดเข้าไปในบริบทของ Claude Code โดยพื้นฐาน ผู้เชี่ยวชาญที่กำหนดเองของคุณก็ผ่าน pipeline เดียวกันทุกประการ นี่คือการแยกส่วนเทมเพลต **Research Expert**:
+
+```xml
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3
+interactions. Once the task is complete, these instructions should be gradually
+deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target
+audience, and deliverable format whenever the user's intent is ambiguous. Skip
+only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally
+detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore
+   various facets of the requirements:
+   - If necessary, deploy a preliminary investigator to conduct an initial
+     survey of industry-specific solutions using `webSearch`;
+   - If necessary, deploy a specialized investigator to research authoritative
+     sources—such as academic papers, news articles, and research reports—
+     using `webSearch`;
+   - Assign an agent to synthesize the target solution, while simultaneously
+     verifying the rigor and credibility of the gathered papers, news, and
+     research reports;
+   - If necessary, assign an agent to analyze competitor data to provide
+     supplementary analytical perspectives;
+   - If necessary, assign an agent to handle the implementation of a product
+     demo (generating outputs such as HTML, Markdown, etc.);
+   - If the task is sufficiently complex, you may assign additional teammates
+     to the roles defined above, or introduce other specialized roles; you are
+     permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive,
+   step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these
+   agents shall scrutinize the plan from multiple roles and perspectives to
+   identify any omitted steps and to propose reasonable additions or
+   optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke
+   `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+   - If Approved: Proceed to execute the plan within this current session.
+   - If Rejected: Revise the plan based on the provided feedback, and then
+     invoke `ExitPlanMode` once again.
+   - If an Error Occurs: Do *not* follow the suggestions; prompt the user for
+     further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact
+  changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an
+  appropriate location and notify the user.
+</system-reminder>
+```
+
+---
+
+## การวิเคราะห์ทีละส่วน
+
+### 1. ส่วนหัวขอบเขต `[SCOPED INSTRUCTION]` (ตัวห่อหุ้ม — สร้างอัตโนมัติ)
+> The following instructions are intended for the next 1–3 interactions...
+
+นี่บอก Claude Code ว่า: **คำสั่งเหล่านี้ใช้งานได้เฉพาะในการสนทนา 1–3 รอบถัดไป**เท่านั้น จากนั้นจะค่อยๆ จางหาย ป้องกันไม่ให้ "บุคลิกผู้เชี่ยวชาญ" รั่วไหลเข้าสู่บทสนทนาที่ไม่เกี่ยวข้องในภายหลัง
+
+**บรรทัดนี้สร้างโดย cc-viewer อัตโนมัติ คุณไม่จำเป็นต้องเขียน**
+
+### 2. คำจำกัดความงานเริ่มต้น (**นี่คือสิ่งที่คุณควรเขียนใหม่**)
+> Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+นี่คือ "ประธาน-กริยา-กรรม" ของเทมเพลตทั้งหมด: **บอก Claude Code ถึงท่าทีและเป้าหมาย** ค่าเริ่มต้น "การสำรวจหลายเอเจนต์ + แผนการนำไปใช้" เหมาะกับงานด้าน**วิศวกรรมซอฟต์แวร์ / การวางแผน**ดี แต่ดูแปลกสำหรับโดเมนอื่นๆ จำนวนมาก (การตรวจทานเนื้อหา การวิเคราะห์ข้อมูล การเขียนคำโฆษณา การวิจัยตลาด การตรวจสอบการปฏิบัติตามข้อกำหนด...)
+
+**เราขอแนะนำอย่างยิ่งให้เขียนบรรทัดนี้ใหม่ตามวัตถุประสงค์ของคุณ** เช่น:
+
+- **ผู้ตรวจทานเนื้อหา**: "You are a senior content reviewer specializing in {domain}. Your goal is to identify factual inaccuracies, tone inconsistencies, and structural weaknesses in the provided material."
+- **นักวิเคราะห์การแข่งขัน**: "Conduct a rigorous competitive analysis for {product category}. Produce a comparison matrix, positioning insights, and strategic recommendations."
+- **นักเขียนคำโฆษณา**: "Generate multiple creative copy variants for {scenario}, each with distinct positioning, tone, and call-to-action strategy."
+
+### 3. ขั้นตอนกระบวนการทำงาน (1–5 รายการ — **ตัดทอนหรือขยายตามความซับซ้อน**)
+
+Research Expert มี 5 ขั้นตอน: **สำรวจ → สังเคราะห์ → ตรวจทาน → ส่งแผน → ดำเนินการ** ซึ่งบังคับใช้ "หลายเอเจนต์ขนาน + การตรวจทานข้าม + การอนุมัติแผน" — ความเข้มงวดสามชั้น เหมาะสำหรับงานที่มีเดิมพันสูง/ขอบเขตกว้าง แต่**มากเกินไปสำหรับงานเบาๆ**
+
+- **งานง่าย** (การค้นหาเดี่ยว / แก้ไขเล็กน้อย): ตัดการกระจายงานหลายเอเจนต์และการตรวจทานออก เพียง "ผลิตคำตอบ" ในขั้นตอนเดียว
+- **งานปานกลาง**: เก็บ "สำรวจ → สังเคราะห์ → ตรวจทาน" ไว้ ตัดการเต้น ExitPlanMode ออก ส่งมอบผลโดยตรง
+- **งานซับซ้อนต้นทุนสูง** (การ refactor ขนาดใหญ่ การเปรียบเทียบหลายตัวเลือก การวิจัยข้ามโดเมน): เก็บทั้ง 5 ขั้นตอน อาจเพิ่มขั้นตอน "โมเดลความเสี่ยง" หรือ "เมทริกซ์เปรียบเทียบตัวเลือก"
+
+### 4. บทบาทย่อยในขั้นตอนที่ 1 (**ปรับแต่งตามโดเมนของคุณ**)
+
+Research Expert ระบุ 6 บทบาทที่เป็นไปได้ (ผู้สำรวจอุตสาหกรรม นักวิจัยวิชาการ ผู้สังเคราะห์ + ผู้ตรวจสอบข้อเท็จจริง นักวิเคราะห์คู่แข่ง ผู้สร้าง demo ช่องสำหรับขยาย) **เขียนรายการนี้ใหม่ตามสถานการณ์ของคุณ**:
+
+- **การเขียน**: "source collector + style analyst + fact checker"
+- **การวิเคราะห์ข้อมูล**: "data-cleaning agent + statistical modeling agent + visualization agent"
+- **การตรวจสอบโค้ด**: "static-analysis agent + dependency-chain auditor + threat modeler"
+
+### 5. รายการตรวจสอบผลลัพธ์ขั้นสุดท้าย (**สอดคล้องกับความต้องการจริงของคุณ**)
+
+> Your final plan must include the following elements: ...
+
+เทมเพลตเดิมระบุ 6 องค์ประกอบของ "แผนการนำไปใช้" ผลลัพธ์ของคุณอาจเป็นสิ่งอื่นที่แตกต่างไปโดยสิ้นเชิง:
+
+- **รายงานวิจัย** → "Executive summary / Methodology / Key findings / Limitations / Action recommendations"
+- **รายงานการตรวจทาน** → "Issue list / Severity rating / Fix suggestions / Before-after examples"
+- **เมทริกซ์เปรียบเทียบ** → "Dimension definitions / Scoring rubric / Conclusions / Recommendation rationale"
+
+---
+
+## เคล็ดลับการเขียน (TL;DR)
+
+1. **เก็บตัวห่อหุ้มไว้**: บรรทัด `<system-reminder>` + `[SCOPED INSTRUCTION]` ถูกเพิ่มโดย cc-viewer — อย่าเขียนซ้ำ
+2. **เขียนประโยคเปิดใหม่**: ระบุบทบาท เป้าหมาย และรูปแบบผลลัพธ์ในบรรทัดเดียว
+3. **ปรับเปลี่ยนกระบวนการทำงาน**: 1–2 ขั้นตอนสำหรับงานเบาๆ ใช้วงรอบ 5 ขั้นตอนเต็มเฉพาะงานซับซ้อนเท่านั้น
+4. **เขียนบทบาทย่อยในขั้นตอนที่ 1 ใหม่**: ค่าเริ่มต้น (เอกสารวิชาการ / คู่แข่ง / demo) อาจไม่ใช่สิ่งที่คุณต้องการ
+5. **"รายการตรวจสอบผลลัพธ์" สุดท้ายคือมาตรฐานคุณภาพของคุณ**: ระบุโครงสร้างผลลัพธ์ออกมา — Claude Code จะปฏิบัติตามอย่างเคร่งครัด
+
+---
+
+## ตัวอย่างที่ปรับโครงสร้างใหม่: Competitive Analyst
+
+```
+You are a senior competitive intelligence analyst for {industry}. Your goal is to
+produce a decision-grade competitive landscape report for the product "{our product}".
+
+Instructions:
+1. Use the Agent tool to dispatch 3 parallel investigators:
+   - Market landscape agent: map the top 5–8 competitors with core positioning
+   - Feature matrix agent: compile a feature-by-feature comparison using
+     publicly available sources (webSearch)
+   - Pricing & GTM agent: analyze pricing models, distribution channels, and
+     go-to-market motions
+
+2. Synthesize the three streams into a unified competitive report.
+
+3. Dispatch one review agent to stress-test the report: challenge any
+   assumption lacking a cited source, flag outdated data (>12 months), and
+   propose one "non-obvious" insight.
+
+4. Deliver the final report with the following sections:
+   - TL;DR (3 bullets)
+   - Competitor positioning map
+   - Feature matrix (markdown table)
+   - Pricing & GTM table
+   - Top 3 strategic implications for our product
+   - Caveats & data gaps
+```
+
+เทียบกับ Research Expert ดั้งเดิม: ตัดเหลือ 4 ขั้นตอน บทบาทย่อยลดจาก 6 เหลือ 3 รายการผลลัพธ์ถูกเขียนใหม่ทั้งหมดเป็น "ส่วนของรายงาน"

package/concepts/th/UltraPlan.md

@@ -53,3 +53,104 @@ UltraPlan นำเสนอบทบาทผู้เชี่ยวชาญ
 4. สังเคราะห์ข้อค้นพบทั้งหมดเป็นแผนการดำเนินงานที่ครอบคลุม
 5. ส่งเอเจนต์ตรวจสอบหลายตัวเพื่อพิจารณาแผนจากบทบาทและมุมมองที่หลากหลาย
 6. ดำเนินการตามแผนเมื่อได้รับอนุมัติ
+
+---
+
+## Raw Templates
+
+Below are the two raw prompt templates UltraPlan actually sends to Claude Code (see `src/utils/ultraplanTemplates.js`):
+
+### Code Expert (codeExpert)
+
+<textarea readonly><system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify user intent whenever the request is ambiguous (target element, interaction style, scope of platforms, etc.). Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate a highly detailed implementation plan.
+
+Instructions:
+1. Use the `Agent` tool to spawn parallel agents that simultaneously explore different aspects of the codebase:
+- If necessary, assign a preliminary researcher to use the `webSearch` tool to first investigate cutting-edge solutions in the relevant industry domain;
+- One agent responsible for understanding the relevant existing code and architecture;
+- One agent responsible for identifying all files that need to be modified;
+- One agent responsible for identifying potential risks, edge cases, and dependencies;
+- You may add other roles or deploy additional agents beyond the three listed above; the maximum number of concurrently dispatched agents is 5.
+
+2. Synthesize the findings from all agents into a detailed, step-by-step implementation plan.
+
+3. Use the `Agent` tool to spawn 2-3 review agents that examine the plan from different perspectives, checking for missing steps, potential risks, or corresponding mitigation strategies.
+
+4. Integrate the feedback gathered during the review process, then call `ExitPlanMode` to submit your final plan.
+
+5. Once `ExitPlanMode` returns a result:
+- If approved: proceed to execute the plan within this session.
+- If rejected: revise the plan based on the feedback provided and call `ExitPlanMode` again.
+- If an error occurs (including receiving a "Not in Plan Mode" message): do **not** follow the suggestions provided in the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the implementation strategy;
+- An ordered list of files to be created or modified, with precise details of the required changes for each file;
+- A step-by-step execution sequence;
+- Testing and validation procedures;
+- Potential risks and their corresponding mitigation strategies;
+
+6. After the final plan has been successfully executed:
+First run `git diff --quiet && git diff --cached --quiet` (or equivalent) to detect whether the working tree actually has non-trivial changes; if there are no real changes (or only whitespace/comment-only edits), skip the UltraReview step.
+Otherwise, if the project is managed with Git:
+Initiate a team (`TeamCreate`), dynamically allocating the number of teammates based on task complexity (5 is recommended);
+Task: Conduct a Code Review of the current git changes from multiple perspectives;
+Pre-requisites:
+- The git repository may be located in a subdirectory of the current directory; prefer `git rev-parse --show-toplevel` (fall back to recursive lookup) before proceeding;
+- In the case of multiple repositories, tasks may be executed separately;
+The team's goal is to analyze the current Git change log and validate each modification from different perspectives, specifically including:
+- Whether requirements/objectives have been met and functionality is complete;
+- Whether newly added code introduces side effects, breaks existing functionality, or poses potential risks;
+- Code quality: naming, readability, complexity, technical debt, maintainability;
+- Testing and documentation: whether there is adequate test coverage, and whether critical logic has necessary comments or documentation;
+- Dependencies and compatibility: whether new dependencies or version compatibility issues have been introduced;
+Workflow:
+- Each teammate, according to their own role, covers the review dimensions one by one and independently outputs a report;
+- After consolidating the reports, perform a cross-review to identify conflicts or shared concerns;
+- Distill specific, actionable modification suggestions and annotate them with priority levels (P0/P1/P2/P3);
+- Upon completion, adopt P0 items, and selectively adopt P1 items when they are concrete and low-risk; defer P2/P3 to backlog;
+- After execution is complete, close the team (`TeamDelete`);
+</system-reminder></textarea>
+
+### Research Expert (researchExpert)
+
+<textarea readonly><system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3 interactions. Once the task is complete, these instructions should be gradually deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target audience, and deliverable format whenever the user's intent is ambiguous. Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore various facets of the requirements:
+- If necessary, deploy a preliminary investigator to conduct an initial survey of industry-specific solutions using `webSearch`;
+- If necessary, deploy a specialized investigator to research authoritative sources—such as academic papers, news articles, and research reports—using `webSearch`;
+- Assign an agent to synthesize the target solution, while simultaneously verifying the rigor and credibility of the gathered papers, news, and research reports;
+- If necessary, assign an agent to analyze competitor data to provide supplementary analytical perspectives;
+- If necessary, assign an agent to handle the implementation of a product demo (generating outputs such as HTML, Markdown, etc.);
+- If the task is sufficiently complex, you may assign additional teammates to the roles defined above, or introduce other specialized roles; you are permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive, step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these agents shall scrutinize the plan from multiple roles and perspectives to identify any omitted steps and to propose reasonable additions or optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+- If Approved: Proceed to execute the plan within this current session.
+- If Rejected: Revise the plan based on the provided feedback, and then invoke `ExitPlanMode` once again.
+- If an Error Occurs (including the message "Not in Plan Mode"): Do *not* follow the suggestions provided by the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an appropriate location and notify the user.
+</system-reminder></textarea>

package/concepts/tr/CustomUltraplanExpert.md

@@ -0,0 +1,165 @@
+# Custom UltraPlan Expert — Yazım Kılavuzu
+
+## İki giriş alanı ne işe yarar
+
+- **Uzman adı**: UltraPlan varyant satırındaki rol düğmesinde gösterilen etiket (maks. 30 karakter). Yalnızca bir görüntü adıdır ve **asla** Claude Code'a gönderilmez.
+- **Prompt gövdesi**: rol talimatınız. Gönderim sırasında cc-viewer **otomatik olarak** bunu `[SCOPED INSTRUCTION]` kapsam başlığıyla birlikte `<system-reminder>...</system-reminder>` etiketleriyle sarmalar. Bu yüzden **yalnızca gövdeyi yazın** — `<system-reminder>` etiketlerini kendiniz eklemeyin.
+
+---
+
+## Uzman şablonu nasıl görünür?
+
+Yerleşik her uzman (Code Expert / Research Expert) esasen Claude Code bağlamına enjekte edilen bir `<system-reminder>` bloğudur. Özel uzmanınız da tam olarak aynı pipeline üzerinden geçer. İşte **Research Expert** şablonunun ayrıştırılmış hali:
+
+```xml
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3
+interactions. Once the task is complete, these instructions should be gradually
+deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target
+audience, and deliverable format whenever the user's intent is ambiguous. Skip
+only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally
+detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore
+   various facets of the requirements:
+   - If necessary, deploy a preliminary investigator to conduct an initial
+     survey of industry-specific solutions using `webSearch`;
+   - If necessary, deploy a specialized investigator to research authoritative
+     sources—such as academic papers, news articles, and research reports—
+     using `webSearch`;
+   - Assign an agent to synthesize the target solution, while simultaneously
+     verifying the rigor and credibility of the gathered papers, news, and
+     research reports;
+   - If necessary, assign an agent to analyze competitor data to provide
+     supplementary analytical perspectives;
+   - If necessary, assign an agent to handle the implementation of a product
+     demo (generating outputs such as HTML, Markdown, etc.);
+   - If the task is sufficiently complex, you may assign additional teammates
+     to the roles defined above, or introduce other specialized roles; you are
+     permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive,
+   step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these
+   agents shall scrutinize the plan from multiple roles and perspectives to
+   identify any omitted steps and to propose reasonable additions or
+   optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke
+   `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+   - If Approved: Proceed to execute the plan within this current session.
+   - If Rejected: Revise the plan based on the provided feedback, and then
+     invoke `ExitPlanMode` once again.
+   - If an Error Occurs: Do *not* follow the suggestions; prompt the user for
+     further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact
+  changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an
+  appropriate location and notify the user.
+</system-reminder>
+```
+
+---
+
+## Bölüm bölüm analiz
+
+### 1. `[SCOPED INSTRUCTION]` kapsam başlığı (sarmalayıcı — otomatik üretilir)
+> The following instructions are intended for the next 1–3 interactions...
+
+Bu, Claude Code'a şunu söyler: **bu talimatlar yalnızca sonraki 1–3 turda etkindir**, sonra silinir. "Uzman kişiliğinin" sonradan ilgisiz konuşmalara sızmasını önler.
+
+**Bu satır cc-viewer tarafından otomatik üretilir. Sizin yazmanıza gerek yok.**
+
+### 2. Açılış görev tanımı (**yeniden yazmanız gereken kısım budur**)
+> Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+Bu, tüm şablonun "özne-yüklem-nesne"sidir: **Claude Code'a tutum ve hedefi söyler**. Varsayılan "çoklu ajan keşfi + uygulama planı" **yazılım mühendisliği / planlama** görevlerine iyi uyar, ancak diğer birçok alan için tuhaf görünür (içerik incelemesi, veri analizi, metin yazarlığı, pazar araştırması, uyumluluk denetimi…).
+
+**Bu satırı hedefinize göre yeniden yazmanızı şiddetle öneririz**, örneğin:
+
+- **İçerik denetçisi**: "You are a senior content reviewer specializing in {domain}. Your goal is to identify factual inaccuracies, tone inconsistencies, and structural weaknesses in the provided material."
+- **Rekabet analisti**: "Conduct a rigorous competitive analysis for {product category}. Produce a comparison matrix, positioning insights, and strategic recommendations."
+- **Metin yazarı**: "Generate multiple creative copy variants for {scenario}, each with distinct positioning, tone, and call-to-action strategy."
+
+### 3. İş akışı adımları (1–5 öğe — **karmaşıklığa göre kısaltın veya genişletin**)
+
+Research Expert'in 5 adımı vardır: **keşif → sentez → inceleme → plan gönderme → yürütme**. Bu, "paralel çoklu ajan + çapraz inceleme + plan onayı" — üç katman titizlik dayatır; yüksek riskli/geniş kapsamlı görevler için uygundur ancak **hafif görevler için aşırıdır**.
+
+- **Basit görev** (tek arama / küçük düzeltme): çoklu ajan dağıtımını ve incelemeyi atlayın; tek adımda "yanıtı üretin".
+- **Orta görev**: "keşif → sentez → inceleme"yi koruyun; ExitPlanMode dansını atlayın; sonucu doğrudan teslim edin.
+- **Karmaşık, yüksek maliyetli görev** (büyük refactor, çoklu seçenek karşılaştırması, alanlar arası araştırma): 5 adımın hepsini koruyun, muhtemelen bir "risk modeli" veya "seçenek karşılaştırma matrisi" adımı ekleyin.
+
+### 4. Adım 1'deki alt roller (**alanınıza göre uyarlayın**)
+
+Research Expert 6 potansiyel rolü listeler (sektör keşifçisi, akademik araştırmacı, sentezleyici + olgu denetleyici, rakip analisti, demo üreticisi, genişletilebilirlik yuvası). **Bu listeyi senaryonuza göre yeniden yazın**:
+
+- **Yazma**: "source collector + style analyst + fact checker"
+- **Veri analizi**: "data-cleaning agent + statistical modeling agent + visualization agent"
+- **Kod denetimi**: "static-analysis agent + dependency-chain auditor + threat modeler"
+
+### 5. Nihai teslimat kontrol listesi (**gerçek ihtiyacınızla hizalayın**)
+
+> Your final plan must include the following elements: ...
+
+Orijinal şablon "uygulama planının" 6 öğesini listeler. Teslimatınız tamamen başka bir şey olabilir:
+
+- **Araştırma raporu** → "Executive summary / Methodology / Key findings / Limitations / Action recommendations"
+- **İnceleme raporu** → "Issue list / Severity rating / Fix suggestions / Before-after examples"
+- **Karşılaştırma matrisi** → "Dimension definitions / Scoring rubric / Conclusions / Recommendation rationale"
+
+---
+
+## Yazım ipuçları (TL;DR)
+
+1. **Sarmalayıcıyı koruyun**: `<system-reminder>` + `[SCOPED INSTRUCTION]` satırı cc-viewer tarafından eklenir — tekrarlamayın.
+2. **Açılış cümlesini yeniden yazın**: rol, hedef ve çıktı formatını tek satırda belirtin.
+3. **İş akışını esnetin**: hafif görevler için 1–2 adım, tam 5 adımlı döngü yalnızca karmaşık olanlar için.
+4. **Adım 1 alt rollerini yeniden yazın**: varsayılanlar (akademik makaleler / rakipler / demo) muhtemelen istediğiniz şey değildir.
+5. **Nihai "teslimat kontrol listesi" kalite çıtanızdır**: çıktı yapısını detaylı belirtin — Claude Code buna katı şekilde uyacaktır.
+
+---
+
+## Yeniden düzenlenmiş örnek: Competitive Analyst
+
+```
+You are a senior competitive intelligence analyst for {industry}. Your goal is to
+produce a decision-grade competitive landscape report for the product "{our product}".
+
+Instructions:
+1. Use the Agent tool to dispatch 3 parallel investigators:
+   - Market landscape agent: map the top 5–8 competitors with core positioning
+   - Feature matrix agent: compile a feature-by-feature comparison using
+     publicly available sources (webSearch)
+   - Pricing & GTM agent: analyze pricing models, distribution channels, and
+     go-to-market motions
+
+2. Synthesize the three streams into a unified competitive report.
+
+3. Dispatch one review agent to stress-test the report: challenge any
+   assumption lacking a cited source, flag outdated data (>12 months), and
+   propose one "non-obvious" insight.
+
+4. Deliver the final report with the following sections:
+   - TL;DR (3 bullets)
+   - Competitor positioning map
+   - Feature matrix (markdown table)
+   - Pricing & GTM table
+   - Top 3 strategic implications for our product
+   - Caveats & data gaps
+```
+
+Orijinal Research Expert ile karşılaştırıldığında: 4 adıma kısaltıldı, alt roller 6'dan 3'e düşürüldü, teslimat listesi tamamen "rapor bölümleri" olarak yeniden yazıldı.

package/concepts/tr/UltraPlan.md

@@ -53,3 +53,104 @@ Araştırma ve analiz görevleri için tasarlanmış çoklu ajan iş akışı:
 4. Tüm bulguları kapsamlı bir uygulama planında sentezleme
 5. Planı farklı roller ve perspektiflerden incelemek için birden fazla inceleme ajanı dağıtma
 6. Onaylandıktan sonra planı yürütme
+
+---
+
+## Raw Templates
+
+Below are the two raw prompt templates UltraPlan actually sends to Claude Code (see `src/utils/ultraplanTemplates.js`):
+
+### Code Expert (codeExpert)
+
+<textarea readonly><system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify user intent whenever the request is ambiguous (target element, interaction style, scope of platforms, etc.). Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate a highly detailed implementation plan.
+
+Instructions:
+1. Use the `Agent` tool to spawn parallel agents that simultaneously explore different aspects of the codebase:
+- If necessary, assign a preliminary researcher to use the `webSearch` tool to first investigate cutting-edge solutions in the relevant industry domain;
+- One agent responsible for understanding the relevant existing code and architecture;
+- One agent responsible for identifying all files that need to be modified;
+- One agent responsible for identifying potential risks, edge cases, and dependencies;
+- You may add other roles or deploy additional agents beyond the three listed above; the maximum number of concurrently dispatched agents is 5.
+
+2. Synthesize the findings from all agents into a detailed, step-by-step implementation plan.
+
+3. Use the `Agent` tool to spawn 2-3 review agents that examine the plan from different perspectives, checking for missing steps, potential risks, or corresponding mitigation strategies.
+
+4. Integrate the feedback gathered during the review process, then call `ExitPlanMode` to submit your final plan.
+
+5. Once `ExitPlanMode` returns a result:
+- If approved: proceed to execute the plan within this session.
+- If rejected: revise the plan based on the feedback provided and call `ExitPlanMode` again.
+- If an error occurs (including receiving a "Not in Plan Mode" message): do **not** follow the suggestions provided in the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the implementation strategy;
+- An ordered list of files to be created or modified, with precise details of the required changes for each file;
+- A step-by-step execution sequence;
+- Testing and validation procedures;
+- Potential risks and their corresponding mitigation strategies;
+
+6. After the final plan has been successfully executed:
+First run `git diff --quiet && git diff --cached --quiet` (or equivalent) to detect whether the working tree actually has non-trivial changes; if there are no real changes (or only whitespace/comment-only edits), skip the UltraReview step.
+Otherwise, if the project is managed with Git:
+Initiate a team (`TeamCreate`), dynamically allocating the number of teammates based on task complexity (5 is recommended);
+Task: Conduct a Code Review of the current git changes from multiple perspectives;
+Pre-requisites:
+- The git repository may be located in a subdirectory of the current directory; prefer `git rev-parse --show-toplevel` (fall back to recursive lookup) before proceeding;
+- In the case of multiple repositories, tasks may be executed separately;
+The team's goal is to analyze the current Git change log and validate each modification from different perspectives, specifically including:
+- Whether requirements/objectives have been met and functionality is complete;
+- Whether newly added code introduces side effects, breaks existing functionality, or poses potential risks;
+- Code quality: naming, readability, complexity, technical debt, maintainability;
+- Testing and documentation: whether there is adequate test coverage, and whether critical logic has necessary comments or documentation;
+- Dependencies and compatibility: whether new dependencies or version compatibility issues have been introduced;
+Workflow:
+- Each teammate, according to their own role, covers the review dimensions one by one and independently outputs a report;
+- After consolidating the reports, perform a cross-review to identify conflicts or shared concerns;
+- Distill specific, actionable modification suggestions and annotate them with priority levels (P0/P1/P2/P3);
+- Upon completion, adopt P0 items, and selectively adopt P1 items when they are concrete and low-risk; defer P2/P3 to backlog;
+- After execution is complete, close the team (`TeamDelete`);
+</system-reminder></textarea>
+
+### Research Expert (researchExpert)
+
+<textarea readonly><system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3 interactions. Once the task is complete, these instructions should be gradually deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target audience, and deliverable format whenever the user's intent is ambiguous. Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore various facets of the requirements:
+- If necessary, deploy a preliminary investigator to conduct an initial survey of industry-specific solutions using `webSearch`;
+- If necessary, deploy a specialized investigator to research authoritative sources—such as academic papers, news articles, and research reports—using `webSearch`;
+- Assign an agent to synthesize the target solution, while simultaneously verifying the rigor and credibility of the gathered papers, news, and research reports;
+- If necessary, assign an agent to analyze competitor data to provide supplementary analytical perspectives;
+- If necessary, assign an agent to handle the implementation of a product demo (generating outputs such as HTML, Markdown, etc.);
+- If the task is sufficiently complex, you may assign additional teammates to the roles defined above, or introduce other specialized roles; you are permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive, step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these agents shall scrutinize the plan from multiple roles and perspectives to identify any omitted steps and to propose reasonable additions or optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+- If Approved: Proceed to execute the plan within this current session.
+- If Rejected: Revise the plan based on the provided feedback, and then invoke `ExitPlanMode` once again.
+- If an Error Occurs (including the message "Not in Plan Mode"): Do *not* follow the suggestions provided by the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an appropriate location and notify the user.
+</system-reminder></textarea>