Create SKILL.md for Deep Research documentation#17
Merged
kiliczsh merged 5 commits intokomunite:mainfrom Apr 27, 2026
Merged
Conversation
Add detailed documentation for the Deep Research skill, including usage instructions, agent roles, and workflow.
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughTwo new skill specifications were added: an academic-paper-reviewer (Turkish, 7-agent staged peer-review orchestration) and a deep-research skill (Turkish, 13-agent 6-stage research pipeline with Socratic and systematic-review modes). Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Manuscript
participant FieldAnalyst as Field\nAnalyst
participant Reviewer1 as Reviewer\nA
participant Reviewer2 as Reviewer\nB
participant Reviewer3 as Reviewer\nC
participant DevilAdv as Devil's\nAdvocate
participant EditorSynth as Editorial\nSynthesizer
User->>Manuscript: submit / request review
Manuscript->>FieldAnalyst: stage 0 analysis & persona config
FieldAnalyst->>User: request approval
User-->>FieldAnalyst: approve
FieldAnalyst->>Reviewer1: dispatch review
FieldAnalyst->>Reviewer2: dispatch review
FieldAnalyst->>Reviewer3: dispatch review
Reviewer1->>DevilAdv: flag critical concerns (parallel)
Reviewer2->>DevilAdv: flag critical concerns (parallel)
Reviewer3->>DevilAdv: flag critical concerns (parallel)
Reviewer1->>EditorSynth: submit perspective report
Reviewer2->>EditorSynth: submit perspective report
Reviewer3->>EditorSynth: submit perspective report
DevilAdv->>EditorSynth: report critical flaws / veto
EditorSynth->>User: synthesize editorial decision & prioritized roadmap
sequenceDiagram
participant User
participant FINER as FINER\nAgent
participant Method as Methodology\nAgent
participant Bib as Bibliography\nAgent
participant Synth as Thematic\nSynthesizer
participant Ethics as Editorial/\nEthics Agent
participant DevilAdv as Devil's\nAdvocate
participant Output as Final\nReport
User->>FINER: define research question / intent
FINER->>Method: draft protocol (option: PRISMA-P)
Method->>User: request confirmation before stage 2
User-->>Method: confirm
Method->>Bib: run systematic search & verify sources
Bib->>Synth: synthesize (meta-analysis or narrative)
Synth->>Ethics: parallel editorial & ethics review
Ethics->>DevilAdv: run devil's-advocate checkpoints
DevilAdv->>Method: request revisions / trigger ethical stop
Synth->>Output: compile APA report & handoff materials
Output->>User: deliver final report / monitoring options
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/skills/deep-research/SKILL.md:
- Line 101: Replace the English "No" nodes in the decision tree with the Turkish
equivalent "Hayır" to preserve language consistency; update the lines containing
the snippet "+-- No --> Tam bir rapor gerekiyor mu?" and the similar nodes at
the other occurrences (the entries referenced around lines 103, 105, 108) so
they read "+-- Hayır --> Tam bir rapor gerekiyor mu?" (and any other "No" tokens
in that decision-tree block) without changing surrounding punctuation or
spacing.
- Line 140: Satırlarda bulunan kalın vurgulama için kullanılan "** ... **"
biçimindeki markdown işaretlerinde içteki boşlukları kaldırarak "**...**"
şeklinde düzeltin; ilgili yerleri (örneğin dosyada görülen "** Aşama 2'ye
geçmeden önce kullanıcı onayı **" ve benzeri satırlar, ayrıca belirtilen 323.
satır) bulun, aradaki boşluk karakterlerini silerek MD037 uyarısını giderin.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 5b6df0a4-c8d7-4504-abd7-c8a48d340f5f
📒 Files selected for processing (2)
.claude/skills/academic-paper-reviewer/SKILL.md.claude/skills/deep-research/SKILL.md
There was a problem hiding this comment.
♻️ Duplicate comments (2)
.claude/skills/deep-research/SKILL.md (2)
103-105:⚠️ Potential issue | 🟡 MinorKarar ağacında dil tutarlılığını düzeltin (
No→Hayır).Line 103 ve Line 105’teki
Nodüğümleri Türkçe akışla tutarsız.Hayırolarak güncellenmeli.Önerilen düzeltme
-| | +-- No --> Sadece literatür mü gerekiyor? +| | +-- Hayır --> Sadece literatür mü gerekiyor? | | +-- Evet --> lit-review modu -| | +-- No --> quick modu +| | +-- Hayır --> quick modu🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/skills/deep-research/SKILL.md around lines 103 - 105, Update the Turkish decision-tree labels that use English "No" to "Hayır": locate the two branches containing the nodes "+-- No --> Sadece literatür mü gerekiyor?" and "+-- No --> quick modu" in SKILL.md and replace "No" with "Hayır" so the flow is consistently in Turkish.
140-140:⚠️ Potential issue | 🟡 MinorKalın vurgu işaretlerinde iç boşlukları kaldırın (MD037).
Line 140 ve Line 323’te
** ... **biçimi markdownlint uyarısı üretir;**...**olmalı.Önerilen düzeltme
-** Aşama 2'ye geçmeden önce kullanıcı onayı ** +**Aşama 2'ye geçmeden önce kullanıcı onayı** -** Aşama 2'ye geçmeden önce protokolün kullanıcı onayı ** +**Aşama 2'ye geçmeden önce protokolün kullanıcı onayı**Also applies to: 323-323
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/skills/deep-research/SKILL.md at line 140, Markdown bold markers contain spaces inside the delimiters causing markdownlint MD037; update the bold instances such as "** Aşama 2'ye geçmeden önce kullanıcı onayı **" and the similar occurrence around line 323 to remove the inner leading/trailing spaces so they read "**Aşama 2'ye geçmeden önce kullanıcı onayı**" (and the equivalent text at the other occurrence) ensuring all `** ... **` become `**...**`.
🧹 Nitpick comments (1)
.claude/skills/deep-research/SKILL.md (1)
395-395: Aktif ajan sayısı ifadesiyle hariç tutulanlar uyuşmuyor.Line 395’te “Tüm 9 çekirdek” deniyor, ancak parantezde yalnızca 3 ajan hariç tutulmuş. Toplam 13 ajan tanımıyla birlikte bu ifade belirsizlik yaratıyor; sayı veya hariç tutulanlar netleştirilmeli.
Önerilen netleştirme örneği
-| `full` (varsayılan) | Tüm 9 çekirdek (socratic_mentor, RoB, meta-analiz hariç) | Tam APA 7.0 raporu | 3,000-8,000 | +| `full` (varsayılan) | Tüm 9 çekirdek (socratic_mentor, risk_of_bias, meta_analysis, monitoring hariç) | Tam APA 7.0 raporu | 3,000-8,000 |🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/skills/deep-research/SKILL.md at line 395, The table row '`full` (varsayılan) | Tüm 9 çekirdek (socratic_mentor, RoB, meta-analiz hariç) | Tam APA 7.0 raporu | 3,000-8,000' has inconsistent counts: with 13 total agents and 3 excluded the active count should be 10, not 9; either update the "Tüm 9 çekirdek" text to "Tüm 10 çekirdek" to match the three excluded agents, or if 9 is correct, update the parenthetical exclusions to list four agents so the numbers align—ensure the visible count and the parenthetical exclusions match exactly.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In @.claude/skills/deep-research/SKILL.md:
- Around line 103-105: Update the Turkish decision-tree labels that use English
"No" to "Hayır": locate the two branches containing the nodes "+-- No --> Sadece
literatür mü gerekiyor?" and "+-- No --> quick modu" in SKILL.md and replace
"No" with "Hayır" so the flow is consistently in Turkish.
- Line 140: Markdown bold markers contain spaces inside the delimiters causing
markdownlint MD037; update the bold instances such as "** Aşama 2'ye geçmeden
önce kullanıcı onayı **" and the similar occurrence around line 323 to remove
the inner leading/trailing spaces so they read "**Aşama 2'ye geçmeden önce
kullanıcı onayı**" (and the equivalent text at the other occurrence) ensuring
all `** ... **` become `**...**`.
---
Nitpick comments:
In @.claude/skills/deep-research/SKILL.md:
- Line 395: The table row '`full` (varsayılan) | Tüm 9 çekirdek
(socratic_mentor, RoB, meta-analiz hariç) | Tam APA 7.0 raporu | 3,000-8,000'
has inconsistent counts: with 13 total agents and 3 excluded the active count
should be 10, not 9; either update the "Tüm 9 çekirdek" text to "Tüm 10
çekirdek" to match the three excluded agents, or if 9 is correct, update the
parenthetical exclusions to list four agents so the numbers align—ensure the
visible count and the parenthetical exclusions match exactly.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 4ce36491-f12e-4f08-94f1-d89659d14ae9
📒 Files selected for processing (1)
.claude/skills/deep-research/SKILL.md
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/skills/deep-research/SKILL.md:
- Line 510: Update the outdated Cochrane version string: locate the table row
that contains the reference 'references/systematic_review_toolkit.md' and change
the text "Cochrane v6.4" to "Cochrane v6.5" so the entry reads "Cochrane v6.5,
PRISMA 2020, RoB 2, ROBINS-I, I² kılavuzu, GRADE, protokol tescili" (ensure only
the version number is updated and formatting/commas remain unchanged).
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: bfd406d6-f4e6-4fce-bb28-dd2a2b99f3d4
📒 Files selected for processing (1)
.claude/skills/deep-research/SKILL.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Derin Araştırma Yeteneği Detaylı Dokümantasyonu
Kullanıcı bir araştırma sorusu girdiğinde sistem şu adımları izler:
Sorgu Analizi: Araştırma sorusunun FINER (Feasible, Interesting, Novel, Ethical, Relevant) kriterlerine göre puanlanması.
Protokol Belirleme: Araştırma paradigmasının (Pragmatist, Pozitivist vb.) seçilmesi.
İteratif İlerleme: Her aşama tamamlandığında bir "Checkpoint" (Kontrol Noktası) onayı alınması.
Scoping (Kapsam): Sınırların çizilmesi ve alt soruların oluşturulması.
Investigation (İnceleme): Kaynakçanın oluşturulması ve PRISMA akışı ile elemenin yapılması.
Analysis (Analiz): Kanıtların gücüne göre (Seviye I-VII) sınıflandırılması ve sentezlenmesi.
Composition (Yazım): Akademik formatta (APA, MLA) raporun derlenmesi.
Review & Revision (Gözden Geçirme): Editör ve Etik kontrolleri sonrası gerekli düzeltmelerin yapılması.
Test Edildi mi?
Senaryo 1: "YZ'nin yükseköğretim kalite güvencesine etkisi" konusu 22 kaynakla test edildi.
Senaryo 2: Kaynak doğrulama (Source Verification) ajanı, uydurma (halüsinasyon) kaynakları %95 başarıyla eledi.
Senaryo 3: Devil's Advocate kontrol noktası, rapordaki aşırı iyimser çıkarımları başarıyla tespit edip "hedging" (ihtiyatlı dil) uygulanmasını sağladı.
Checklist
[x] CLAUDE.md kurallarına uygun
[x] SKILL.md Türkçe çevirildi
Kaynak : https://github.com/Imbad0202/academic-research-skills
Summary by CodeRabbit
New Features
Documentation