[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77EH2ASM1ZY85FBG87SWZXF":3,"skill-same:01M77EH2ASM1ZY85FBG87SWZXF":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M77EH2ASM1ZY85FBG87SWZXF","litreview",null,"Academic literature orientation skill that searches papers via Consensus, builds a strategic search plan using PICO (default) or SPIDER \u002F Decomposition \u002F hybrid as fallbacks, and synthesizes findings into a formatted Word (.docx) research guide. Grill-me intake (research question specificity + framework hint + tentative depth) before the recon search; a second forcing checkpoint after Phase 2 confirms framework + sub-areas + depth before searches consume budget. Configurable depth (5\u002F10\u002F20 queries) controls coverage vs. speed. Output is a 'launching pad' — an orientation guide that lets a researcher dive in confidently, not a finished review. Use when the user starts literature-oriented research (e.g., 'litreview on [topic]', 'literature review on [topic]', 'I'm starting a literature review on X', 'I'm writing a paper on X', 'help me research X', 'I'm doing research on X', 'can you help me research X'). Do NOT use for single one-off paper searches wanting a quick list — that's a plain Consensus search.","haresh-sai06\u002FSapSynk-AI","haresh-sai06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180730984?v=4","01M75NJVH4TXYCE7FW7YVMSVFF","Haresh Sainaath S","01M75NJVHTCW1Z2P6MNCYGNSTJ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__litreview-2\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: litreview\ndescription: \"Academic literature orientation skill that searches papers via Consensus, builds a strategic search plan using PICO (default) or SPIDER \u002F Decomposition \u002F hybrid as fallbacks, and synthesizes findings into a formatted Word (.docx) research guide. Grill-me intake (research question specificity + framework hint + tentative depth) before the recon search; a second forcing checkpoint after Phase 2 confirms framework + sub-areas + depth before searches consume budget. Configurable depth (5\u002F10\u002F20 queries) controls coverage vs. speed. Output is a 'launching pad' — an orientation guide that lets a researcher dive in confidently, not a finished review. Use when the user starts literature-oriented research (e.g., 'litreview on [topic]', 'literature review on [topic]', 'I'm starting a literature review on X', 'I'm writing a paper on X', 'help me research X', 'I'm doing research on X', 'can you help me research X'). Do NOT use for single one-off paper searches wanting a quick list — that's a plain Consensus search.\"\nlicense: MIT\nmetadata:\n  source_spec: \"megaprompts\u002F09-litreview-megaprompt.md\"\n  build_pattern: \"Path B (direct conversion)\"\n  research_pack_convention: \"Agent Integrity Rules verbatim per PR #657 audit; sibling of pulse\"\n  version: 1.0.0\n---\n\n# Litreview — Academic Literature Orientation\n\n> **Portability:** Requires a Consensus MCP connection, Node.js with `docx` package for document generation, and (in CLI) `bash_tool`. Works in Claude Code CLI natively. In Claude.ai with Consensus MCP + Code Execution, the workflow is supported.\n\nProduce a **launching pad** — not a finished literature review, but an orientation document that gives a researcher entering an unfamiliar field everything they need to start reading and searching with confidence. Think: what a generous colleague who knows the field would tell you over coffee.\n\n## Agent Integrity Rules (Research-Pack Convention)\n\nInherited from the research-pack convention; locked verbatim per PR #657's cross-skill consistency audit.\n\n- **Source discipline.** Only cite Consensus-returned papers from THIS session. Training knowledge labeled `[Not from Consensus — model knowledge]` and excluded from cited count. Sparse results stated explicitly, never silently filled.\n- **Counting discipline.** Three numbers tracked: searches executed \u002F unique papers received (deduplicated) \u002F papers cited. Every cited paper has a retrievable Consensus URL from this session. Use `scripts\u002Fcitation_tracker.py` for deterministic counts.\n- **Tool constraints.** Consensus per-query cap depends on plan tier. **Detect at first search**, report at checkpoint. Rate limit is **1 query\u002Fsec** — sequential execution mandatory.\n- **Retry policy.** On failure → wait 3s → retry once → log. After 3 consecutive failures: stop, alert user, share what was collected.\n- **Plan-tier detection.** Parse first-search response for \"Showing top 10\" \u002F \"upgrade\" → free tier (10\u002Fsearch). 20 returned → Pro (20\u002Fsearch). Calculate theoretical ceiling and surface at checkpoint so user can recalibrate.\n\nSee [`references\u002Fsearch_budget_allocation.md`](references\u002Fsearch_budget_allocation.md) for the sequential-execution rationale + plan-tier signals.\n\n## Error Handling\n\n| Failure | Behavior |\n|---|---|\n| Consensus rate-limit hit | Wait 3s, retry once, log outcome |\n| Search returns 0 results | Note explicitly; \"either niche terminology or genuine gap\"; never silently fill |\n| Plan-tier cap detected | Log tier; report at checkpoint; surface in audit |\n| 3 consecutive failures | Stop searching, alert user, share what's collected, ask how to proceed |\n| Sub-area returns thin results (\u003C5 papers) | Flag in audit; suggest manual PubMed\u002FScholar supplementation |\n| User wants to adjust sub-areas | Update table, re-confirm before searching |\n| DOCX validation fails | Unpack XML, fix, repack |\n\n## Phase 0: Grill-Me Intake (3 forcing questions, one at a time)\n\nEach question carries explicit \"why I'm asking\". Stop condition: max 3 before Phase 1.\n\n### Q1 (root) — Research question specificity\n\n> **State the research question in 1–2 sentences. Specific is better — \"How do LLMs perform on clinical reasoning tasks compared to physicians?\" beats \"AI in medicine\". Vague questions produce vague reviews.**\n>\n> *Why I'm asking:* The reconnaissance search hinges on precise terminology. Vague questions produce thin recon results that don't yield a useful framework breakdown.\n\n**Refuse mush.** Re-ask once with examples if user is too broad. If still vague, deliver with explicit \"broad-scope orientation, not depth review\" caveat.\n\n### Q2 (depends on Q1) — Framework hint\n\n> **Framework — pick one or say \"you pick\":**\n>\n> 1. **PICO** (Population \u002F Intervention \u002F Comparison \u002F Outcome — most clinical questions)\n> 2. **SPIDER** (Sample \u002F Phenomenon \u002F Design \u002F Evaluation \u002F Research-type — social\u002Fqualitative)\n> 3. **Decomposition** (Problem \u002F Solution \u002F Evaluation \u002F Limitations — technology-focused)\n> 4. **Hybrid** (you pick which components from which framework)\n> 5. **You pick** — analyze Q1 and recommend\n>\n> *Why I'm asking:* PICO is the default for ~70% of clinical questions but maps poorly to qualitative work or technology evaluation. Picking upfront saves the recon search from suggesting a misaligned framework.\n\nForcing choice with default (\"you pick\"). The skill surfaces its own framework recommendation after the recon search so user can override. Use `scripts\u002Fframework_recommender.py` for the heuristic.\n\nSee [`references\u002Fframework_selection.md`](references\u002Fframework_selection.md) for PICO \u002F SPIDER \u002F Decomposition canon.\n\n### Q3 (depends on Q1) — Tentative depth\n\n> **Tentative depth — pick one. Final confirmation comes after the framework breakdown:**\n>\n> 1. **Quick scan** (5 searches)\n> 2. **Standard review** (10 searches)\n> 3. **Deep dive** (20 searches)\n>\n> *Why I'm asking:* I ask this twice — once now to calibrate the recon search emphasis, once after the framework breakdown to confirm. Tentative answer affects which sub-areas to surface first; final answer drives search budget allocation.\n\nForcing choice. **Re-asked** at the post-Phase-2 checkpoint after the user has seen the framework breakdown.\n\n**Stop condition:** 3 questions max before Phase 1. The post-Phase-2 checkpoint is its own grill-me moment (framework table + sub-area-adjustment + depth-reconfirmation).\n\n## Phase 1: Initial Reconnaissance\n\n**One broad Consensus search** to map themes, terminology, methodological distinctions.\n\n- Query: broad version of Q1 (terminology variants are okay; first search casts wide)\n- Record: `citation_tracker.py --action record_search --session NAME --query \"...\"`\n- Record received count: `citation_tracker.py --action record_papers_received --session NAME --count N`\n- **Detect plan tier** from response: \"Showing top 10\" \u002F \"upgrade\" → free; 20 returned → Pro\n\nSynthesize for the checkpoint:\n- Themes that surfaced\n- Terminology variations (e.g., \"LLM\" vs \"large language model\" vs \"GPT-style model\")\n- Methodological distinctions (clinical trials vs benchmark eval vs case study)\n- Coverage gaps (sub-questions absent from recon results)\n\n## Phase 2: Framework Selection + Sub-area Generation\n\nChoose framework (from Q2 OR override based on recon):\n- **PICO** — most clinical questions (~70% default)\n- **SPIDER** — social \u002F qualitative\n- **Decomposition** — technology focus (Problem \u002F Solution \u002F Evaluation \u002F Limitations)\n- **Hybrid** — explicit cross-framework mapping\n\nGenerate **4-5 sub-area questions** mapped to framework components. Each becomes a targeted Phase 3 search.\n\n## Checkpoint (grill-me forcing-options moment)\n\nAfter Phase 2, halt and present:\n\n### 3-4 sentence recon summary\n- What themes surfaced\n- Terminology landscape\n- Evidence landscape characterization\n\n### Framework breakdown table\n\n| Framework Component | How It Maps to This Topic | Proposed Sub-area to Explore |\n|---|---|---|\n| (Component 1) | ... | Sub-area 1 |\n| (Component 2) | ... | Sub-area 2 |\n| (Component 3) | ... | Sub-area 3 |\n| (Component 4) | ... | Sub-area 4 |\n| Cross-cutting theme | ... | Sub-area 5 |\n\n### Depth re-confirmation (forcing choice)\n\nSurface the **practical constraint**: detected plan tier + theoretical ceiling.\n\n- Quick scan (5 searches × ~10 results each = ~50 papers max)\n- Standard review (10 searches × ~10 = ~100 papers)\n- Deep dive (20 searches × ~10 = ~200 papers)\n\n### Sub-area forcing options\n\n- \"Looks good — proceed with these sub-areas\"\n- \"Adjust: add sub-area on [X]\"\n- \"Adjust: remove and replace [Y] with [Z]\"\n- \"Restart with different framework\"\n\n### Why I'm asking (the rationale)\n\n> A wrong framework or sub-area set wastes the search budget. This is the **last cheap moment** to correct course.\n\n**Wait for user response before Phase 3.** Refuse to start Phase 3 without explicit user choice.\n\n## Phase 3: Targeted Searches\n\nSequential (1 query\u002Fsec), budget per depth tier. See [`references\u002Fsearch_budget_allocation.md`](references\u002Fsearch_budget_allocation.md) for full canon.\n\n### Quick scan (5 searches)\n- 5 sub-area searches (one per sub-area)\n- Skip era-gated + review-specific\n\n### Standard review (10 searches)\n- 5 sub-area searches\n- 2 review article searches (top 2 sub-areas): `\"systematic review [topic]\"` \u002F `\"meta-analysis [topic]\"`\n- 2 era-gated searches (most important sub-area): `year_max: 2015` + `year_min: 2021`\n- 1 follow-up on highest-cited paper using its key terms + `year_min` after publication\n\n### Deep dive (20 searches)\n- 5 sub-area searches\n- 5 review article searches (one per sub-area)\n- 4 era-gated searches (top 2 sub-areas, old + new each)\n- 3 follow-ups on top 3 highest-cited papers\n- 3 spare for emerging threads (surprising findings to chase)\n\nThroughout: 1 q\u002Fsec rate limit. Sequential. Confirm response before next call. Record each via `citation_tracker.py`.\n\n## Cross-Search Intelligence\n\nThree trackers across ALL search results — run `scripts\u002Fcross_search_aggregator.py --session NAME` after Phase 3 completes:\n\n1. **Repeat-hit papers** — same paper appearing in 3+ sub-area searches = likely foundational\n2. **Recurring authors** — same author in multiple searches = dominant research group; top 3-5 most frequent matter\n3. **Citation-per-year heuristic** — a 2023 paper with 150 citations >> 2008 paper with 150 citations. Use for seminal-work identification.\n\nThese feed the \"Start Here\" + \"Key Research Groups\" + \"Bibliography\" DOCX sections.\n\n## Phase 4: DOCX Research Guide\n\nGenerate via Node.js + `docx` library. 8 sections (see [`references\u002Fdocx_8_sections.md`](references\u002Fdocx_8_sections.md) for full spec):\n\n1. **Topic Overview** — single tight paragraph (4-6 sentences)\n2. **Start Here — Priority Reading Order** — 5-7 papers ordered: best recent review → foundational → 2-3 frontier → gap\u002Fcontroversy. Each: hyperlinked title + authors\u002Fyear + 1-sentence contribution + 1-sentence \"what to look for\"\n3. **How the Field Got Here** — chronological narrative (1-2 paragraphs) + timeline table (5-8 milestones: Year \u002F Milestone \u002F Significance) + terminology evolution note\n4. **Sub-area Guides** (one per sub-area, 4 parts each)\n   - 4a. What the Research Shows (2-3 sentence synthesis with inline citations)\n   - 4b. Key Papers (3-5 hyperlinked papers with citation count, year, 1-sentence importance)\n   - 4c. Key Search Terms (6-10 keywords, synonyms, MeSH, historical terms)\n   - 4d. Boolean Search Strings (2-3 ready-to-paste strings)\n5. **Key Research Groups** — top 3-5 authors\u002Fgroups with affiliations, sub-area coverage, representative paper link (from cross-search aggregator)\n6. **Open Questions & Gaps** — three categories: methodological \u002F population-context \u002F conceptual-theoretical. Each gap explains *why it matters*.\n7. **Bibliography** — alphabetical by first author. Every entry has clickable \"View on Consensus\" link. Every inline citation matches a bibliography entry.\n8. **Audit Log** — search summary table (#, query, filters, papers returned, status), counts block, coverage notes including detected tier and theoretical ceiling\n\n### DOCX Technical Requirements\n\nDocument the key `docx` library patterns:\n\n- Page: US Letter, 1-inch margins\n- Lists: `LevelFormat.BULLET` (never unicode bullets)\n- Hyperlinks: `ExternalHyperlink` with `style: \"Hyperlink\"`, full URL (never truncated)\n- Tables: dual widths (`columnWidths` + cell `width`), `ShadingType.CLEAR`\n- Validation step after save (zip-integrity check: `python3 -c \"import zipfile,sys; zipfile.ZipFile(sys.argv[1]).testzip()\" output.docx` — no output = intact — then confirm the required sections are present)\n\nReference the **docx skill** for setup patterns and best practices.\n\n## Output\n\n```\nresearch_guide_\u003Ctopic-slug>_\u003CYYYY-MM-DD>.docx\n```\n\nPlus:\n- Chat summary block: \"Saved: \u003Cpath>. Audit: N searches × M unique papers \u002F K cited. Plan tier: \u003Ctier>.\"\n- Audit log printed inline if user asks for it\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fcitation_tracker.py` | JSON-backed three-count audit at `~\u002F.litreview_sessions\u002F\u003Csession>.json` |\n| `scripts\u002Fframework_recommender.py` | Heuristic PICO\u002FSPIDER\u002FDecomposition suggestion from research question |\n| `scripts\u002Fcross_search_aggregator.py` | Repeat-hits + recurring-authors + citation-per-year ranking after Phase 3 |\n\n## References\n\n- [`references\u002Fframework_selection.md`](references\u002Fframework_selection.md) — PICO \u002F SPIDER \u002F Decomposition canon (7+ sources)\n- [`references\u002Fsearch_budget_allocation.md`](references\u002Fsearch_budget_allocation.md) — depth tiers + cross-search intelligence + sequential execution rationale (7+ sources)\n- [`references\u002Fdocx_8_sections.md`](references\u002Fdocx_8_sections.md) — research guide DOCX spec + technical requirements (7+ sources)\n\n## Anti-Patterns To Reject\n\n- Parallelizing Consensus calls\n- Skipping the interactive checkpoint (running all searches without user confirmation)\n- Padding thin results with training knowledge\n- Defaulting to non-PICO framework without justification\n- Citing papers in chat that didn't come from Consensus this session\n- Hardcoding plan tier instead of detecting from first response\n- Skipping era-gated searches in standard\u002Fdeep budgets\n- Skipping cross-search intelligence (repeat-hits, recurring authors)\n- Truncating Consensus URLs in hyperlinks\n\n---\n\n**Version:** 1.0.0\n**Source spec:** [`megaprompts\u002F09-litreview-megaprompt.md`](..\u002F..\u002F..\u002F..\u002Fmegaprompts\u002F09-litreview-megaprompt.md)\n**Build pattern:** Path B (direct conversion). Sibling of `pulse` (research-pack shape).\n","# Litreview — Academic Literature Orientation\n\n> **Portability:** Requires a Consensus MCP connection, Node.js with `docx` package for document generation, and (in CLI) `bash_tool`. Works in Claude Code CLI natively. In Claude.ai with Consensus MCP + Code Execution, the workflow is supported.\n\nProduce a **launching pad** — not a finished literature review, but an orientation document that gives a researcher entering an unfamiliar field everything they need to start reading and searching with confidence. Think: what a generous colleague who knows the field would tell you over coffee.\n\n## Agent Integrity Rules (Research-Pack Convention)\n\nInherited from the research-pack convention; locked verbatim per PR #657's cross-skill consistency audit.\n\n- **Source discipline.** Only cite Consensus-returned papers from THIS session. Training knowledge labeled `[Not from Consensus — model knowledge]` and excluded from cited count. Sparse results stated explicitly, never silently filled.\n- **Counting discipline.** Three numbers tracked: searches executed \u002F unique papers received (deduplicated) \u002F papers cited. Every cited paper has a retrievable Consensus URL from this session. Use `scripts\u002Fcitation_tracker.py` for deterministic counts.\n- **Tool constraints.** Consensus per-query cap depends on plan tier. **Detect at first search**, report at checkpoint. Rate limit is **1 query\u002Fsec** — sequential execution mandatory.\n- **Retry policy.** On failure → wait 3s → retry once → log. After 3 consecutive failures: stop, alert user, share what was collected.\n- **Plan-tier detection.** Parse first-search response for \"Showing top 10\" \u002F \"upgrade\" → free tier (10\u002Fsearch). 20 returned → Pro (20\u002Fsearch). Calculate theoretical ceiling and surface at checkpoint so user can recalibrate.\n\nSee [`references\u002Fsearch_budget_allocation.md`](references\u002Fsearch_budget_allocation.md) for the sequential-execution rationale + plan-tier signals.\n\n## Error Handling\n\n| Failure | Behavior |\n|---|---|\n| Consensus rate-limit hit | Wait 3s, retry once, log outcome |\n| Search returns 0 results | Note explicitly; \"either niche terminology or genuine gap\"; never silently fill |\n| Plan-tier cap detected | Log tier; report at checkpoint; surface in audit |\n| 3 consecutive failures | Stop searching, alert user, share what's collected, ask how to proceed |\n| Sub-area returns thin results (\u003C5 papers) | Flag in audit; suggest manual PubMed\u002FScholar supplementation |\n| User wants to adjust sub-areas | Update table, re-confirm before searching |\n| DOCX validation fails | Unpack XML, fix, repack |\n\n## Phase 0: Grill-Me Intake (3 forcing questions, one at a time)\n\nEach question carries explicit \"why I'm asking\". Stop condition: max 3 before Phase 1.\n\n### Q1 (root) — Research question specificity\n\n> **State the research question in 1–2 sentences. Specific is better — \"How do LLMs perform on clinical reasoning tasks compared to physicians?\" beats \"AI in medicine\". Vague questions produce vague reviews.**\n>\n> *Why I'm asking:* The reconnaissance search hinges on precise terminology. Vague questions produce thin recon results that don't yield a useful framework breakdown.\n\n**Refuse mush.** Re-ask once with examples if user is too broad. If still vague, deliver with explicit \"broad-scope orientation, not depth review\" caveat.\n\n### Q2 (depends on Q1) — Framework hint\n\n> **Framework — pick one or say \"you pick\":**\n>\n> 1. **PICO** (Population \u002F Intervention \u002F Comparison \u002F Outcome — most clinical questions)\n> 2. **SPIDER** (Sample \u002F Phenomenon \u002F Design \u002F Evaluation \u002F Research-type — social\u002Fqualitative)\n> 3. **Decomposition** (Problem \u002F Solution \u002F Evaluation \u002F Limitations — technology-focused)\n> 4. **Hybrid** (you pick which components from which framework)\n> 5. **You pick** — analyze Q1 and recommend\n>\n> *Why I'm asking:* PICO is the default for ~70% of clinical questions but maps poorly to qualitative work or technology evaluation. Picking upfront saves the recon search from suggesting a misaligned framework.\n\nForcing choice with default (\"you pick\"). The skill surfaces its own framework recommendation after the recon search so user can override. Use `scripts\u002Fframework_recommender.py` for the heuristic.\n\nSee [`references\u002Fframework_selection.md`](references\u002Fframework_selection.md) for PICO \u002F SPIDER \u002F Decomposition canon.\n\n### Q3 (depends on Q1) — Tentative depth\n\n> **Tentative depth — pick one. Final confirmation comes after the framework breakdown:**\n>\n> 1. **Quick scan** (5 searches)\n> 2. **Standard review** (10 searches)\n> 3. **Deep dive** (20 searches)\n>\n> *Why I'm asking:* I ask this twice — once now to calibrate the recon search emphasis, once after the framework breakdown to confirm. Tentative answer affects which sub-areas to surface first; final answer drives search budget allocation.\n\nForcing choice. **Re-asked** at the post-Phase-2 checkpoint after the user has seen the framework breakdown.\n\n**Stop condition:** 3 questions max before Phase 1. The post-Phase-2 checkpoint is its own grill-me moment (framework table + sub-area-adjustment + depth-reconfirmation).\n\n## Phase 1: Initial Reconnaissance\n\n**One broad Consensus search** to map themes, terminology, methodological distinctions.\n\n- Query: broad version of Q1 (terminology variants are okay; first search casts wide)\n- Record: `citation_tracker.py --action record_search --session NAME --query \"...\"`\n- Record received count: `citation_tracker.py --action record_papers_received --session NAME --count N`\n- **Detect plan tier** from response: \"Showing top 10\" \u002F \"upgrade\" → free; 20 returned → Pro\n\nSynthesize for the checkpoint:\n- Themes that surfaced\n- Terminology variations (e.g., \"LLM\" vs \"large language model\" vs \"GPT-style model\")\n- Methodological distinctions (clinical trials vs benchmark eval vs case study)\n- Coverage gaps (sub-questions absent from recon results)\n\n## Phase 2: Framework Selection + Sub-area Generation\n\nChoose framework (from Q2 OR override based on recon):\n- **PICO** — most clinical questions (~70% default)\n- **SPIDER** — social \u002F qualitative\n- **Decomposition** — technology focus (Problem \u002F Solution \u002F Evaluation \u002F Limitations)\n- **Hybrid** — explicit cross-framework mapping\n\nGenerate **4-5 sub-area questions** mapped to framework components. Each becomes a targeted Phase 3 search.\n\n## Checkpoint (grill-me forcing-options moment)\n\nAfter Phase 2, halt and present:\n\n### 3-4 sentence recon summary\n- What themes surfaced\n- Terminology landscape\n- Evidence landscape characterization\n\n### Framework breakdown table\n\n| Framework Component | How It Maps to This Topic | Proposed Sub-area to Explore |\n|---|---|---|\n| (Component 1) | ... | Sub-area 1 |\n| (Component 2) | ... | Sub-area 2 |\n| (Component 3) | ... | Sub-area 3 |\n| (Component 4) | ... | Sub-area 4 |\n| Cross-cutting theme | ... | Sub-area 5 |\n\n### Depth re-confirmation (forcing choice)\n\nSurface the **practical constraint**: detected plan tier + theoretical ceiling.\n\n- Quick scan (5 searches × ~10 results each = ~50 papers max)\n- Standard review (10 searches × ~10 = ~100 papers)\n- Deep dive (20 searches × ~10 = ~200 papers)\n\n### Sub-area forcing options\n\n- \"Looks good — proceed with these sub-areas\"\n- \"Adjust: add sub-area on [X]\"\n- \"Adjust: remove and replace [Y] with [Z]\"\n- \"Restart with different framework\"\n\n### Why I'm asking (the rationale)\n\n> A wrong framework or sub-area set wastes the search budget. This is the **last cheap moment** to correct course.\n\n**Wait for user response before Phase 3.** Refuse to start Phase 3 without explicit user choice.\n\n## Phase 3: Targeted Searches\n\nSequential (1 query\u002Fsec), budget per depth tier. See [`references\u002Fsearch_budget_allocation.md`](references\u002Fsearch_budget_allocation.md) for full canon.\n\n### Quick scan (5 searches)\n- 5 sub-area searches (one per sub-area)\n- Skip era-gated + review-specific\n\n### Standard review (10 searches)\n- 5 sub-area searches\n- 2 review article searches (top 2 sub-areas): `\"systematic review [topic]\"` \u002F `\"meta-analysis [topic]\"`\n- 2 era-gated searches (most important sub-area): `year_max: 2015` + `year_min: 2021`\n- 1 follow-up on highest-cited paper using its key terms + `year_min` after publication\n\n### Deep dive (20 searches)\n- 5 sub-area searches\n- 5 review article searches (one per sub-area)\n- 4 era-gated searches (top 2 sub-areas, old + new each)\n- 3 follow-ups on top 3 highest-cited papers\n- 3 spare for emerging threads (surprising findings to chase)\n\nThroughout: 1 q\u002Fsec rate limit. Sequential. Confirm response before next call. Record each via `citation_tracker.py`.\n\n## Cross-Search Intelligence\n\nThree trackers across ALL search results — run `scripts\u002Fcross_search_aggregator.py --session NAME` after Phase 3 completes:\n\n1. **Repeat-hit papers** — same paper appearing in 3+ sub-area searches = likely foundational\n2. **Recurring authors** — same author in multiple searches = dominant research group; top 3-5 most frequent matter\n3. **Citation-per-year heuristic** — a 2023 paper with 150 citations >> 2008 paper with 150 citations. Use for seminal-work identification.\n\nThese feed the \"Start Here\" + \"Key Research Groups\" + \"Bibliography\" DOCX sections.\n\n## Phase 4: DOCX Research Guide\n\nGenerate via Node.js + `docx` library. 8 sections (see [`references\u002Fdocx_8_sections.md`](references\u002Fdocx_8_sections.md) for full spec):\n\n1. **Topic Overview** — single tight paragraph (4-6 sentences)\n2. **Start Here — Priority Reading Order** — 5-7 papers ordered: best recent review → foundational → 2-3 frontier → gap\u002Fcontroversy. Each: hyperlinked title + authors\u002Fyear + 1-sentence contribution + 1-sentence \"what to look for\"\n3. **How the Field Got Here** — chronological narrative (1-2 paragraphs) + timeline table (5-8 milestones: Year \u002F Milestone \u002F Significance) + terminology evolution note\n4. **Sub-area Guides** (one per sub-area, 4 parts each)\n   - 4a. What the Research Shows (2-3 sentence synthesis with inline citations)\n   - 4b. Key Papers (3-5 hyperlinked papers with citation count, year, 1-sentence importance)\n   - 4c. Key Search Terms (6-10 keywords, synonyms, MeSH, historical terms)\n   - 4d. Boolean Search Strings (2-3 ready-to-paste strings)\n5. **Key Research Groups** — top 3-5 authors\u002Fgroups with affiliations, sub-area coverage, representative paper link (from cross-search aggregator)\n6. **Open Questions & Gaps** — three categories: methodological \u002F population-context \u002F conceptual-theoretical. Each gap explains *why it matters*.\n7. **Bibliography** — alphabetical by first author. Every entry has clickable \"View on Consensus\" link. Every inline citation matches a bibliography entry.\n8. **Audit Log** — search summary table (#, query, filters, papers returned, status), counts block, coverage notes including detected tier and theoretical ceiling\n\n### DOCX Technical Requirements\n\nDocument the key `docx` library patterns:\n\n- Page: US Letter, 1-inch margins\n- Lists: `LevelFormat.BULLET` (never unicode bullets)\n- Hyperlinks: `ExternalHyperlink` with `style: \"Hyperlink\"`, full URL (never truncated)\n- Tables: dual widths (`columnWidths` + cell `width`), `ShadingType.CLEAR`\n- Validation step after save (zip-integrity check: `python3 -c \"import zipfile,sys; zipfile.ZipFile(sys.argv[1]).testzip()\" output.docx` — no output = intact — then confirm the required sections are present)\n\nReference the **docx skill** for setup patterns and best practices.\n\n## Output\n\n```\nresearch_guide_\u003Ctopic-slug>_\u003CYYYY-MM-DD>.docx\n```\n\nPlus:\n- Chat summary block: \"Saved: \u003Cpath>. Audit: N searches × M unique papers \u002F K cited. Plan tier: \u003Ctier>.\"\n- Audit log printed inline if user asks for it\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fcitation_tracker.py` | JSON-backed three-count audit at `~\u002F.litreview_sessions\u002F\u003Csession>.json` |\n| `scripts\u002Fframework_recommender.py` | Heuristic PICO\u002FSPIDER\u002FDecomposition suggestion from research question |\n| `scripts\u002Fcross_search_aggregator.py` | Repeat-hits + recurring-authors + citation-per-year ranking after Phase 3 |\n\n## References\n\n- [`references\u002Fframework_selection.md`](references\u002Fframework_selection.md) — PICO \u002F SPIDER \u002F Decomposition canon (7+ sources)\n- [`references\u002Fsearch_budget_allocation.md`](references\u002Fsearch_budget_allocation.md) — depth tiers + cross-search intelligence + sequential execution rationale (7+ sources)\n- [`references\u002Fdocx_8_sections.md`](references\u002Fdocx_8_sections.md) — research guide DOCX spec + technical requirements (7+ sources)\n\n## Anti-Patterns To Reject\n\n- Parallelizing Consensus calls\n- Skipping the interactive checkpoint (running all searches without user confirmation)\n- Padding thin results with training knowledge\n- Defaulting to non-PICO framework without justification\n- Citing papers in chat that didn't come from Consensus this session\n- Hardcoding plan tier instead of detecting from first response\n- Skipping era-gated searches in standard\u002Fdeep budgets\n- Skipping cross-search intelligence (repeat-hits, recurring authors)\n- Truncating Consensus URLs in hyperlinks\n\n---\n\n**Version:** 1.0.0\n**Source spec:** [`megaprompts\u002F09-litreview-megaprompt.md`](..\u002F..\u002F..\u002F..\u002Fmegaprompts\u002F09-litreview-megaprompt.md)\n**Build pattern:** Path B (direct conversion). Sibling of `pulse` (research-pack shape).\n",{"name":5,"license":15,"metadata":24,"description":7},{"version":25,"source_spec":26,"build_pattern":27,"research_pack_convention":28},"1.0.0","megaprompts\u002F09-litreview-megaprompt.md","Path B (direct conversion)","Agent Integrity Rules verbatim per PR #657 audit; sibling of pulse","main","835716bfbede9677a779d77bfd04befb81c069ac","skills\u002Fclaude__litreview-2","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI","https:\u002F\u002Fgithub.com\u002Fharesh-sai06","https:\u002F\u002Fharesh-sainaath.live\u002F","I am a Student pursuing Artificial Intelligence and Machine Learning at Sri Krishna College of Technology,Coimbatore.","2026-06-13 22:42:28",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add haresh-sai06\u002FSapSynk-AI --skill litreview",{"tool":43,"command":44},"bunx","bunx skills add haresh-sai06\u002FSapSynk-AI --skill litreview",{"tool":46,"command":47},"pnpm","pnpm dlx skills add haresh-sai06\u002FSapSynk-AI --skill litreview","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__litreview-2\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M77GQ5PRFQMV3QBDAQPCSXJB","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__youtube-full-2\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M77GPXXAB3Y8ZNG919MD4703","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__x-twitter-growth-2\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M77GPSS7AFYH90Y5S6XHRXZW","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__write-a-skill-2\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M77GPKB6HJS2X5XK03649C6R","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__workflow-builder-2\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M77GP31EFXE1KS38XBZ1J9MN","webinar-marketing","When the user wants to plan, promote, run, or improve a webinar or virtual event to generate and convert demand. Use when the user mentions 'webinar,' 'virtual event,' 'online event,' 'live demo,' 'virtual summit,' 'workshop,' 'masterclass,' 'fireside chat,' 'roundtable,' 'registration funnel,' 'show-up rate,' 'attendance rate,' 'webinar promotion,' 'webinar follow-up,' or 'on-demand webinar.' Also use when they have a webinar that isn't converting — low registrations, low show-up, or attendees who don't buy — and want to diagnose and fix it. Covers the full funnel: registration, promotion, show-up, live engagement, live-to-close, and post-event nurture. Distinct from launch-strategy (full product launches) and email-sequence (lifecycle nurture) — this is the end-to-end webinar\u002Fevent motion. NOT for in-person field events logistics, and NOT for generic lifecycle email (use email-sequence).","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__webinar-marketing-2\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M77GNNA22HWXX6CEQQ3JY2YB","vpe-advisor","VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad\u002Ftribe\u002Fchapter design + tech-lead manager-trigger thresholds), and production discipline (on-call, deployment cadence, postmortem culture). Use when sprint velocity is dropping, eng hiring is broken, team structure is unclear, or deciding when to add a tech-lead manager. NOT a CTO skill (which owns architecture) — VPE owns delivery operations and how the team ships.","https:\u002F\u002Fgithub.com\u002Fharesh-sai06\u002FSapSynk-AI\u002Fblob\u002Fmain\u002Fskills\u002Fclaude__vpe-advisor-2\u002FSKILL.md",[],[]]