Borrowing it
Nothing to install: this file belongs to u9401066/med-paper-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/u9401066/med-paper-assistant/master/.claude/skills/parallel-search/SKILL.mdgit clone --depth 1 https://github.com/u9401066/med-paper-assistantWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/u9401066/med-paper-assistant/parallel-search)<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/parallel-search"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/parallel-search/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/parallel-search"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/parallel-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00560 |
| Opus 5 | $0.00015 | $0.00280 |
| Sonnet 5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
parallel-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Parallel Search Skill
觸發：並行搜尋、parallel search、批量搜尋、多組搜尋、廣泛搜尋、comprehensive search
使用 pubmed-search MCP 多次搜尋 + 合併結果，提高覆蓋率。
工具
| 階段 | Tool | 說明 |
|---|---|---|
| 搜尋 | unified_search(query, limit) |
每組關鍵字獨立搜尋 |
| 結果 | read_session(action="pmids") |
取回 PMID + 去重 |
| Session | get_session_log() |
列出搜尋歷史 |
| 儲存 | save_reference_mcp(pmid) |
存入專案（永遠優先） |
工作流
- 拆分關鍵字：同一主題拆 3-5 組變體（同義詞、MeSH、縮寫）
- 並行搜尋：每組
unified_search()各取 20-30 篇 - 合併去重：
read_session(action="pmids")取回 PMID 後，以 PMID/DOI 手動比對去重 - 篩選：review title/abstract，標記 relevant
- 儲存：
save_reference_mcp(pmid)存入專案 - 不足時擴展：選擇下方擴展策略
擴展策略
| 類型 | 適用 | 方法 |
|---|---|---|
| broaden | 結果太少 | 移除限制詞、用上位概念 |
| narrow | 結果太多 | 加 AND 條件、限制 study type |
| lateral | 結果偏離 | 換同義詞、相關但不同角度 |
| temporal | 需歷史脈絡 | 分年代搜尋 |
| citation | 找到核心文獻 | find_related_articles / find_citing_articles |
Session 提示
search_index=-1= 最近一次搜尋query_filter="keyword"= 篩選特定搜尋- 搜尋結果自動暫存，用
get_session_pmids()取回
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 49 lines · 31 tokens per session scan A 5aee6c0f6861
parallel-search is a skill published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 8d ago), licensed Apache-2.0. It adds 31 tokens to every session and 560 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
tikz-figure-review
Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…
animating-computational-mechanics
Animate continuum mechanics, tensor calculus, and finite element concepts — deformation gradients, polar decomposition, Cauchy/Piola–Kirchhoff stresses, weak form, mesh convergence — using Matplotlib (FuncAnimation), Manim (ValueTracker / applyfunction / Transform), or Blender (bpy + ParaView .obj pipeline). Use when…
refining-ml-papers
Refines ML/scientific LaTeX papers based on reviewer or advisor feedback. Handles structural reorganization (moving problem statements, merging sections), concrete instantiations of abstract tables, cross-file deduplication, and compilation verification. Use when the user requests paper revisions, addresses reviewer…
rigorous-paper-reviewer
Review a LaTeX research paper for mathematical rigor, notation consistency, proof obligations, numerical-analysis discipline, complexity claims, convergence/error bounds, figure quality, reader-state flow, cross-references, and global coherence. Use when the user wants a deep technical review or verification pass on a…