PU

pubmed-search-mcp-harness

Manages literature research workflows and PubMed search pipelines for Codex agents.

Install

mkdir -p .claude/skills/pubmed-search-mcp-harness && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12520" && unzip -o skill.zip -d .claude/skills/pubmed-search-mcp-harness && rm skill.zip

Installs to .claude/skills/pubmed-search-mcp-harness

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Codex harness for PubMed Search MCP. Triggers: pubmed search, literature search, unified_search, pipeline, fulltext, release checklist, Codex.
142 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Work with PubMed Search MCP research workflows
  • Manage pipeline state and fulltext access
  • Handle citation exports
  • Perform linting and format checks
  • Run type checks and tests

How it works

The skill acts as a Codex harness for PubMed Search MCP, facilitating research workflows, managing pipeline states, and ensuring adherence to research guardrails like using `unified_search` and preserving session state.

Inputs & outputs

You give it
Research tasks related to PubMed Search MCP
You get back
Managed research workflows, pipeline state, and exported citations

When to use pubmed-search-mcp-harness

  • Performing literature reviews
  • Exporting research citations
  • Managing research pipelines

About this skill

PubMed Search MCP: Codex Harness Skill

Use this skill when working with Codex on PubMed Search MCP research workflows, pipeline state, fulltext access, exports, and release checks.

What To Read First

  • AGENTS.md for Codex workspace instructions.
  • .github/agents/research.agent.md for research-agent behavior.
  • .github/hooks/ and scripts/hooks/copilot/ for pipeline enforcement assets.
  • .claude/skills/pubmed-* and .claude/skills/pipeline-persistence for user-facing workflows.
  • .clinerules/ for project/release rules that also apply to Codex.

Canonical Commands

  • Lint: uv run ruff check .
  • Format check: uv run ruff format --check .
  • Types: uv run mypy src/ tests/
  • Tests: uv run pytest
  • Tool docs sync: uv run python scripts/count_mcp_tools.py --update-docs
  • Skill audit: python scripts/check_cline_skills.py

Research Guardrails

  • Prefer unified_search as the primary multi-source entrypoint.
  • For external Python package/API questions, prefer the stable pubmed_search.api facade over MCP presentation modules.
  • Preserve session/pipeline state instead of relying on agent memory.
  • Respect NCBI email/API-key policy and institutional access configuration.
  • Keep exported citations reproducible with PMIDs, DOI, source, date filters, and query strategy.

When not to use it

  • When not working with Codex on PubMed Search MCP
  • When the task is not related to research workflows or pipeline state
  • When external Python package/API questions do not involve `pubmed_search.api`

Limitations

  • It is a Codex harness specific to PubMed Search MCP
  • It prefers `unified_search` as the primary multi-source entrypoint
  • It requires respecting NCBI email/API-key policy and institutional access configuration

How it compares

This skill provides a specific harness for Codex to interact with PubMed Search MCP, enforcing research guardrails and canonical commands for linting, formatting, and testing, unlike a general search tool.

Compared to similar skills

pubmed-search-mcp-harness side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
pubmed-search-mcp-harness (this skill)02moNo flagsIntermediate
literature-review5592moReviewAdvanced
openalex-database487moReviewIntermediate
scientific-critical-thinking187moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

literature-review

K-Dense-AI

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

5591,298

openalex-database

davila7

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

48202

scientific-critical-thinking

davila7

Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.

1888

biorxiv-database

lifangda

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.

780

physics-validator

omriwen

Validate optical physics parameters including Fresnel numbers, diffraction regimes, and resolution limits. This skill should be used when configuring Telescope, Microscope, or Camera instruments to ensure physically realistic parameters.

664

fda-database

davila7

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

539

Search skills

Search the agent skills registry