Claude Code skill for verifying OpenEvidence biomedical citations against PubMed with parallel accuracy scoring and audit reports
htlin222/audit-oe-skillMITApr 20, 2026
Score42
How is this score calculated?
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Free, open source website technology detection. Identify any site's full tech stack from its URL — CLI, library and MCP server for Claude, Claude Code, Codex and ChatGPT. No API key, no credits, no subscription.
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning required.
Open-source build package for creating an MCP server that gives Claude Code full control over Autodesk Fusion 360. Localhost-only, no bloat, no binaries.
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
An MCP server for OpenReview to fetch user papers, specific conference papers (e.g. ICML / ICLR / NeurIPS), parse .pdf files and save them into .json. Can be added to Claude Code to sample ideas from the recent AI/ML/SWE conferences.
AI agent pipeline orchestration for Claude Code. Deploy specialized agents in coordinated pipelines with self-learning capabilities, mesh coordination, Raft consensus, CRDT knowledge graphs, and pipeline debugging. 15 production-grade skills with reasoning protocols, 20+ agent types, 15 ready-to-run templates. Zero infrastructure.
Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.
Evals & guardrails for AI agents and the MCP tools they call: lint + auto-fix, fuzz, SHIP/FIX-FIRST/BLOCK verdict, live guard. Runs in CI, Claude Code, Codex, Cursor.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
How is this score calculated?
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
How is this score calculated?
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
How is this score calculated?
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.
Review the upstream source before running this command.
Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.
Dimensions a source cannot supply — registries publish no stars or license — are excluded from the entry's own average instead of counted as zero, so entries stay comparable across sources.
Security signals subtract up to 20. Scores are recomputed on every daily ingest.