
Claude Skills by lilinji
github.com/lilinjiProvide implementation guidance for electronic records/signatures (ER/ES) compliance: access control, audit trails, data integrity, and validation expectations in medical device software and supporting tools.
Define what and how to log for medical devices: security/safety events, integrity, protection, and retention of logs for compliance and forensics.
Define secure user/device authentication, session management, and RBAC suitable for medical device risk profiles.
Define how to automate tests (unit, integration, system/HIL where feasible) in CI/CD pipelines for medical devices with gating and evidence capture.
Convert raw Nanopore signal data (FAST5/POD5) to nucleotide sequences using Dorado basecaller. Covers model selection, GPU acceleration, modified base detection, and quality filtering. Use when processing raw Nanopore data before alignment. Note: Guppy is deprecated; use Dorado for all new analyses.
Meta-agent that routes bioinformatics requests to specialised sub-skills. Handles file type detection, analysis planning, report generation, and reproducibility export.
Guide secure, reliable BLE implementation for medical devices handling PHI/therapy control: services, pairing/bonding, LE Secure Connections, privacy, and performance.
Define controlled process for software changes: requests, impact analysis, approvals, verification, and configuration management in regulated contexts.
Ancestry decomposition PCA against the Simons Genome Diversity Project
Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways
Semantic Similarity Index for disease research literature using PubMedBERT embeddings
Query the ClinPGx API for pharmacogenomic gene-drug data, clinical annotations, CPIC guidelines, and FDA drug labels
Provide conventions for code comments that support traceability to requirements, risks, and tests, while maintaining clarity and brevity.
Measure and enforce coverage appropriate to safety class: statement/branch and MC/DC where applicable, with documented exclusions.
Ensure integrity of data in storage and transmission using checksums/CRCs/ECC, validation, and redundancy where needed for medical devices.
Apply defensive coding techniques to prevent, detect, and safely handle abnormal conditions in safety-relevant software.
Guide creation and maintenance of Software Architecture (SAD) and Design Descriptions (SDD) that support safety, traceability, and compliance.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance
Detect runtime defects (memory, concurrency, timing, performance, power) via dynamic tools and instrumentation in medical device software.
Define C coding practices aligned with MISRA C and medical device safety needs: type safety, control flow, memory management, interrupts, and static analysis.
Define a constrained C++ subset suitable for medical device firmware, aligned to MISRA C++ guidance: safe types, RAII, limited dynamic features, and predictable behavior.
Guide selection and use of cryptography for medical devices: algorithms, key derivation, data at rest/in transit, library choice, and FIPS considerations.
Compute HEIM diversity and equity metrics from VCF or ancestry data. Generates heterozygosity, FST, PCA plots, and a composite HEIM Equity Score with markdown reports.
Provide actionable guidance for software under EU MDR, focusing on classification (Rule 11), technical documentation expectations, UDI for software, PMS/PMCF needs, and alignment with MDCG guidance.
Provide patterns for detecting, containing, and recovering from faults in medical device software, scaled to safety class.
Guide preparation of FDA premarket submission software documentation (510(k), De Novo, PMA), including documentation depth determination, required documents, cybersecurity, SBOM, interoperability, and post-market commitments.
Uncover robustness and security issues by fuzzing inputs/protocols relevant to medical devices (parsers, IPC, network/BLE/USB).
Galaxy tool discovery, intelligent recommendation, and execution — 8,000+ bioinformatics tools from usegalaxy.org with multi-signal scoring and workflow suggestions
Compare your genome to George Church (PGP-1) and estimate ancestry composition via IBS and EM admixture
Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.
Calculate polygenic risk scores from DTC genetic data using the PGS Catalog
Provide patterns for HAL design that enable testability, portability, and safety: clear interfaces, separation from application logic, and mockability.
Validate software with real or representative hardware, sensors, actuators, and timing, to uncover integration and safety issues not visible in simulation.
Provide actionable guidance to implement IEC 62304 lifecycle controls across planning, development, verification, release, and maintenance, with class-dependent rigor for Class A/B/C software items.
Apply IEC 62443 concepts (secure development lifecycle, component requirements, security levels) to networked medical devices, ensuring threat-aware design, implementation, and verification of cybersecurity controls.
Provide concise, high-value inline documentation practices (comments and short docblocks) that improve safety, maintainability, and traceability without cluttering code.
Validate interactions between software components and hardware interfaces, ensuring interfaces, protocols, and data flows behave correctly in realistic configurations.
Enable safe and standards-aligned interoperability: HL7 FHIR/IHE profiles, data formats, terminology mapping, and API design for medical data exchange.
Define safe interrupt design: short ISRs, deferred work, priority assignment, critical section management, and testing strategies.
Integrate ISO 14971:2019 risk management into software development: hazard identification, risk evaluation, control implementation in code, verification of effectiveness, and documentation of residual risk.
Define generation, storage, rotation, revocation, and provisioning of cryptographic keys for medical devices, supporting secure boot, OTA, and comms.
Interact with the Labstep electronic lab notebook API using labstepPy. Query experiments, protocols, resources, inventory, and other lab entities.
Search PubMed and bioRxiv, summarise papers with LLM, build citation graphs, and generate literature review sections.