Designs, evaluates, and improves agentic harnesses for developer tools, assistants, workflow runtimes, copilots, and AI-powered products. Applies when work involves defining or reviewing tool-use architecture, permissions, workflow state, durability, context and memory systems, evaluation strategy, observability, user experience, or phased implementation plans for an agentic system.

Workflow for turning meeting transcripts or notes into decisions, action items, unresolved questions, risks, and follow-up artifacts. Use for prompts like "summarize this meeting", "extract action items", "what did we decide", or "draft the follow-up". Best when you have notes or a transcript, attendee context, and the reason the meeting happened. Optional Open Brain search and capture can pull surrounding context and store the final synthesis or decisions.

Operator-first competitive analysis workflow for competitor profiling, pricing and packaging comparisons, positioning maps, SWOTs, and strategic recommendations. Use for prompts like "analyze our competitors", "benchmark our pricing", "map the market", "who are we up against", or "build a SWOT". Best when you have a company or product, ideal customer profile, and competitor set or permission to discover it. Optional Open Brain search and capture can pull prior notes and store the final brief.

Create or migrate native verifiers.v1 taskset, environment, and harness packages. Use to build a taskset, port a benchmark, add task tools, script or model a user, build a multi-agent environment, package an agent harness, or migrate an existing v0 environment to the typed v1 trace model.

Generates RESTful API documentation (OpenAPI 3.0 / Swagger spec) by scanning route definitions in code for Flask, FastAPI, Express, Gin, and other frameworks. Trigger when users ask about API documentation, OpenAPI, Swagger, endpoint docs, generating docs from code, or extracting endpoints.

Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded passwords, or code security checks.

Searches ClinicalTrials.gov for studies by condition, intervention, and recruitment status using the modern v2 REST API with cursor (pageToken) pagination. Use when the user wants to find trials for a diagnosis or drug, screen patients against open studies, build a trial-matching feature, or pull a trial corpus for analysis. Trigger keywords: clinical trial, ClinicalTrials.gov, NCT number, trial search, recruiting studies, eligibility, query.cond, query.intr, pageToken, v2 API. Pairs adjacent to OpenMed: take Disease/Pharmaceutical entities from openmed.analyze_text and turn them into query.cond / query.intr filters; the returned eligibility text feeds parsing-trial-eligibility. ClinicalTrials.gov API v2 is fully public — no API key, no license.

Scaffold a SMART-on-FHIR app (SMART App Launch v2 — EHR launch and standalone launch, OAuth2 PKCE, scopes, token handling, fhirContext) so an OpenMed-powered tool can run inside Epic or Cerner/Oracle Health. Covers the .well-known/smart-configuration discovery, authorize/token sequence, scopes like patient/DocumentReference.rs and launch/patient, and fetching clinical notes the app then de-identifies and runs NER on locally with OpenMed. Use when the user wants to embed OpenMed inside an EHR, mentions SMART on FHIR, OAuth2 launch, scopes, Epic/Cerner app, or clinician-facing FHIR app. Pairs adjacent.

Deduplicate and reconcile OpenMed-extracted conditions into one clean active problem list with clinical status (active / resolved / historical). Use after NER and context resolution when the user wants a problem list, condition reconciliation, dedup of synonymous diagnosis mentions, or active-vs-resolved status from a note. Covers clustering synonymous mentions into one concept, excluding negated mentions, applying clinical context (historical / hypothetical / recent) to set status, and emitting a USCDI-Problem-shaped list. SNOMED CT concept grounding is user-supplied and out-of-process. Hand-off: consume openmed.analyze_text Disease entities plus resolving-clinical-context axes. Pairs after extracting-clinical-entities.

Decodes pipe-delimited HL7 v2.x messages (ADT, ORU, MDM, ORM) into structured segments/fields/components and surfaces OBX-5 and NTE-3 free-text narrative for OpenMed. Use before OpenMed processing when ingesting HL7 v2 feeds from an interface engine, lab/results system, or ADT stream and you need the embedded clinical note text de-identified and analyzed. Flatten OBX/NTE text then call openmed.deidentify and openmed.analyze_text; segment-aware redaction is available via openmed.interop.hl7v2. Trigger keywords: HL7, HL7 v2, ADT, ORU, OBX, MSH, PID, pipe-delimited, interface engine, Mirth, lab results.

Searches and fetches PubMed and PMC via NCBI E-utilities (ESearch then EFetch/ESummary) to gather biomedical evidence and build text corpora. Use when the user wants citations for a condition or drug, abstracts to summarize, MeSH-based searches, or a corpus of literature to run NER over. Trigger keywords: PubMed, PMC, NCBI, E-utilities, ESearch, EFetch, ESummary, MeSH, PMID, literature search, abstracts, evidence. Pairs adjacent to OpenMed: fetched abstracts feed openmed.analyze_text for biomedical NER, and OpenMed-extracted diagnoses/drugs/genes become the search terms. E-utilities are public; an optional free API key raises rate limits from 3 to 10 requests/second.

Turn scanned faxes, images, and CSV/CDA exports into clean text ready for OpenMed de-identification and NER, fully on-device. Use when the user has clinical documents (image scans, photographed/faxed notes, tabular CSV/TSV exports, C-CDA XML) and needs OCR or structured intake before openmed.deidentify and openmed.analyze_text, asks about openmed.multimodal, OCR engines (Tesseract / PaddleOCR), tabular redaction, or layout and reading order. Covers the verified ocr() and redact_document() entry points and the ExtractedDocument contract. Pairs before deidentifying-clinical-text and extracting-clinical-entities.

De-identify non-English clinical text on-device with OpenMed by passing lang= and locale= to deidentify(). Use when the user has Spanish, German, French, Italian, Portuguese, Dutch, Hindi, Telugu, Arabic, Japanese, or Turkish medical notes, needs locale-aware fake surrogates, must handle language-specific national IDs (DNI, NIR, Steuer-ID, codice fiscale, BSN, CPF, TCKN, Aadhaar), or asks which languages OpenMed PII supports. Covers SUPPORTED_LANGUAGES, get_pii_models_by_language, get_patterns_for_language, LANG_TO_LOCALE, and accent normalization. Pairs with OpenMed deidentifying-clinical-text and generating-synthetic-surrogates.

Orient and bootstrap any project that uses OpenMed, the on-device clinical and biomedical NLP library, for named-entity recognition, PHI de-identification, FHIR export, and evaluation. Use when the user mentions OpenMed, wants to install it, asks which OpenMed capability or model fits a task, or is starting to build a clinical/medical text pipeline and needs the right entry point.

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairness_report. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to surface a documentation gap where subgroup data is missing, or needs equalized-odds-style disparity numbers for a clinical model. Trigger on "fairness", "subgroup", "bias audit", "disparity", "equalized odds", "under-protected group", "per-group recall", or "STANDING Together" for an OpenMed model.

Package multiple FHIR R4 resources produced from OpenMed output into a single valid transaction Bundle ready to POST to an EHR, using OpenMed's verified bundle assembler openmed.clinical.exporters.fhir.to_bundle. Covers deterministic urn:uuid fullUrls, automatic in-Bundle reference rewriting, request blocks (method/url) for transaction vs batch, and conditional create. Use after exporting-to-fhir when the user has several Condition/Observation/MedicationStatement resources and wants one transaction Bundle, mentions Bundle, transaction, references, or posting to a FHIR server. Builds on exporting-to-fhir; pairs after.

Turborepo expert guidance. Use when setting up or optimizing monorepo builds, configuring task caching, remote caching, parallel execution, or the --affected flag for incremental CI.

Expert guidance for @vercel/ncc — a simple CLI for compiling Node.js modules into a single file with all dependencies included. Use when bundling serverless functions, CLI tools, or any Node.js project into a self-contained file.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.

Create, configure, and manage WhatsApp Business senders via Twilio's Channels Senders API. Covers programmatic sender registration, profile setup, webhook configuration, sender lifecycle statuses, and ISV flows. Use this skill to register and manage production WhatsApp senders at scale.