Clinical Trials Database
google-deepmind/science-skills
Query ClinicalTrials.gov via APIv2. An agent skill from google-deepmind/science-skills.
Medplum (FHIR healthcare) coding rules: style, patterns, security, testing.
$ npx skills add softspark/ai-toolkit --skill medplum-rules -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install softspark/ai-toolkit medplum-rules --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/medplum-rules .claude/skills/medplum-rules && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "medplum-rules" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/medplum-rules into .claude/skills/medplum-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medplum-rules", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/softspark/ai-toolkit/tree/main/app/skills/medplum-rulesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add softspark/ai-toolkit --skill medplum-rules -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install softspark/ai-toolkit medplum-rules --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/app/skills/medplum-rules .agents/skills/medplum-rules && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "medplum-rules" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/medplum-rules into .agents/skills/medplum-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medplum-rules", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add softspark/ai-toolkit --skill medplum-rules -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install softspark/ai-toolkit medplum-rules --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/app/skills/medplum-rules .cursor/skills/medplum-rules && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "medplum-rules" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/medplum-rules into .cursor/skills/medplum-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medplum-rules", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/softspark/ai-toolkit.git --path app/skills/medplum-rules--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add softspark/ai-toolkit --skill medplum-rules -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install softspark/ai-toolkit medplum-rules --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/app/skills/medplum-rules .gemini/skills/medplum-rules && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "medplum-rules" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/medplum-rules into .gemini/skills/medplum-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medplum-rules", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install softspark/ai-toolkit medplum-rulesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add softspark/ai-toolkit --skill medplum-rules -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/app/skills/medplum-rules .github/skills/medplum-rules && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "medplum-rules" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/medplum-rules into .github/skills/medplum-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medplum-rules", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add softspark/ai-toolkit --skill medplum-rules -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install softspark/ai-toolkit medplum-rules --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/app/skills/medplum-rules .opencode/skills/medplum-rules && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "medplum-rules" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/medplum-rules into .opencode/skills/medplum-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medplum-rules", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
medplum-rulesMedplum (FHIR healthcare) coding rules: style, patterns, security, testing.
Medplum Rules is an agent skill from softspark/ai-toolkit. Medplum (FHIR healthcare) coding rules: style, patterns, security, testing. Triggers: medplum.config.mts, medplum.config.ts, FHIR, Medplum, Bot, Subscription, Questionnaire.
Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Clinical and healthcare research. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.
Read from SKILL.md and the folder at commit e40ed87. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
hl7.orgloinc.orgsnomed.infoFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Medplum Rules loads about 4.2k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 1,917 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from softspark/ai-toolkit at commit e40ed87, republished under its Apache-2.0 licence (© softspark). 1,917 words, ~4,245 tokens.
.claude/skills/medplum-rules/SKILL.md (or your agent's skills folder).These rules come from app/rules/medplum/ in ai-toolkit. They cover
the project's standards for coding style, frameworks, patterns,
security, and testing in Medplum (FHIR healthcare). Apply them when writing or
reviewing Medplum (FHIR healthcare) code.
resourceType as first field.Patient, ServiceRequest), camelCase for fields (birthDate, valueQuantity).meta.profile when creating resources that must conform to a StructureDefinition.createReference(resource) from @medplum/core to build Reference objects.display on references for human readability.getReferenceString(resource) for comparisons and logging — returns ResourceType/id.parseReference(ref) to extract resourceType and id from a reference string.system, code, and display in every Coding element.http://loinc.org, http://snomed.info/sct, http://hl7.org/fhir/sid/icd-10-cm.getCodeBySystem(cc, system) to find codes; setCodeBySystem(cc, system, code) to set them.CodeableConcept over plain Coding when the FHIR spec allows both — it supports multiple codings and free text.identifier arrays with system + value for external IDs (MRN, NPI, SSN).getIdentifier(resource, system) and setIdentifier(resource, system, value) helpers.http://hl7.org/fhir/sid/us-npi).createResourceIfNoneExist(resource, 'identifier=system|value') for idempotent creates.extension array with url and typed value[x] fields.getExtension(resource, url) and getExtensionValue(resource, url) helpers.urn:uuid:<uuid> for internal references between entries in a transaction Bundle.request.method (POST, PUT, DELETE) and request.url.fullUrl on entries that are referenced by other entries.Practitioner?identifier=npi|123) for existing resources.safeLog()) for any output that might contain patient data. Never console.log raw FHIR resources.display strings may contain patient names — treat as PHI in logs and error messages.AuditEvent creation. No exceptions.security.md rules for full HIPAA, access policy, and PHI handling requirements.formatHumanName(), formatAddress(), formatDate(), formatQuantity() for display strings.getDisplayString(resource) as a universal fallback for any resource's display name.given[], family, prefix[], suffix[].MedplumClient for all FHIR operations. Never use raw fetch against Medplum endpoints.medplum.createResource(), readResource(), updateResource(), deleteResource() for CRUD.medplum.searchResources() for typed arrays. Use medplum.searchOne() when expecting a single result.medplum.executeBatch() for transaction Bundles — groups multiple operations atomically.medplum.upsertResource(resource, query) for atomic create-or-update.medplum.createResourceIfNoneExist(resource, query) for idempotent creation.autoBatchTime on MedplumClient to auto-batch concurrent GET requests. Use Promise.all() instead of sequential await to benefit from batching.import { Patient, Observation } from '@medplum/fhirtypes'.any for resource data.event.input in bot handlers: const patient = event.input as Patient.patient.name?.[0]?.given?.[0].<MedplumProvider client={medplum}> at the root.useMedplum() hook to access the MedplumClient instance in components.useMedplumContext() for client + profile + loading state together.<ResourceForm> for auto-generated CRUD forms, <ResourceTable> for display.<SearchControl> for searchable/filterable resource lists.<QuestionnaireForm> to render FHIR Questionnaires and capture responses.useSubscription(criteria) for real-time WebSocket data in React components.@mantine/core/styles.css.handler function: export async function handler(medplum: MedplumClient, event: BotEvent).event.input. Access secrets via event.secrets.event.contentType to determine input format (application/fhir+json, text/plain, x-application/hl7-v2+er7).medplum bot deploy <bot-name>.channel.type: 'rest-hook' and channel.endpoint: 'Bot/<ID>' for event-driven execution.List to resource type for searches: PatientList(name: "Eve").address_city, not address-city.... on Observation { valueQuantity { value } }._reference for reverse lookups: EncounterList(_reference: patient).medplum login for auth, medplum get/medplum post for FHIR operations.medplum bot deploy for bot deployment in CI/CD pipelines.medplum bulk export for bulk data operations.type: 'transaction' for atomic multi-resource operations — all-or-nothing.type: 'batch' when operations are independent and partial failure is acceptable.urn:uuid:<uuid> in fullUrl for forward references between entries.{ reference: 'urn:uuid:<uuid>' }.ifNoneExist on POST entries for conditional creation (idempotent).ifMatch: 'W/"versionId"' on PUT entries for optimistic concurrency.Practitioner?identifier=http://hl7.org/fhir/sid/us-npi|123.Prefer: respond-async header._include=ResourceType:searchParam to fetch referenced resources in one call._revinclude=ResourceType:searchParam to fetch resources referencing your results.:iterate modifier for multi-hop traversal: _include:iterate=Patient:general-practitioner._count + _offset for pagination; use searchResourcePages() for async iteration.:contains modifier for substring search on string params: name:contains=eve.:not modifier to exclude: status:not=completed.status=active,on-hold.name=Simpson&birthdate=1940-03-29.searchResources() over search() — returns typed array, not raw Bundle.Subscription resource with criteria (FHIR search query) and channel.type: 'rest-hook'.channel.endpoint to Bot/<BOT_ID> for automated processing.subscribeToCriteria() client-side for WebSocket real-time updates.AuditEvent changes — prevents notification spirals.AccessPolicy.resource[] with resourceType and optional criteria, readonly, hiddenFields, readonlyFields.%profile variable to scope data to the current user: Observation?performer=%profile.%patient variable for patient-portal access: Observation?subject=%patient.writeConstraint with FHIRPath for state machine enforcement (e.g., prevent status rollback).createResourceIfNoneExist(resource, query) for idempotent creates keyed on identifier.upsertResource(resource, query) for atomic create-or-update in a single request.If-None-Exist header on POST for server-side conditional creation.identifier systems (MRN, SSN, insurance ID) for deterministic matching.link field with type: 'replaced-by' for merge workflows.createResourceIfNoneExist() at ingestion to prevent duplicates.Questionnaire resources for form definitions. Use linkId for question identification.QuestionnaireResponse for captured answers. Link to Questionnaire via questionnaire field.getQuestionnaireAnswers(response) to extract answers as a map keyed by linkId.QuestionnaireResponse creation.startClientLogin) for backend services and integrations.startLogin + processCode) for user-facing web apps.localStorage in production — use secure HTTP-only cookies or server-side sessions.refreshIfExpired() before critical operations. Set gracePeriod to refresh proactively.setBasicAuth(clientId, clientSecret) only for server-side code, never in browser.$rotate-client-secret operation periodically.readonly: true or explicit interaction arrays to restrict write access.criteria with FHIR search syntax to filter visible resources (e.g., Patient?organization=Organization/123).hiddenFields to prevent sensitive fields from being returned (e.g., SSN).readonlyFields to allow viewing but prevent modification of specific fields.writeConstraint FHIRPath expressions for business rules (e.g., prevent status rollback on finalized resources).type, agent, entity, and outcome.Binary resources with securityContext for sensitive file attachments.$expunge operation for permanent deletion when required.patient/*.read style scopes for patient-facing apps.user/*.read style scopes for practitioner-facing apps.launch/patient context for apps launched within a patient context.meta.project on operations when building multi-tenant middleware.event.secrets) for API keys, connection strings, and credentials.MockClient from @medplum/mock for unit tests — it simulates the full MedplumClient API in memory.mockClient.createResource() before running test assertions.search, searchResources, searchOne, readResource, updateResource, deleteResource.new MockClient() per test to ensure isolation between test cases.await handler(mockClient, mockEvent).BotEvent objects with input, contentType, secrets, and bot fields.mockClient.searchResources() after handler execution.application/fhir+json, text/plain, x-application/hl7-v2+er7.event.secrets for bots that depend on external API keys.validateResource(resource) from @medplum/core to check resources against StructureDefinitions.OperationOutcome errors when missing.StructureDefinition resource, then validate resources against it.$validate operation for server-side validation in integration tests.name, name:exact, name:contains)._include returns related resources in the Bundle._count and _offset parameters.identifier=value vs identifier=system|value.ge, le, gt, lt.medplum/medplum-server) for local integration tests.createTestPatient(overrides?), createTestObservation(overrides?).generateId() from @medplum/core for unique test identifiers.http://example.com/test-mrn to avoid collision with real systems.OperationOutcome for error responses: check issue[].severity, issue[].code, issue[].expression.isOk(outcome) and isNotFound(outcome) from @medplum/core for status checks.deepEquals(a, b) for resource comparison (ignores meta.versionId and meta.lastUpdated).subject.reference matches expected Patient/id format.© softspark, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in app/skills/medplum-rules of softspark/ai-toolkit.
Open the folder on GitHubat commit e40ed87
Medplum Rules next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Medplum Rules this skillsoftspark/ai-toolkit | 179 | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Clinical Trials Databasegoogle-deepmind/science-skills | 3.2k | 2 repos | ~3.2k | Automated safety check: Pass | Apache-2.0 | |
| CHARLS Paper Reproduction Guidexjtulyc/MedgeClaw | 617 | 1 repos | ~1.8k | Automated safety check: Pass | None | |
| Biomedical Analysis Dispatchxjtulyc/MedgeClaw | 617 | 1 repos | ~2k | Automated safety check: Pass | None | |
| Research Proposalluwill/research-skills | 858 | — | ~4.4k | Automated safety check: Notes | None | |
| Medical Imaging ReviewLeonChaoX/qinyan-academic-skills | 943 | 3 repos | ~1.1k | Automated safety check: Notes | MIT |
google-deepmind/science-skills
Query ClinicalTrials.gov via APIv2. An agent skill from google-deepmind/science-skills.
xjtulyc/MedgeClaw
Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.
xjtulyc/MedgeClaw
Routes bioinformatics, drug discovery, clinical and multi-omics tasks from a chat interface to Claude Code sessions running K-Dense scientific skills, with a live dashboard per task.
luwill/research-skills
A skill your agent uses when the user asks to write or draft a PhD / doctoral research proposal, research plan, 研究计划书, or 开题报告 — a forward-looking plan of background, gap, research questions…
LeonChaoX/qinyan-academic-skills
Write comprehensive literature reviews for medical imaging AI research.
lamm-mit/scienceclaw
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.
softspark/ai-toolkit
Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.
softspark/ai-toolkit
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.
softspark/ai-toolkit
Analyzes code quality, complexity, patterns across codebase.
softspark/ai-toolkit
Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.
softspark/ai-toolkit
Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.
softspark/ai-toolkit
Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).
Categories
Medplum (FHIR healthcare) coding rules: style, patterns, security, testing. Medplum Rules is an agent skill from softspark/ai-toolkit. Medplum (FHIR healthcare) coding rules: style, patterns, security, testing.
Medplum Rules fits situations like: tasks that involve Clinical and healthcare research.
Run `npx skills add softspark/ai-toolkit --skill medplum-rules -a claude-code`. Or copy the skill folder (app/skills/medplum-rules in softspark/ai-toolkit) into .claude/skills/medplum-rules in your project. Claude Code loads it when a task matches its description.
Run `npx skills add softspark/ai-toolkit --skill medplum-rules -a codex`. Or copy the skill folder (app/skills/medplum-rules in softspark/ai-toolkit) into .agents/skills/medplum-rules in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add softspark/ai-toolkit --skill medplum-rules -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/medplum-rules, .gemini/skills/medplum-rules, .github/skills/medplum-rules and .opencode/skills/medplum-rules in your project.
SKILL.md names no scripts, command-line tools or credentials: Medplum Rules is instructions for the agent only. Its frontmatter pre-approves these tools: Read.
SKILL.md names 3 domains. In commands or code: hl7.org, loinc.org and snomed.info; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Medplum Rules is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Medplum Rules: Clinical Trials Database (google-deepmind/science-skills, 3.2k stars), CHARLS Paper Reproduction Guide (xjtulyc/MedgeClaw, 617 stars), Biomedical Analysis Dispatch (xjtulyc/MedgeClaw, 617 stars) and Research Proposal (luwill/research-skills, 858 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 8, 2026.
Source: softspark/ai-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.