Skills for your AI
Guides tracing, dataset creation, evaluation, monitoring, feedback, and CI/CD testing for LLM applications with LangSmith. Use when the user wants to set up tracing, evaluate model outputs, inspect runs, record feedback, or integrate LangSmith with LangChain o
Sets up OpenTelemetry tracing, evaluations, datasets, experiments, trace queries, feedback logging, production monitoring, and playground testing for self-hosted Phoenix LLM observability. Use when the user wants to trace an LLM app, evaluate outputs, manage d
Validates OCR-corrected text against original source images for accuracy, completeness and markdown rendering, and produces a structured validation report. Use when a corrected text file and its source image need verification, when checking for lost or added c
Guides authorized red-team reconnaissance and testing of Okta-as-IdP authentication, covering tenant discovery, user enumeration, auth flow analysis, password spray, MFA factors, OIDC/SAML misconfigurations, and admin API surface. Use when scoping or testing a
Manages microscopy images and metadata on OMERO servers via the Python API, covering sessions, data retrieval, pixel and ROI analysis, annotations, and batch scripts. Use when connecting to OMERO, listing or fetching projects, datasets, images, screens, plates
Validates 1EdTech / IMS Global OneRoster v1.1 and v1.2 CSV roster sets: manifest integrity, bulk vs delta strictness, foreign key references, and encoding sanitization. Trigger phrases: oneroster csv validator, validate oneroster zip, clever roster error, oner
Finds, validates, and escalates open redirect vulnerabilities in authorized web targets, chaining them to OAuth token theft, phishing, or SSRF. Use when given crawled URLs and a controlled test domain to hunt redirect parameters, bypass filters, test DOM-based
Guides open source contributors through environment setup, contribution discovery, style and workflow, documentation, pull request review, testing, community engagement, tool building, licensing, analytics, translation, and accessibility or security compliance
Answers build questions about OpenAI products and APIs using official developer documentation with citations. Use when the user asks how to build with Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, or Realtime, or needs doc-backed guidance on Op
Converts OpenAPI 3.0 JSON/YAML specs into TypeScript interfaces, type aliases and type guards. Use when the user provides an OpenAPI 3.0 spec file and asks to validate it, extract schemas and endpoints, generate TypeScript types, add type guards, or save the g
Installs, refreshes, re-authenticates, verifies, and configures the OpenCode agent provider (CLI and SDK pinned at 1.18.25) in a NanoClaw project. Use when adding OpenCode as a provider, updating an existing install, signing in again, checking compatibility, o
Queries the Open Targets Platform GraphQL API for target-disease associations, drug, tractability, safety, and genetic evidence data. Use when the user asks about a gene, disease, or drug identifier, druggability, safety liabilities, known drugs for a disease,
Writes Opentrons Protocol API v2 Python scripts for Flex and OT-2 liquid handling, hardware modules, labware, and liquid tracking. Use when drafting a protocol file, loading pipettes/labware/modules, writing pipetting commands, scripting module control, labeli
Turns operational data into risk registers, mitigation plans, monitoring alerts, compliance gap analyses, incident and continuity plans, vendor risk reports, and risk reports. Use when asked to identify or reduce operational risks, monitor risk indicators, rev
Quantizes large language models to 8/4/3/2/1-bit with HQQ (no calibration data), saves or pushes the result, configures mixed precision, selects inference backends, and loads pre-quantized HQQ models. Use when the user gives a model name or path and a target b
Runs a read-only overnight audit of a code repository covering security, performance, accessibility, dependencies, and code quality, then compiles a severity-rated report. Use when the user wants a full codebase audit, a security or dependency review, or a sev
Retrieves PagerDuty incident details, identifies on-call teams, analyzes likely root causes, searches GitHub for correlated code changes, and drafts remediation pull requests. Use when given an incident ID or service name, asked who is on call, asked for a lik
Debug complex issues by generating competing root-cause hypotheses across six failure categories, collecting cited evidence, arbitrating the true cause, and validating fixes. Use when a bug has multiple plausible causes, initial debugging has stalled, or a fix
Audits forgot-password and account recovery flows for username enumeration, token exposure, token replay, missing rate limits, weak token predictability, missing session/IP binding, non-expiring tokens, and Referer leaks. Use when testing a password reset endp
Generates production deployment configurations for PocketBase — systemd or Docker, reverse proxy with TLS, SMTP/S3 settings, hardening, and backups. Use when deploying PocketBase to a server, exposing it via nginx or Caddy, offloading email or storage, securin
Provides accurate PocketBase JavaScript/TypeScript SDK code examples and guidance for CRUD, authentication, realtime subscriptions, file handling, batch operations, and query syntax. Use when a user needs SDK snippets or parameter explanations for a PocketBase
Conducts authorized penetration tests through scoping, reconnaissance, exploitation, validation, and reporting. Use when planning an engagement, mapping attack surface, testing vulnerabilities, verifying fixes, running social engineering, password, wireless, o
Builds permit-ready Environmental Impact Assessment reports from data collection through impact, risk, mitigation, alternatives, consultation, compliance, monitoring and reporting. Use when starting an EIA, screening impacts, assessing risks, planning mitigati
Audits CI/CD pipeline misconfigurations across GitHub Actions, Jenkins, GitLab CI and Azure DevOps, enumerating configurations, mapping injection and supply chain attack paths, and reporting evidence with countermeasures. Use when reviewing pipeline security,
