oaknational
101 verified skills303 total stars
clerk-testing
E2E testing for Clerk apps. Use with Playwright or Cypress for auth flow tests.
testing3
clerk-orgs
Clerk Organizations for B2B SaaS - create multi-tenant apps with org switching, role-based access, verified domains, and enterprise SSO. Use for team workspaces, RBAC, org-based routing, member management.
data-ai3
clerk-expert
Active workflow skill for Clerk planning, research, and implementation support. Grounded in current official Clerk documentation with Vercel (Express) + shared Clerk instance as the default deployment context. Use when the working agent needs Clerk expertise for active tasks — distinct from the clerk-reviewer, which is a read-only assessment specialist.
testing3
design-system-expert
Active workflow skill for design token and visual consistency planning, research, and implementation support. Grounded in the DTCG standard, three-tier token model, and CSS custom properties with live-standards-first doctrine. Use when the working agent needs design system expertise for active tasks — distinct from the design-system-reviewer, which is a read-only assessment specialist.
development3
ground-truth-evaluation
Evaluate and validate ground truths for Oak semantic search using the COMMIT protocol. Use when reviewing existing ground truths, diagnosing low MRR scores, interpreting benchmark results, or running pnpm benchmark.
testing3
start-right-quick
Apply the repository start-right quick grounding workflow to the active session. Use when the user asks to start right, re-ground work, or explicitly apply the shared start-right-quick skill guidance and linked directives before or during task execution.
testing3
clerk-nextjs-patterns
Advanced Next.js patterns - middleware, Server Actions, caching with Clerk.
tools3
clerk-setup
Add Clerk authentication to any project by following the official quickstart guides.
testing3
clerk-webhooks
Clerk webhooks for real-time events and data syncing. Listen for user creation, updates, deletion, and organization events. Build event-driven features like database sync, notifications, integrations.
development3
design-system-expert
Active workflow skill for design token architecture, CSS custom property governance, and visual consistency grounded in DTCG JSON and the project three-tier token model.
development3
elasticsearch-expert
Active workflow skill for Elasticsearch planning, research, and implementation support grounded in current official Elastic documentation with Elastic Serverless as the default deployment context.
testing3
jc-metacognition
Reflective thinking — read and apply the metacognition directive.
tools3
jc-start-right-quick
Quick session grounding — load context and start working.
tools3
react-component-expert
Active workflow skill for React component architecture, hooks correctness, render performance, and composition patterns grounded in official React documentation.
development3
receiving-code-review
How to process code review feedback effectively. Understand before acting, verify suggestions, ask for clarification.
development3
worktrees
When and how to use git worktrees for isolated work.
tools3
patterns
Check .agent/memory/patterns/ for known solutions to recurring design problems before inventing a new approach. Triggered when facing code, architecture, process, testing, or agent infrastructure decisions.
development3
accessibility-expert
Active workflow skill for accessibility planning, auditing, and remediation grounded in WCAG 2.2 AA and WAI-ARIA Authoring Practices.
testing3
clerk-webhooks
Clerk webhooks for real-time events and data syncing. Listen for user creation, updates, deletion, and organization events. Build event-driven features like database sync, notifications, integrations.
development3
worktrees
When and how to use git worktrees for isolated work.
tools3
napkin
Maintain a per-repo napkin file at .agent/memory/napkin.md. Always active. Read distilled.md and napkin.md before doing anything. Write continuously.
documentation3
react-component-expert
Active workflow skill for React component architecture, hooks correctness, render performance, and composition patterns grounded in official React documentation.
development3
systematic-debugging
Structured debugging workflow: reproduce, isolate, hypothesise, verify, fix, regression test.
development3
elasticsearch-expert
Active workflow skill for Elasticsearch planning, research, and implementation support grounded in official Elastic documentation.
testing3
go
Load the shared GO execution workflow from `.agent/skills/go/shared/go.md`.
development3
complex-merge
Structured workflow for merging significantly diverged branches. Use when either branch has changed 100+ files, a dry-run merge produces 10+ conflicts, or the other branch refactored core interfaces your branch consumes.
development3
finishing-branch
Branch completion checklist. Use before merging or creating a PR. Covers quality gates, commit hygiene, documentation updates, and PR description.
testing3
parallel-agents
Guidance on dispatching parallel sub-agents safely. Use when facing multiple independent tasks that can be worked on without shared state or sequential dependencies.
testing3
patterns
Check .agent/memory/patterns/ for known solutions to recurring design problems before inventing a new approach. Triggered when facing code, architecture, process, testing, or agent infrastructure decisions.
development3
sentry-expert
Active workflow skill for Sentry and OpenTelemetry planning, research, and implementation support. Grounded in current official Sentry and OpenTelemetry documentation with Vercel Node.js plus the HTTP MCP server and Search CLI as the default Oak deployment context.
tools3
worktrees
When and how to use git worktrees for isolated work. Use for parallel development, risky experiments, or review work that should not affect the main working directory.
development3
chatgpt-report-normalisation
Recover ChatGPT-, deep-research-, or other LLM-exported reports from paired markdown, DOCX, and PDF copies into source-faithful clean markdown by copying content as faithfully as possible, repairing structure, and using the DOCX to repair real links.
documentation3
clerk-expert
Active workflow skill for Clerk planning, research, and implementation support grounded in current official Clerk documentation with Vercel (Express) + shared Clerk instance as the default deployment context.
testing3
clerk-testing
E2E testing for Clerk apps. Use with Playwright or Cypress for auth flow tests.
testing3
create-mcp-app
This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.
tools3
finishing-branch
Branch completion checklist: quality gates, commit hygiene, documentation, PR description.
testing3
jc-commit
Create a well-formed commit for current changes with conventional message format.
development3
jc-consolidate-docs
Consolidate documentation, extract patterns, verify plan hygiene, and check fitness functions.
testing3
jc-session-handoff
Lightweight end-of-session continuity update with a conditional consolidation gate.
tools3
migrate-oai-app
This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK. Provides step-by-step migration guidance with API mapping tables.
tools3
start-right-quick
Quick grounding at session start — read directives and check practice box.
testing3
clerk-nextjs-patterns
Advanced Next.js patterns - middleware, Server Actions, caching with Clerk.
tools3
clerk-setup
Add Clerk authentication to any project by following the official quickstart guides.
testing3
clerk
Clerk authentication router. Use when user asks about adding authentication, setting up Clerk, custom sign-in flows, Next.js patterns, organizations, syncing users, or testing. Automatically routes to the specific skill based on their task.
testing3
clerk-expert
Active workflow skill for Clerk planning, research, and implementation support grounded in official Clerk documentation.
testing3
design-system-expert
Active workflow skill for design token architecture, CSS custom property governance, and visual consistency grounded in DTCG JSON and the project three-tier token model.
development3
ground-truth-design
Design ground truth queries for the Oak semantic search service using known-answer-first methodology.
content-media3
parallel-agents
Guidance on dispatching parallel sub-agents safely for independent tasks.
data-ai3
tsdoc
TSDoc and documentation workflow for canonical source comments, README updates, and ADR touchpoints.
documentation3
jc-start-right-thorough
Thorough session grounding for complex, cross-workspace, or architectural work.
tools3
accessibility-expert
Active workflow skill for accessibility planning, research, and implementation support. Grounded in WCAG 2.2 AA, WAI-ARIA 1.3 Editor's Draft, and axe-core with live-standards-first doctrine. Use when the working agent needs a11y expertise for active tasks — distinct from the accessibility-reviewer, which is a read-only assessment specialist.
testing3
accessibility-expert
Active workflow skill for accessibility planning, auditing, and remediation grounded in WCAG 2.2 AA and WAI-ARIA Authoring Practices.
testing3
add-app-to-server
This skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add a view to my MCP tool", "enrich MCP tools with UI", "add interactive UI to existing server", "add MCP Apps to my server", or needs to add interactive UI capabilities to an existing MCP server that already has tools. Provides guidance for analyzing existing tools and adding MCP Apps UI resources.
tools3
assumptions-expert
Active workflow skill for conducting assumption audits during planning phases. Grounded in the inverted doctrine hierarchy (project principles first, external expertise last). Use when the working agent needs to challenge proportionality, validate assumptions, or audit blocking relationships — distinct from the assumptions-reviewer, which is a read-only assessment specialist.
testing3
assumptions-expert
Active workflow skill for assumption auditing during planning phases. Grounded in the inverted doctrine hierarchy (project principles first, external expertise last).
testing3
chatgpt-report-normalisation
Recover ChatGPT-, deep-research-, or other LLM-exported reports from paired markdown, DOCX, and PDF copies into source-faithful clean markdown by copying content as faithfully as possible, repairing structure, and using the DOCX to repair real links.
documentation3
chatgpt-report-normalisation
Recover ChatGPT-, deep-research-, or other LLM-exported reports from markdown, DOCX, and PDF copies into clean repo-quality markdown with real links, stripped artefacts, inline footnotes, and a dated accuracy sweep of unstable claims.
testing3
clerk
Clerk authentication router. Use when user asks about adding authentication, setting up Clerk, custom sign-in flows, Next.js patterns, organizations, syncing users, or testing. Automatically routes to the specific skill based on their task.
testing3
clerk-custom-ui
Customize Clerk component appearance - themes, layout, colors, fonts, CSS. Use for appearance styling, visual customization, branding.
development3
clerk-custom-ui
Customize Clerk component appearance - themes, layout, colors, fonts, CSS. Use for appearance styling, visual customization, branding.
development3
clerk-custom-ui
Customize Clerk component appearance - themes, layout, colors, fonts, CSS. Use for appearance styling, visual customization, branding.
development3
clerk-nextjs-patterns
Advanced Next.js patterns - middleware, Server Actions, caching with Clerk.
tools3
clerk
Clerk authentication router. Use when user asks about adding authentication, setting up Clerk, custom sign-in flows, Next.js patterns, organizations, syncing users, or testing. Automatically routes to the specific skill based on their task.
testing3
clerk-orgs
Clerk Organizations for B2B SaaS - create multi-tenant apps with org switching, role-based access, verified domains, and enterprise SSO. Use for team workspaces, RBAC, org-based routing, member management.
data-ai3
clerk-testing
E2E testing for Clerk apps. Use with Playwright or Cypress for auth flow tests.
testing3
clerk-webhooks
Clerk webhooks for real-time events and data syncing. Listen for user creation, updates, deletion, and organization events. Build event-driven features like database sync, notifications, integrations.
development3
complex-merge
Structured workflow for merging significantly diverged branches. 7-phase process with gap analysis and reviewer validation.
research3
convert-web-app
This skill should be used when the user asks to "add MCP App support to my web app", "turn my web app into a hybrid MCP App", "make my web page work as an MCP App too", "wrap my existing UI as an MCP App", "convert iframe embed to MCP App", "turn my SPA into an MCP App", or needs to add MCP App support to an existing web application while keeping it working standalone. Provides guidance for analyzing existing web apps and creating a hybrid web + MCP App with server-side tool and resource registration.
tools3
elasticsearch-expert
Active workflow skill for Elasticsearch planning, research, and implementation support. Grounded in current official Elastic documentation with Elastic Serverless as the default deployment context. Use when the working agent needs Elasticsearch expertise for active tasks — distinct from the elasticsearch-reviewer, which is a read-only assessment specialist.
testing3
finishing-branch
Branch completion checklist: quality gates, commit hygiene, documentation, PR description.
testing3
go
Re-ground and structure execution with ACTION/REVIEW/GROUNDING cadence. Use when the user asks to go, re-ground work mid-session, or explicitly apply the GO workflow to structure task execution with periodic self-assessment.
development3
ground-truth-design
Design ground truth queries for the Oak semantic search service using known-answer-first methodology. Use when creating new ground truths, redesigning existing queries, or working with files in src/lib/search-quality/ground-truth/.
testing3
ground-truth-design
Design ground truth queries for the Oak semantic search service using known-answer-first methodology.
content-media3
ground-truth-evaluation
Evaluate and validate ground truths for Oak semantic search using the COMMIT protocol.
testing3
ground-truth-evaluation
Evaluate and validate ground truths for Oak semantic search using the COMMIT protocol.
testing3
jc-chatgpt-report-normalisation
Normalise a ChatGPT/LLM-exported report into clean markdown with durable citations.
testing3
jc-gates
Run all quality gates and fix issues.
testing3
jc-go
Re-ground and structure execution with ACTION/REVIEW/GROUNDING cadence.
development3
jc-plan
Create or promote a plan following the plan architecture.
tools3
jc-review
Perform a code review with specialist sub-agents.
development3
systematic-debugging
Structured debugging workflow. Use when encountering bugs, test failures, or unexpected behaviour. Reproduce, isolate, hypothesise, verify, fix, regression test.
development3
mcp-expert
Active workflow skill for MCP planning, research, and implementation support. Grounded in the current canonical MCP specification and ext-apps extension docs with live-spec-first doctrine. Use when the working agent needs MCP expertise for active tasks — distinct from the mcp-reviewer, which is a read-only assessment specialist.
tools3
mcp-expert
Active workflow skill for MCP planning, research, and implementation support grounded in the current canonical MCP specification and ext-apps extension docs with live-spec-first doctrine.
tools3
mcp-expert
Active workflow skill for MCP planning, research, and implementation support grounded in the current canonical MCP specification.
tools3
napkin
Maintain a per-repo napkin file at .agent/memory/napkin.md that tracks mistakes, corrections, surprises, and what works. Always active, every session, unconditionally. Read distilled.md and napkin.md before doing anything. Write to the napkin continuously as you work. Log your own mistakes, not just user corrections.
documentation3
napkin
Maintain a per-repo napkin file at .agent/memory/napkin.md. Always active. Read distilled.md and napkin.md before doing anything. Write continuously.
documentation3
parallel-agents
Guidance on dispatching parallel sub-agents safely for independent tasks.
data-ai3
patterns
Check .agent/memory/patterns/ for known solutions to recurring design problems before inventing a new approach.
testing3
patterns
Check .agent/memory/patterns/ for known solutions to recurring design problems before inventing a new approach.
testing3
react-component-expert
Active workflow skill for React component architecture, hook patterns, render performance, and composition support. Grounded in the official React documentation with live-docs-first doctrine. Use when the working agent needs React expertise for active tasks — distinct from the react-component-reviewer, which is a read-only assessment specialist.
development3
receiving-code-review
How to process code review feedback effectively. Understand before acting, verify suggestions technically, ask for clarification when needed. Complements the reviewer sub-agents.
development3
receiving-code-review
How to process code review feedback effectively. Understand before acting, verify suggestions, ask for clarification.
development3
sentry-expert
Active workflow skill for Sentry and OpenTelemetry planning, research, and implementation support grounded in official Sentry and OpenTelemetry documentation.
testing3
start-right-quick
Load the shared start-right-quick grounding workflow from `.agent/skills/start-right-quick/shared/start-right.md`.
data-ai3
start-right-thorough
Apply the repository start-right-thorough grounding workflow to the active session. Use for high-risk, cross-workspace, architectural, or planning-heavy work where full one-gate-at-a-time discipline is required from the start.
testing3
start-right-thorough
Thorough grounding at session start for complex, cross-workspace, or architectural work.
tools3
start-right-thorough
Load the shared thorough start-right workflow from `.agent/skills/start-right-thorough/shared/start-right-thorough.md`.
data-ai3
systematic-debugging
Structured debugging workflow: reproduce, isolate, hypothesise, verify, fix, regression test.
development3
tsdoc
Write and audit canonical TSDoc plus the adjacent README or ADR updates that belong with a code change.
development3
clerk-setup
Add Clerk authentication to any project by following the official quickstart guides.
testing3
clerk-orgs
Clerk Organizations for B2B SaaS - create multi-tenant apps with org switching, role-based access, verified domains, and enterprise SSO. Use for team workspaces, RBAC, org-based routing, member management.
data-ai3