人気上昇中の Agent Skills
2104 件のスキルEvidence-led web performance optimization using real-user signals and browser traces to improve loading speed and runtime responsiveness.
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
A structured approach to writing runbooks, troubleshooting entries, migration and deprecation guides for readers who execute steps under time pressure.
Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems.
Manages datasets, tables, and jobs in BigQuery, enabling SQL queries, data ingestion, and basic analysis.
Configure email verification, password reset flows, password policies, and custom hashing algorithms for Better Auth email/password authentication.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
A toolkit for creating animated GIFs optimized for Slack, providing constraints, validation tools, and animation concepts.
Build comprehensive attack trees to visualize threat paths, useful for mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
Delegation mode for open-code-review (OCR).
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase.
Guidance on writing fast, robust, modern Svelte code, covering reactivity, event handling, styling, and library integration.
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
TanStack React Start auth patterns with @clerk/tanstack-react-start
Recommend the right Stripe Connect integration configuration based on your business description or company URL.
Set up Sentinel production error capture in your own Convex deployment.
dbs-learning breaks a topic into sequential learning articles and adjusts the depth, angle, and pace of subsequent content based on user feedback.
Score any website the way an Awwwards jury would, from evidence alone.
A structured approach for writing proposals, RFCs, design docs, specs, or migration plans, with decision boxes and completeness checks.
Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.
Helps users write syntactically and semantically correct primary constructors in Dart and migrate to or use the new constructor syntax.
Golang package and module lookup via `godig`, a pkg.go.dev API client (CLI + MCP server).
Validate Unity 6+ URP Render Graph renderer features for correctness in resource wiring, material binding, execution structure, descriptor usage, and global resource exposure.
Use when writing a postmortem, incident report, or root-cause analysis after an outage, a defect that reached users, a data issue, or a near miss - or when turning an incident channel, alert log, or war-room thread into a durable document.
Prove a Convex feature works — seed, drive as multiple mocked users via convex-test, assert behavior including the negative authz cases (wrong user refused, data-scope enforced).
Decode content resonance mechanisms, audience emotions, effective stances, and sharing motivations using communication and social psychology theories, and provide discussion directions for chat rooms.
Apply when tempted to ask 'should I do X?' on reversible work.
Record decisions using ADR or decision log formats to persist choices and their rationale.
Analyze X (Twitter) posts for viral potential using the actual recommendation algorithm.
Run every Convex audit (authz, reviewer, advisor, insights) into one scored, deduped readiness report with an ordered fix plan — Lighthouse for your backend.
Updates the official dbskill while preserving other skills and user data.
Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors.
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result.
Unity UI Toolkit expert for Unity 6.0+ that understands, edits, and generates UXML and USS files with flex-based layouts.
Operate the Clerk CLI for authentication, user/org/session management, impersonation, local webhook testing, deploy verification, instance config, env keys, feature toggles, and any Clerk API call.
The dbs-standard-answer skill mines relevant industries, disciplines, and credible theories from the user's theory, viewpoint, or dilemma, directly answers the question, and then extracts conditional standard answers through historically isomorphic cases.
Use diagrams to document business processes, workflows, lifecycles, and system interactions, treating diagrams as source code.
Deploy Expo apps to the app stores with EAS - build and submit to the iOS App Store, Google Play Store, and TestFlight, configure eas.json build and submit profiles, manage app versions and build numbers, and publish App Store metadata and ASO.
Install and authenticate Link CLI for agent payments, financial insights, or both.
Generate game content procedurally — seeded deterministic RNG, value/Perlin/ Simplex noise for terrain and heightmaps, grid dungeon generation (rooms + corridors, BSP, random walk), and weighted loot/drop tables.
Accessibility engineering for product interfaces, used when building or reviewing UI components and custom widgets, or when users report keyboard or screen-reader issues.
Turn a local folder into a stable, searchable, and maintainable knowledge base for agents, with navigation, versioning, health checks, and SOT tiered governance.
Drive a Next.js route to instant navigation via a test-driven agentic loop under Cache Components, and guard against regression.
Turn an investment agent into a supply-chain bottleneck hunter.