AGENT SKILLS · MISSION KIT
Useful agent skills ranked by real adoption
Browse verified skills from public repositories. Compare what each skill does, package contents, install activity, and source evidence before adding it to your agent.
- CATALOG SCOPE
- VERIFIED
- skills
- 22,961
- repositories
- 3541
- last synced
- Nov 4, 2026
didit-protocoldidit-database-validation
Integrate Didit Database Validation API to verify personal data against government databases. Use when the user wants to validate identity against government records, verify national ID numbers, check CPF/CURP/DNI/cedula numbers, perform identity database lookups, validate identity documents against official sources, or implement database verification for Latin American or Spanish identity documents using Didit. Supports 18 countries with 1x1 and 2x2 matching methods.
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Aug 10
j4flmaodevops-opentelemetry
OpenTelemetry observability framework for distributed systems. Covers: OTel concepts (traces, metrics, logs, SDK, API, Collector, OTLP), Collector pipeline (receiver, processor, exporter, batch, sampling, tail sampling, attributes), SDK instrumentation (automatic and manual for Java, Python, Node.js, Go, .NET), trace sampling strategies (head-based, tail-based, probabilistic, consistent), multi-backend export (Jaeger, Zipkin, Prometheus, Datadog, Grafana). Do NOT use for: Vendor-specific APM age
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Sep 26
j4flmaokubernetes
Use this skill for Kubernetes cluster administration, architecture, operations, and production best practices. Covers: cluster architecture (control plane, etcd, worker nodes), networking (CNI, Service, Ingress, NetworkPolicies), storage (CSI, PVC, StorageClasses), security (RBAC, PodSecurity, secrets), scheduling (taints/tolerations, node affinity, topology spread), upgrades, backup/DR, and cluster autoscaling. Do NOT use for: application-level Kubernetes patterns (kubernetes-patterns), Helm ch
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Sep 26
uxcel-labpm-analytics
Run a product-analytics analysis that produces a decision, not a dashboard — start from the question, pick actionable over vanity metrics, separate signal from noise, segment (averages lie), pair quant with qual, and end in an insight→impact→action story. Catches the defaults Claude misses: vanity metrics, correlation-as-causation, reacting to small samples/short windows, survivorship/selection bias, unsegmented averages. Trigger when asked to analyze product data/metrics, plan what to measure,
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
uxcel-labpm-gtm-plan
Build a go-to-market plan that's a stage-appropriate system — customers, channels, pricing, timing, and partnerships that fit the company's maturity — not a generic launch checklist. Gates on GTM readiness (validated demand) and company stage, picks the right channel and entry timing, and treats the buyer journey as non-linear. Catches the defaults Claude misses: GTM-as-one-time-launch, stage-skipping, channel/timing blindness, funnel-forcing, partnerships-as-shortcut. Trigger when asked to crea
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
uxcel-labpm-product-review
Orchestrated review of a PM artifact (spec, PRD, OKRs, roadmap, prioritization, strategy). Routes by artifact type to the right audits, auto-runs the always-relevant assumption check, and returns one prioritized report. Trigger when the user asks for a full review of a PM document, "review my spec/roadmap/OKRs", "is this PRD solid", or general PM feedback — but NOT when they name a single specific audit.
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
uxcel-labux-heuristics-audit
Run a structured usability audit of any UI against Nielsen's 10 heuristics. Produces a severity-rated, prioritized issue list — each finding tagged with the violated heuristic and a concrete fix. Use when auditing a screen, flow, or component for usability problems, or as a validation step after generating UI.
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
uxcel-labux-iconography
Choose and design UI icons that are understood, not just decorative — universal metaphors, one consistent style, text/accessible labels where meaning isn't obvious, legible at small sizes, and adequate touch targets. Replaces ambiguous icon-only buttons and mixed icon styles with a system. Trigger when asked to add or pick icons, design an icon set, decide filled vs outlined, label icons, fix inconsistent/ambiguous iconography, or choose between a system library (SF Symbols/Material) and custom
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
uxcel-labux-information-architecture-audit
Run a structured information architecture audit on a sitemap, navigation tree, category structure, menu labels, or multi-screen product. Produces a severity-rated issue list with concrete fixes — catches scheme/task mismatches, narrow-and-deep hierarchies, low-information-scent labels, inconsistent labeling systems, single-path findability, and dead-end pages. Use when auditing IA, site structure, categories, taxonomy, or labels, or as a validation step after generating navigation or any multi-s
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
uxcel-labux-loaders-and-progress
Design or critique loading states and progress indicators — match the feedback type (spinner, text, determinate bar, skeleton, progress tracker) to the wait duration and task structure, and manage perceived performance. Trigger when the user asks to design or review loaders, spinners, loading states, skeleton screens, progress bars, progress trackers, steppers, or multi-step flow progress.
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
uxcel-labux-search
Design or critique search experiences — search input, auto-suggest, results page, filtering/sorting, and zero-results recovery. Matches search features to how users actually seek (known-item vs. exploratory) and gates levers like rich suggestions, filter layout, and chips. Trigger when the user asks to design or review search, a search bar, autocomplete/auto-suggest, search results, filters, sorting, or a "no results" page.
- 1h installs
- 1
- GitHub stars
- 27
- Updated
- Jul 2
sstoboai-elements-workflow
This skill provides guidance for building workflow visualizations using Vercel AI Elements and React Flow. It should be used when implementing interactive node-based interfaces, workflow diagrams, or process flow visualizations in Next.js applications. Covers Canvas, Node, Edge, Connection, Controls, Panel, and Toolbar components.
- 1h installs
- 1
- GitHub stars
- 25
- Updated
- Jan 21
sstobobetterauth-tanstack-convex
Step-by-step guide for setting up Better Auth authentication with Convex and TanStack Start. This skill should be used when configuring authentication in a Convex + TanStack Start project, troubleshooting auth issues, or implementing sign up/sign in/sign out flows. Covers installation, environment variables, SSR authentication, route handlers, and the expectAuth pattern.
- 1h installs
- 1
- GitHub stars
- 25
- Updated
- Jan 21
amirtaherkhaninestjs-oop-design-patterns
Applies pragmatic OOP, SOLID, object-design rules, and design patterns to NestJS and TypeScript code. Use when writing or refactoring controllers, providers, use cases, entities, value objects, repositories, adapters, factories, strategies, handlers, or tests; when diagnosing god services, primitive obsession, inheritance misuse, duplicated conditionals, or leaky abstractions; and when selecting a pattern without over-engineering. Do not use for pure functional codebases or non-NestJS frontend w
- 1h installs
- 1
- GitHub stars
- 8
- Updated
- Aug 2
zguiyangpi-delegate
Delegate one bounded atomic coding or investigation task to a local Pi worker with a structured task contract, explicit model/session control, direct-or-isolated write policy, and a structured result. Use after the calling agent has decided the task and must independently review the result.
- 1h installs
- 1
- GitHub stars
- 3
- Updated
- Oct 4
allanyiinproblem-decomposer
當使用者要拆解大型、混亂、跨部門、反覆卡關或高不確定性的難題，或明確要求做問題拆解、issue tree、根因與對策分層時使用。先分清楚現象、目標落差、真正問題與根因假設，再判斷問題是範疇型、分析型、動態系統型、研究型或交付型，最後用 issue tree/MECE、WBS、系統思考、驗收標準、依賴排程、資源分派與流動指標，產出可執行的問題拆解報告、工作包、關鍵路徑、並行策略與 PDCA 回饋節奏。
- 1h installs
- 1
- GitHub stars
- 2
- Updated
- Mar 29
ryanxkhcareer-coach
Use when the user wants to build a Career Blueprint, explore career goals, assess their skills, or create a structured career development plan. Also use when the user says "coach me", "career plan", "career blueprint", or asks for help thinking through their career direction.
- 1h installs
- 1
- GitHub stars
- 2
- Updated
- Mar 10
jupid-taxform-1040-es
Use this skill when an individual taxpayer needs to compute, schedule, or pay federal estimated income tax for the current year using Form 1040-ES. Triggers on phrases like "estimated tax payment", "1040-ES", "quarterly tax payment", "self-employment estimated tax", "avoid underpayment penalty", "how much should I pay quarterly", "safe harbor estimated tax", "Roth conversion estimated tax". Do NOT use for: corporate estimated tax (Form 1120-W), employer payroll tax deposits (Form 941/944), W-2 w
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Jul 17
jupid-taxform-2210
Use this skill when an individual filer needs to determine whether they owe an underpayment of estimated tax penalty and how much, or whether they meet one of the safe harbors that exempts them from the penalty. Triggers on phrases like "underpayment penalty", "Form 2210", "estimated tax penalty", "should I file 2210", "annualized income method", "Schedule AI", "safe harbor estimated tax", "I owe more than $1,000, do I have a penalty", "uneven income annualized", "withholding wasn't enough", or
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Jul 17
kezsmeisterannual-eps
Extract annual Diluted EPS for one or more public company tickers (comma-separated) by browsing Yahoo Finance in Chrome. Produces two markdown tables per ticker - (1) raw annual EPS for the past 10 years and (2) YoY growth rate. Use when the user wants annual EPS data, EPS history, or earnings per share trends for a stock.
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Feb 26
adminiumjsadminium-project
Work in an Adminium project folder — the code-first way to run Adminium — beyond an app's own files. Use for adminium.config.ts and databases, page and schema files, custom dashboard pages and widgets written in React, hooks that run before or after a record is saved, actions that add a button running your code, pulling Studio changes into files, checking and deploying a project.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 4
gharib89setup-harness
Set up this repo's agent harness for Claude Code: one check entry point (scripts/check.sh), a pre-commit runner, the linters, formatters, typecheckers and tests it runs, hooks that run them after every edit and at every turn end, vendored language servers proven by a real LSP hover, and a cloud setup that installs them in every Claude Code on the web session, proven in a real one; each third-party tool pinned and passed through an install check. Independent of Ship; run it before /setup-skills.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 4
gillesdandreajira
Jira through the acli CLI. Use on any Jira issue key (e.g. ABC-123), JQL, or a request to view, search, create, edit, comment on, transition, assign, or link Jira work, or to download its attachments.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 14
gillesdandreazod
Zod 4.5 idioms. Use when writing or editing a Zod schema, customizing validation errors, writing transforms or codecs, or converting between Zod and JSON Schema.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 14