Claude Skills by thedixitjain

../../../engineering-team/skills/senior-computer-vision/SKILL.md

Complete toolkit for senior fullstack with modern tools and best practices.

'Implement advanced error capture and context enrichment with Sentry. Use when adding captureException/captureMessage calls, enriching errors with user context, tags, breadcrumbs, or custom fingerprinting. Trigger with \"sentry error capture\", \"sentry context\", \"enrich sentry errors\", \"sentry exception handling\", \"sentry breadcrumbs\", \"sentry fingerprint\". '

'Configure Sentry across development, staging, and production environments with separate DSNs, environment-specific sample rates, per-environment alert rules, and dashboard filtering. Use when setting up Sentry for dev/staging/production, managing environment-specific configurations, isolating data between environments, or configuring .env files for per-environment DSNs. Trigger: \"sentry environments\", \"sentry staging setup\", \"multi-environment sentry\", \"sentry dev vs prod\", \"sentry ...

'Build reliable Sentry integrations with graceful degradation, circuit breakers, and offline queuing. Use when implementing fault-tolerant error tracking, handling SDK initialization failures, building retry logic for Sentry transports, or ensuring apps survive Sentry outages. Trigger with \"sentry reliability\", \"sentry circuit breaker\", \"sentry offline queue\", \"sentry graceful degradation\", \"sentry failover\", or \"resilient sentry setup\". '

One sentence - what this skill does and when to invoke it

'Diagnose and fix SerpApi errors: invalid keys, exhausted credits, blocked searches. Use when SerpApi returns errors, empty results, or unexpected status codes. Trigger: \"serpapi error\", \"fix serpapi\", \"serpapi not working\", \"serpapi empty results\". '

Registers external services with health checks, central config, and unified execution. Use when integrating multiple external services needing coordination.

Import cookies from your real Chromium browser into the headless browse session. (gstack)

Walk a user through setup or installation one step at a time with the remaining steps visible.

Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

\"Set up Promptbook \\u2014 connect your account to start tracking builds.\\n\\ Use when the user wants to enable session analytics on promptbook.gg.\\nTrigger with\\ \\ \\\"/setup\\\" or \\\"set up promptbook\\\".\\n\"

Sexual Health Analyzer

Use when running the final pre-submission preflight for Social Forces (SF) via ScholarOne Manuscript Central — double-anonymized preparation with a separate title page, the reference-inclusive 10,000-word cap, the 10 tables-and-figure-panels limit, Chicago 17th author-date, the data availability statement, ORCID, and the $50 processing fee. Final checks; it does not draft content.

Use when building tables and figures for a Social Forces (SF) manuscript. SF imposes a hard limit of 10 tables and figure panels and a 10-page supplementary-materials cap, so exhibits must be selected and consolidated deliberately. Designs and rations exhibits; it does not run the analysis.

Use when building the theoretical argument of a Social Forces (SF) manuscript into a portable, general-audience contribution — whether the work is quantitative, demographic, comparative-historical, ethnographic, network, or computational. SF prizes a theoretically grounded result over a bare finding. Structures the argument; it does not run analyses.

Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates

检测项目技术栈的通用方法，通过分析配置文件识别语言、框架、工具链

SharePoint Automation: manage sites, lists, documents, folders, pages, and search content across SharePoint and OneDrive

sharp-edges

Audits shell scripts for correctness, portability, and common pitfalls. Use when reviewing shell scripts or before committing shell changes.

Use when all plan tasks are done and green to review, archive planning artifacts, and ask how to finish.

'Implement Shopify Plus access control patterns with staff permissions, multi-location management, and Shopify Organization features. Use when building apps for Shopify Plus merchants, implementing per-staff permissions, or managing multi-store organizations. Trigger with phrases like \"shopify permissions\", \"shopify staff\", \"shopify Plus organization\", \"shopify roles\", \"shopify multi-location\". '

Rewrite the previous response more briefly while preserving the substance.

Automate project management workflows in Shortcut -- create stories, manage tasks, track epics, and organize workflows through natural language commands.

Problem-solving strategies for sigma algebras in measure theory

Use when deciding what accompanies a SIGMOD submission beyond the 12 pages, covering extended technical reports, anonymized code and data links that survive multi-round review, appendix placement relative to the unlimited reference pages, and what reviewers actually open during a PACMMOD round.

'Simulate flash loan strategies with profitability calculations and risk assessment across Aave, dYdX, and Balancer. Use when simulating flash loans, analyzing arbitrage profitability, evaluating liquidation opportunities, or comparing flash loan providers. Trigger with phrases like \"simulate flash loan\", \"flash loan arbitrage\", \"liquidation profit\", \"compare Aave dYdX\", \"flash loan strategy\", or \"DeFi arbitrage simulation\". '

Use this skill whenever simulating a Simulink model, running the sim command, setting up SimulationInput objects, passing input signals via timeseries or datasets, configuring model or block parameters programmatically, or accessing logged output data from SimulationOutput. Trigger for any request involving sim(), Simulink.SimulationInput, Simulink.SimulationOutput, logsout, setExternalInput, or setModelParameter.

Throwaway HTML mockups: 2-3 design variants to compare.

'Execute analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task. Acts as a universal skill chameleon that learns from other plugins. Activates when you request \"skill adapter\" functionality. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose. '

Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type

GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode

| Create new skills following the GBrain conformance standard. Generates SKILL.md with frontmatter, Contract, Phases, Output Format, and Anti-Patterns. Checks MECE against existing skills. Updates manifest and resolver.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Structured multi-provider AI debates between Claude and available advisors — use for critical decisions

Present options with trade-offs for informed decision-making — use when choosing between approaches

Skill Development Rules

Reverse-engineer design systems, tokens, and components from live products or screenshots

Use when starting a complex or ambiguous task that risks scope drift

Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage

Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence

Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.

Analyze Rails apps and provide upgrade assessments

Use when a reviewer, CI bot, or another AI leaves feedback to address

Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert

Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.

Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.

Auditoria e evolucao do ecossistema de skills. Qualidade de codigo, seguranca, custos, gaps, duplicacoes, dependencias e relatorios de saude.

Package and finalize completed work for delivery — use when a feature is done and ready to ship