个人作者
Sandeep Mewara
A software professional for more than 15+ years learning ...
- Skills
- 16
- 仓库
- 1
- 职业覆盖
- 4
- 场景覆盖
- 4
- Stars
- ★ 1
Sandeep Mewara 的 Skills 16
extra-role
A custom project-specific role for testing
compliance-review
Ensures regulatory compliance for financial services
extra-role
A custom role missing applies_to for testing
testing-conventions
Enforces testing standards when writing unit tests, integration tests, or agent evaluation tests. Covers test directory structure, naming conventions, fixture and setup patterns, mocking strategy, async testing, coverage requirements, and LLM-as-judge evaluation. Language-specific conventions (Python/pytest, Java/JUnit, C#/xUnit, React/Vitest) are loaded from bundled reference packs. Use this skill when writing tests, creating test files, setting up fixtures, mocking services, or reviewing test code for standards compliance.
shipping
Shipping workflow for platform services. Use this skill when creating pull requests, pushing code for review, updating Jira tickets to reflect PR status, or completing the ship cycle for a feature or bugfix. Trigger this skill when the user says things like "open a PR," "create a pull request," "ship this," "push for review," "update the ticket," "mark this as ready for review," or "I'm done with this feature" — even if they don't explicitly say "shipping." Also trigger when the user wants to transition a Jira ticket status after code changes are ready.
security-standards
Enforces security standards when writing or reviewing code that handles authentication, secrets, sensitive data, API boundaries, or compliance concerns. Covers secrets manager integration, encryption at rest and in transit, IAM authentication and least-privilege authorization, OWASP Top 10 secure coding (including prompt injection), dependency vulnerability management, API security (auth, validation, rate limiting), PII and sensitive data protection in logs and traces, and regulatory compliance (CCPA/GDPR). Use this skill when adding endpoints, handling user data, managing secrets, reviewing for vulnerabilities, configuring auth, working with LLM prompts that accept user input, setting up deployment security, or assessing compliance. Also use when DAST findings need remediation.
product-manager
Product management workflows: write PRDs and spec documents, create user stories with acceptance criteria and T-shirt sizing, plan and prioritize roadmaps by quarter, run competitor and market analysis with live web research, and review Figma designs against PRD requirements for UX consistency. Use this skill whenever the user mentions PRDs, product requirements, user stories, acceptance criteria, story points, roadmaps, feature prioritization, competitor analysis, market research, or reviewing designs against specs — even if they don't explicitly say "product management." Also trigger when the user wants to create Jira-ready tickets, publish specs to Confluence, or audit Figma mockups for missing states.
lifecycle-agent-orchestrator
Development lifecycle orchestrator that drives requirements through to pull requests. Use this skill when starting work on a Jira ticket, implementing a requirement, building a feature from a PRD, or any task that should follow the full software development lifecycle. Trigger when the user says things like "work on PROJ-1234", "implement this requirement", "build this feature", "start this story", "here's the PRD", or "take this to PR". Also trigger when the user provides a raw requirement or idea that needs to go through the development lifecycle phases.
lifecycle-agent-orchestrator-setup
Interactive setup for connecting project-specific skills to the lifecycle agent orchestrator. Scans the project for existing architecture docs, coding standards, domain knowledge, and other skill-like files, then helps the user choose between config-based mapping (lao.config.yaml) or convention-based directory structure. Generates the chosen structure and validates it. Trigger when the user says "set up the orchestrator", "configure project skills", "bootstrap the orchestrator", "connect my project", or "lao-setup".
lifecycle-agent-orchestrator-dry-run
Dry-run mode for the lifecycle agent orchestrator. Simulates the full 9-phase pipeline against a sample or custom requirement without making any real changes — no files, no git, no Jira, no PRs. Use this to validate the orchestrator workflow, demonstrate the pipeline to new users, or test overlay integration. Trigger when the user says "dry run", "simulate the lifecycle", "test the orchestrator", or "show me how the pipeline works".
intake
Reads a Jira story or user-provided requirement and produces a structured scope summary with numbered acceptance criteria. Use this skill at the start of working on any ticket to establish what needs to be built, what the success criteria are, and whether UX changes are involved. Trigger when given a Jira ticket key, a story description, or when the orchestrator needs to extract structured requirements from an unstructured input.
product-designer
Expert product designer that takes a PRD or vague brief and runs the full end-to-end design process: deep problem research (competitive benchmarking, UX research, market analysis), clarifying questions with explicit assumptions, scoped design options on a spectrum from radical to PRD-aligned, a recommendation with design rationale, and final deliverables — a structured research report and Figma-ready design spec built with your project's design system. Use this skill whenever a user shares a PRD, a feature brief, a vague design problem, or says anything like "design this", "help me think through this product", "what should this flow look like", "review this PRD", or "I need a design for X". Even if the request seems simple or partial, invoke this skill — the research and structured thinking it brings is always valuable.
coding-standards
Enforces coding standards when writing or modifying code. Covers naming conventions, exception and error handling patterns, structured logging, tracing, project structure, environment-based configuration, secrets management, app initialization, async patterns, and code quality tooling. Language-specific conventions (Python, Java, C#, React/TypeScript) are loaded from bundled reference packs. Use this skill when writing code, creating new files or modules, defining classes or functions, adding error handling, setting up project scaffolding, configuring deployment, or reviewing code for standards compliance.
code-review
Code reviewer for platform services. Use this skill when reviewing PRs, diffs, specific files, or implementation code for adherence to coding guidelines, project conventions, and architectural alignment. Trigger this skill when asked to review code, check a PR, audit a file, verify an implementation against requirements or a spec, or evaluate whether code follows project standards. Also trigger when the user says things like "look at this code," "is this implementation correct," "check this file," or "review my changes" — even if they don't explicitly say "code review."
architect
System architecture persona for designing, reviewing, and guiding implementation of platform services. Use this skill whenever you need to design a new feature or service, decompose a workflow into agents or modules, make technology or infrastructure decisions, review code or PRs for architectural alignment, produce architecture decision records (ADRs), evaluate scalability or resiliency trade-offs, or ensure security standards are met. Trigger this skill for any request involving system design, architectural review, multi-agent orchestration, service boundaries, API contracts, data flow design, or infrastructure planning — even if the user does not explicitly say "architecture."
acceptance-validation
Validates implemented code against the acceptance criteria established during intake. Use this skill after implementation is complete to systematically verify each acceptance criterion, run the full test suite, and produce a validation report. Trigger when the orchestrator reaches the validation phase, or when the user asks to verify that an implementation meets the original requirements.