neilsanghrajka

Use for Drip Meta Ads CLI work: Meta account/Page preflight, env mapping, paused Facebook campaign creation, Graph fallback commands, redaction, safety rules, and Performance Marketer evidence.

Use for Drip Builder work. Builder turns the user's selected Fashion Designer product images into a reviewed, deployed, one-page limited-drop site and writes builder-output.json.

Use for generic Exa Search API research. Provides auth, request-shape, date-filter, batching, highlights, error-handling, and compact JSON evidence guidance for arbitrary caller-supplied queries. Query-agnostic; does not decide what to search for.

Use for Drip Fashion Designer work. Fashion Designer turns approved Scout ideas into polished product mockups through three thin product-lane agents, lightweight curation, and fashion-designer-output.json.

Use when a sandbox task needs to operate Meta Ads through the `meta` CLI: account/page preflight, campaign/ad set/ad/creative creation or updates, optional read-only status checks, insights reads, catalog/dataset/pixel checks, env mapping, command safety, redaction, and paused-by-default ad operations.

Use for Drip Performance Marketer work. Performance Marketer turns a generated Builder drop-site URL plus selected product images into one paused Facebook-only drop-of-week ad artifact, writes performance-marketer-output.json, and stops before activation, spend, insights readback, or optimization loops.

Use for Drip Scout cultural-moment discovery. Scout is an end-to-end AI employee that coordinates X and Exa research subagents, judges evidence-informed cultural moments, and writes scout-output.json with five diverse fashion-plausible candidates by default.

Use for generic X public-data research, trend discovery, recent-post checks, and social attention signals. Provides app-only bearer auth, endpoint patterns, field selection, error handling, and compact JSON evidence guidance.

Use when implementing one focused performance hypothesis on a branch: make the smallest viable code change, measure it against the shared benchmark, and leave a clean handoff for evaluation.

Use when the team needs a repeatable benchmark or evaluation harness before parallel optimization work begins, so every candidate change is tested with the same command, data shape, and success criteria.

Use when multiple optimization candidates exist and you need to benchmark them consistently, compare impact and risk, pick the winner, and explain the outcome clearly enough for a demo or PR.

Use when you need to add lightweight performance instrumentation, capture a baseline, and identify the slowest endpoint or hot path with enough trace detail for planning and optimization.

Use when you have baseline trace evidence and need to turn it into ranked optimization hypotheses, parallel engineering workstreams, and a clear plan for which ideas should be tested first.

Use when the winning optimization is chosen and you need a crisp PR-ready snapshot: problem, evidence, benchmark table, code change summary, risk notes, and the exact story to tell in a demo.

Use when starting from an unfamiliar repository or GitHub URL and you need a fast performance-focused intake: how to run it, where the user-facing surfaces are, which endpoint is best to optimize, and what the next agents need.

Create and orchestrate a Claude Code agent team for feature implementation

Run an agent team to implement a planned feature

Post-merge cleanup for a completed feature

Naming conventions for features, branches, docs, and commits

Brainstorm a feature, produce design + e2e test plan, and create a draft PR

Generate blackbox e2e smoke test plans for features

How to use the nudge CLI — commands, flags, setup, and onboarding. Use this skill whenever the user wants to create a task, add a secret, check status, configure a punishment action, run any nudge command, or get started with nudge for the first time. Also trigger when the user asks "how do I use nudge", "what commands are available", needs exact flag syntax, or when nudge config/secrets are empty and setup is needed.

Accountability coaching behavior for nudge — psychology, messaging, verification, and strictness. Use this skill whenever composing messages for task creation, reminders, completion, or failure. Also use when the user says "I'm done" and needs verification, tries to cancel or reduce a punishment, says "just cancel it", "I'll do it tomorrow", asks for more time, or tries to negotiate their way out of consequences. Trigger for any nudge interaction where tone, motivation, or judgment about completion matters.

Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.

Use for Jira work through the official Atlassian Rovo MCP Server. Prefer this skill for team Jira tasks, project lookup, issue search, issue creation, and project-specific workflow defaults.

Review open Jira bugs in the team's primary project and prepare an engineering handoff summary. Use when the user asks Codex to review current bugs, triage open bugs, or create a bug-review summary.

Use when building applications that interact with X (formerly Twitter) data. Reach for this skill when agents need to search posts, stream real-time data, manage user relationships, handle authentication, work with API fundamentals like rate limits and pagination, or integrate X data into applications.

Browser automation for the user's Dia browser. Use for browser tasks that require the user's Dia cookies, logged-in sessions, existing tabs, extensions, or remote authenticated sites.