Sagargupta16

Use when the user writes new Python, or asks for review, refactor, or cleanup of Python code, names, comments/docstrings, functions, or tests. Applies Robert Martin's complete Clean Code catalog -- naming, functions, comments, DRY, boundary conditions, and tests -- to the code being changed.

Use when writing code, making git operations, handling secrets, reviewing PRs, or working with dependencies. Enforces git safety, security best practices, PR workflow discipline, and context-efficient development patterns. Auto-activates as guardrails.

Use when reviewing motion quality, adding animation, transitions, hover effects, making the UI feel more alive, or when animations stutter and transitions jank. Covers three modes -- audit motion code against Disney's 12 principles (file:line findings), add purposeful animations and micro-interactions to a feature, or fix animation performance (layout thrashing, compositor properties, scroll-linked motion, blur).

Use when setting up new repositories, auditing existing ones, or preparing repos for public visibility. Generates .gitignore, .env.example, README, and LICENSE files. Detects committed secrets and flags security issues.

Use when the user asks to audit a session for uncaptured learnings. Activates on "audit this session", "session audit", "what did we miss", "end of session check", or "/starter-session-audit". Scans the conversation for corrections, preferences, decisions, and new context, then proposes where to save each.

Use when triaging a pasted error, stack trace, or terminal transcript. Activates on "debug this", "fix this", "why is this broken", or when a user pastes red terminal output. Produces a tight cause-fix-test report, not a lecture.

Use when you want a one-paragraph plain-English summary of what a diff does. Activates on "summarize this diff", "what does this PR do", "explain this branch", or when pointed at a PR URL or local branch.

Use when triaging open Renovate PRs across your own repos into merge / close / defer. Activates on "renovate triage", "review dep PRs", "monthly deps", or on the 1st of a month if deps are grouped monthly.

Pre-ship UI quality gate for the sagas reading site -- accessibility (WCAG, keyboard, contrast), performance (fast static delivery, fonts, motion cost), and SEO (per-page metadata, canonical, OG/Twitter, sitemap, JSON-LD, RSS). Mobile-first, since the product is long-form reading on phones at night. Audits and fixes against this repo's design tokens and dash/motion house rules.

Turn a book idea into a structural outline with promises, arcs, and a chapter plan. Use when Sagar says "outline this book", "plan the plot", "structure this story", or has a new book idea that needs shape before drafting.

Guided revision pass on a draft chapter -- macro-to-micro, with a measurable cut target and a read-aloud check. Use when Sagar says "revise this chapter", "tighten this", "edit pass", or wants a draft made publishable.

Run a full craft critique of a chapter draft -- structure, POV, prose, dialogue, pacing, exposition, hooks -- with findings cited to craft rules. Use when Sagar says "critique this chapter", "review my chapter", "is this chapter good", or pastes prose asking what's wrong with it.

Canon, characterization, and convention check for fan fiction chapters -- OOC detection, canon-compliance audit, tagging and disclaimer hygiene. Use when Sagar works on any fanfic-shelf book and says "canon check", "is this in character", "check my fanfic", or before publishing a fanfic chapter.

Generate and vet names -- characters, places, magic terms, book titles, chapter titles -- consistent with each book's naming rules. Use when Sagar says "name this", "title for this chapter", "what should I call", or needs any proper noun for a book.

Add a chapter to an existing book, with correct ordering and a consistency pass. Use when Sagar says "new chapter", "add chapter", or pastes chapter prose for a book. For releasing a finished chapter, use publish-chapter instead.

Pre-publish gate and release for a chapter -- final checks, publishedOn, RSS verification, bible update. Use when Sagar says "publish this chapter", "release it", "ship chapter N", or sets a chapter final and wants it live.

Use when setting up a new repo, auditing an existing one for hygiene issues, or before publishing a project. Covers .gitignore, .env.example, README, LICENSE, CONTRIBUTING, and detecting committed secrets.

Use when making git operations, handling secrets, committing code, or dealing with credentials. Enforces git safety rules (no force-push to main, no amend of published commits), secret-handling discipline (never commit .env, use .env.example), and destructive-command caution.

Use when implementing features spanning 3+ files, when requirements are unclear, or when structuring multi-step work. Covers when to plan vs just code, plan structure, interview-then-execute, and prototype-over-spec patterns.

Use when reviewing code changes, examining PRs, or checking your own work before submitting. Covers what to look for (correctness, security, performance, style), how to review systematically, and how to give actionable feedback.

Use when preparing to ship a feature -- opening a PR, writing release notes, cutting a version, or coordinating a deploy. Covers PR hygiene, commit messages, release process, and post-ship verification.

Use when completing a task, before claiming work is done, or before creating a PR. Enforces verification beyond "tests pass" -- actually run the code, hit the endpoints, open the browser. Prevents premature completion claims.

REST API conventions covering URL structure, HTTP methods, status codes, pagination, filtering, error responses, and versioning. Use when designing or reviewing REST API endpoints, adding routes, or standardizing API error handling.

Git conventions covering branch naming, conventional commits, PR format, squash strategy, and protected branches. Use when committing, branching, opening PRs, or setting up a git workflow for a project.

React best practices covering functional components, hooks, state management, performance, and accessibility. Use when writing or reviewing React components, hooks, or state logic.

Testing approach covering unit/integration/e2e split, what to test, AAA test structure, mocking strategies, and coverage targets. Use when writing tests, planning test coverage, or reviewing test quality.

Strict TypeScript conventions covering strict mode config, no-any rules, utility types, discriminated unions, branded types, and error handling patterns. Use when writing TypeScript, tightening types, or migrating code to strict mode.

Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.

Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.

A minimal spec-conformant skill used as a lint fixture. Use when testing skillcheck itself.