preetamnath
29 verified skills58 total stars
code-review
Structured code review with P0-P3 findings, confidence scores, and criteria-based analysis. Use for reviewing code changes, PRs, or specific files.
development2
grill-me
Stress-test a plan, design, or decision by challenging assumptions, exposing gaps, and forcing specificity. Use when user says "grill me", wants to stress-test a plan, or wants their design challenged.
testing2
plan-builder
Creates dependency-ordered, wave-grouped executable plans from a goal + context. Produces markdown plans with parallel execution waves compatible with plan-runner. Use when you need to break a goal into sequenced, atomic work items before execution.
development2
propose-alternatives
Propose 2-3 genuinely different approaches to a problem with concrete trade-offs. Use when evaluating design choices, exploring options, or challenging the current approach. Do NOT use for validating a chosen approach, code review, or implementation.
development2
sentry-analysis
Analyze Sentry error logs, breadcrumbs, and codebase context to diagnose and explain the root cause of issues.
development2
git-commit-message
Generate git commit messages in a specific bullet-point format with a conventional header.
development2
fix-verify-loop
Bounded resolver for confirmed P0/P1 findings. For each finding: fix → verify resolution via the verifier agent → up to 2 attempts → escalate. Scoped to per-finding resolution; regressions are the caller's job.
testing2
post-purchase-extension
Post-purchase UI extension SDK reference (29 React components, lifecycle, sandbox rules) for `@shopify/post-purchase-ui-extensions-react` — Shopify's only post-purchase SDK; distinct from the modern `polaris-checkout-extensions` web-component surface, which has no post-purchase target. Use when writing/editing JSX for `@shopify/post-purchase-ui-extensions-react`, building or modifying the screen rendered between payment and the thank-you page, or looking up a post-purchase component's props. TRIGGER when: code imports from `@shopify/post-purchase-ui-extensions-react`; user mentions post-purchase upsell, ShouldRender, applyChangeset, calculateChangeset, sign-changeset, or `Checkout::PostPurchase::*`; user asks to add or change a layout/template/component under `extensions/*post-purchase*/`.
tools2
diagnose-review-fix-orchestrator
End-to-end pipeline for uncertain bugs: diagnose root cause, review the fix, then verify and harden. Chains parallel-diagnosis → two-pass-review → fix-loop.
testing2
fix-loop
Bounded fix-and-verify protocol for resolving findings from a review. Max 2 attempts per finding, adaptive verification, escalates to user on failure.
testing2
parallel-diagnosis
Parallel independent root-cause diagnosis for uncertain bugs. Two agents investigate independently, then converge on a unified diagnosis.
data-ai2
sanity-check
Validate or challenge a plan, design, or decision. Confirms what's good, flags realistic concerns, and identifies blind spots.
development2
polaris-web-components
Polaris <s-*> web component catalog, props/slots reference, and layout patterns for the polaris-app-home surface. Use when writing/editing markup with <s-*> tags (<s-page>, <s-section>, <s-stack>, <s-button>, <s-modal>, etc.), building UI in the Admin App Home SPA, looking up a Polaris component's props/slots/tone/size, or calling App Bridge APIs (shopify.toast, shopify.resourcePicker).
development2
audit-transcripts-for-learnings
Audit past Claude Code transcripts in a chosen scope and date window to extract reusable patterns, then walk through each one to promote it into a slash command, CLAUDE.md rule, memory entry, or new skill. Use when the user wants to retrospectively mine sessions for workflow improvements, recurring corrections, validated approaches, or repeated procedures worth capturing.
development2
explain-deeply
Explain how a feature, flow, or concept works by grounding in source-of-truth and walking top-down with diagrams. TRIGGER when: user says explain/walk me through/ELI5/help me understand; user wants to understand how a feature, flow, or system works; user wants intuition or first principles. SKIP when: user wants a diagnosis/fix/action; user wants a one-line definition they can already apply; quick spot-check or confirmation.
testing2
shopify-dev-mcp
Routes Shopify Dev MCP calls for surfaces NOT covered by the bundled Shopify skills: `storefront-graphql`, `customer`, `partner`, `payments-apps`, `functions`, `hydrogen`, `liquid`, `custom-data`. SKIP for Admin GraphQL or App Home markup — the bundled `shopify-admin` and `shopify-polaris-app-home` skills cover those. SKIP entirely for `@shopify/post-purchase-ui-extensions-react` — the MCP doesn't index that legacy SDK; use `post-purchase-ui-extension` instead.
tools2
interview-me
Move from ambiguity to clarity before building. Use when user says 'interview me', asks to be interviewed, or the task has ambiguous scope.
development2
two-pass-review
Two-pass code review: a `code-reviewer` pass followed by an adversarial `verifier` pass. Use for final review of completed code changes (e.g., end of plan-runner) or any code review where a false positive would cost the user real time. Do NOT use for non-code artifacts or for quick spot-checks during iteration.
development2
sync-codex-agents
Convert this repo's Claude agents (`agents/*.md`) to Codex `.toml` format and stage them for installation to `~/.codex/agents/`. Skips Claude-only MCP wrappers (`codex-*` agents). Use when the user asks to sync, mirror, port, or convert agents for Codex; when Claude agents have been edited and Codex is now stale; or when the user mentions `~/.codex/agents/` is out of date.
tools2
plan-runner
Executes wave-grouped markdown plans via parallel subagents. Orchestrates implementation, per-wave review, fix cycles, and final two-pass-review. Resumable across conversations.
data-ai2
polaris-app-home-web-components
Polaris `<s-*>` web component catalog for the Admin App Home surface. Use when writing/editing Polaris markup — `<s-page>`, `<s-section>`, `<s-button>`, `<s-modal>`, tables, forms, layout. TRIGGER when: code contains `<s-*>` tags; user asks to build/update Admin App Home UI.
development2
polaris-app-home-page-patterns
Polaris App Home page templates (Homepage, Index, Details, Settings) and compositions (Empty state, Setup guide, Callout card, etc.) — index of named patterns to look up via shopify-dev-mcp. TRIGGER when: scaffolding an App Home page or using a named composition (Empty state, Setup guide, Callout card, etc.).
tools2
post-purchase-ui-extension
SDK reference for `@shopify/post-purchase-ui-extensions-react` — Shopify's post-purchase upsell surface (the screen between payment and the thank-you page). Distinct from modern `<s-*>` checkout-extensions, which have no post-purchase target. Use when writing/editing JSX for this package or looking up a post-purchase component's props. TRIGGER when: code imports `@shopify/post-purchase-ui-extensions-react`; user mentions post-purchase offer, post-purchase page, post-purchase upsell, post-purchase-ui-extensions, ShouldRender, applyChangeset, or `Checkout::PostPurchase::*`; user edits files under `extensions/*post-purchase*/`.
tools2
second-opinion
Anchored second-opinion on one concrete proposal: dispatch a subagent to rate the fix, generate ranked alternatives, and flag blind spots, then synthesize back. TRIGGER when: user says 'second opinion', 'rate my fix', 'weigh in on my approach', 'what alternatives am I missing', or wants their candidate edit/decision evaluated against alternatives. SKIP when: multiple decisions on a larger artifact — use `panel-review`.
testing2
tighten-instruction
Collapse a multi-clause instruction into one positive line of trigger + action. TRIGGER when: user says 'tighten this rule', 'make this leaner', 'make this simpler' in a skill, CLAUDE.md, agent prompt, or style guide.
documentation2
panel-review
Multi-reviewer panel on N focused questions about a near-final artifact (plan, design, code, prose). R0 (you) plus two parallel reviewer subagents, per-question table with disagreement preserved, walk decisions one at a time. TRIGGER when: user says 'panel review', 'multi-agent review'; user has a mostly-done artifact and focused micro-decisions to validate. SKIP when: only one proposal under review — use `second-opinion`.
development2
tighten-file
File-level tightening pass on an instruction file (CLAUDE.md, skill, agent prompt, style guide) using `tighten-instruction` as the lens. TRIGGER when: user says 'tighten/simplify this file/skill/CLAUDE.md', 'cut this down'; user points at a verbose instruction file and wants it leaner.
documentation2
polaris-app-home-app-bridge
Shopify App Bridge surface for Polaris App Home — `useAppBridge` hook, all `shopify.*` APIs, and App Bridge web components (`<s-app-nav>`, `<s-app-window>`, `<form data-save-bar>`). TRIGGER when: code calls `shopify.*` or `useAppBridge`; user mentions any App Bridge feature (toast, modal, save bar, scanner, scopes, idToken, picker, intents, etc.).
development2
agent-soul
Load a personality archetype that shapes the agent's voice — greetings, status, closings, pushback tone — while keeping plans, diffs, and recommendations neutral. TRIGGER when: user says load a soul/personality/voice/archetype; user says give me a voice; user asks for a specific persona (e.g. gordon-ramsay, yoda); user says switch/swap/change soul; user says serious mode or resume personality.
development2