Menu
SkillsMP has collected 18 skills from axross/ptcgp-deck-builder. Open a skill to review its source and details.
Showing 18 of 18 collected skills.
Drive one unit of work — a GitHub issue, a pull request, or a free-form prompt — from intake to a review-ready pull request in one continuing session; plan and pause for human approval, implement and verify, request the independent review, and address its…
The authoring discipline for agent skills under the host project's skill root (e.g., `.claude/skills/`) — agentskills.io format, frontmatter management and invocation-control fields, kebab-case naming, description and when_to_use writing for discovery,…
The security and privacy review lens for code changes. Covers secrets/env vars, Next.js's NEXT_PUBLIC_ client-exposed env-var prefix, input validation, public exposure, output-encoding/injection in rendered untrusted content, SSRF/outbound fetch of…
The review methodology for every review task, including post-implementation self-review. Covers reviewer-mode reset, diff scoping with `git status`/`git diff`, severity labels, file-line evidence, fix snippets, verification evidence, second-pass re-review…
Conventions for React components and hooks in this project — the shared-vs-feature tier boundary, promotion criteria for repeated UI, component anatomy (naming, props, server/client boundary, test-id hooks), CSS Modules styling composition, logic extraction…
The project's baseline working rules. Covers the format/lint loop, scoped change management, current-docs lookup triggers, run-script commands, type-safety discipline, source-comment and doc-comment conventions, verification requirements, end-to-end test…
Conventions for Playwright end-to-end tests in this project. Covers the test directory layout and file naming, structured test/step naming, stable test-id chained/scoped locators with a role-then-copy fallback hierarchy (text matching only when asserting the…
How an agent reads and writes GitHub (issues, pull requests, comments, labels, reviews, branches) through a proxy-mediated single-operator identity, as a Claude Code + GitHub MCP harness does. Covers routing everything through the one sanctioned tool channel,…
Suspend this session's in-progress work into a self-contained, downloadable handoff package — a handoff-<unix epoch>.md document plus an optional same-epoch .zip of patches and artifacts — that a fresh-context agent session takes over with /address continue.
The reviewer's maintainability lens on changed code, on top of the project's development, structure, and component rules. Covers naming and file organization, route-local vs shared abstraction boundaries, complexity/readability limits, magic-number and…
Error-handling conventions for this project — `try`/`catch` placement, `reportError(...)`/Sentry capture calls, and top-level error boundaries.
The reviewer's lens on runtime cost and failure-mode behavior. Covers server/client boundary cost and async waterfalls, deferred/streamed loading splits, caching correctness (lifetime, scope, invalidation), asset/image optimization, client bundle and…
How to write a product requirement, feature spec, or issue description. Covers framing the problem/outcome before the solution, separating "what" from "how", explicit non-goals and assumptions, right-sizing scope to the change, testable acceptance criteria,…
The repository's layout and placement rules. Covers the Next.js App Router route-file conventions, the by-feature source layout under src/features, the shared tiers (src/components, src/lib), test colocation, and the e2e/scenario-catalog location, plus stack,…
The PTCGP (Pokémon TCG Pocket) domain model for this project — card data and its schema, the card catalog, deck-construction rules and deck validation, energy types and the Energy Zone, rarity tiers, expansions/sets, and the battle rules that affect the deck…
The reviewer's QA lens on verification evidence, on top of development verification and e2e testing rules. Covers format/lint proof, e2e coverage for new routes/features/surfaces, required test-id hooks, intentional snapshot updates, flaky-test investigation,…
How a surface should look in this project — color-token roles, control selection for a decision shape, spacing/typography/radius tokens, dark-mode behavior, responsive layout, copy tone, and accessibility intent.
Conventions for Vitest unit tests in this project. Covers test framework configuration, explicit test-API imports, colocated test files, describe/case naming and grouping conventions, behavior-focused test design, fixture quality, AHA test abstraction, mocks…