Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
This skill should be used when the user asks to "design a test strategy", "plan test coverage", "create test architecture", "review test structure", or mentions test planning patterns like TDD, BDD, o…
Apply enhanced verification (CoVe-like review, security/arch/perf checks, targeted web research) for high-risk tasks or uncertainty. Use for security, infra, data loss risk, major refactors, or when f…
Enforces the project's core TypeScript standards including explicit typing, import organization, class member ordering, and code safety rules. ALWAYS apply when creating, modifying, or reviewing any T…
Use before starting any task, staging files, committing (including after pre-commit failures), or creating a PR — enforces safe git operations to prevent working on stale branches, amending pushed com…
Identify flaky tests from CI history and test execution patterns. Use when debugging intermittent test failures, auditing test reliability, or improving CI stability.
Auto-generate test data factories from schemas, types, or models. Use when creating test data infrastructure, setting up fixtures, or reducing test setup boilerplate.
Focuses exclusively on writing robust integration tests at system boundaries (seams) rather than writing brittle, shallow unit tests. Use when adding test coverage to an existing system, or testing an…
Git 2.49+ features including reftables, sparse-checkout, partial clone, git-backfill, and worktrees
Create, design, build, optimize, and debug Spring Data JPA entities, repositories, queries, projections, and transactions. Detect and fix N+1 queries, configure auditing, write JPQL and native SQL. Us…
Operate the diffx Git-diff CLI for worktree diffs, local/remote ref ranges, GitHub PR diffs, GitLab MR diffs, commit/compare URL diffs, and git-diff-compatible pass-through. Use when an agent must dec…
Agent harness 12 principles based self-diagnosis and improvement suggestions. Triggers on: harness diagnosis, audit, environment check, setup, maintenance, drift confirmation. NOT for: code implementa…
Required orchestrater for linting using a dedicated sub-agent. Trigger when asked to run sweepi/linting + fixes, and before proposing commits.
Suggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.
Extract, classify, deduplicate, and enrich IOCs from investigation artifacts; map to STIX 2.1 observables
A background maintenance agent that keeps the codebase clean,
Git security best practices for 2025 including signed commits, zero-trust workflows, secret scanning, and verification
Use browser automation MCP (Playwright/Browser/Browser-Use) to validate UI flows, capture screenshots, and reproduce issues. Use when visual verification or web flow testing is needed.
Apply Clay security best practices for secrets and access control. Use when securing API keys, implementing least privilege access, or auditing Clay security configuration. Trigger with phrases like "…
Verifies the implementation completeness against the SPEC.md specification. Triggers on: 스펙 검증, spec-verify, 명세서 검증, 구현 검증. NOT for: 코드 리뷰, 단위 테스트, 빌드 검증.
Detect requests for recursive decomposition and large-scale operations that benefit from RLM processing
Detect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
Use when writing E2E tests with Playwright, setting up test infrastructure, debugging flaky browser tests, organizing project structure, or testing REST APIs. Invoke for browser automation, E2E tests,…
A meta-level debugging specialist who diagnoses stuck agents,
Request effective code reviews—specify focus areas, provide context, ask for architectural feedback, reference Laravel conventions