Skill Creator
marcusgoll
33 published skills · 256 GitHub stars across the catalog. View on GitHub ↗
breaking-change-detector
Detect and warn about breaking API/schema changes before implementation. Auto-trigger when modifying API routes, database schemas, or public interfaces. Validates changes against api-strategy.md versioning rules. Suggests migration paths for breaking changes. Prevents removing endpoints, changing request/response formats, dropping database columns, modifying function signatures without deprecation.
caching-strategy
Cache expensive operations to avoid redundant work across workflow phases. Caches project docs (15min TTL), npm info (60min), grep results (30min), token counts (until file modified), web searches (15min). Auto-triggers when detecting repeated reads of same files or repeated API calls. Saves 20-40% execution time.
create-agent-skills
Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure, progressive disclosure, workflows, validation patterns, and XML formatting.
create-meta-prompts
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
dependency-conflict-resolver
Detect and resolve package dependency conflicts before installation across npm/yarn/pnpm, pip/poetry, cargo, and composer. Auto-trigger when installing/upgrading packages. Validates peer dependencies, version compatibility, security vulnerabilities. Auto-resolves safe conflicts (patches, dev deps), suggests manual review for breaking changes. Prevents conflicting versions, security vulnerabilities, broken builds.
dry-run
Preview command effects without making changes. Simulates file writes, git operations, agent spawns, and state changes. All reads execute normally for accurate preview. Use --dry-run flag on any command.
error-recovery
Classify workflow failures and attempt automatic recovery. Use when sprint/feature fails during implementation to determine if auto-fix is possible or manual intervention required.
git-workflow-enforcer
Enforce git commits after every phase and task to enable rollback and prevent lost work. Auto-trigger when completing phases, tasks, or when detecting uncommitted changes. Auto-commit with Conventional Commits format. Verify branch safety, check for merge conflicts, enforce clean working tree. Block completion if changes not committed.
hallucination-detector
Detect and prevent hallucinated technical decisions during feature work. Auto-trigger when suggesting technologies, frameworks, APIs, database schemas, or external services. Validates all tech decisions against docs/project/tech-stack.md (single source of truth). Blocks suggestions that violate documented architecture. Requires evidence/citation for all technical choices. Prevents wrong tech stack, duplicate entities, fake APIs, incompatible versions.
mockup-extraction
Extract reusable components from approved HTML mockups during implementation. Identifies patterns, maps CSS to Tailwind, and populates prototype-patterns.md for visual fidelity. Use at start of /implement for UI-first features.
regression-test-generator
Generate regression tests when bugs are discovered during /debug or continuous checks. Auto-detects test framework, creates Arrange-Act-Assert tests, and links to error-log.md entries. (project)
task-status-sync
Enforce atomic task status updates through task-tracker commands only. Prevent manual edits to NOTES.md and tasks.md that break synchronization. Auto-trigger when detecting Edit/Write attempts to task files, task completion mentions, or status update discussions. Auto-convert manual edit attempts to equivalent task-tracker commands. Validate task-tracker usage and auto-fix common mistakes.
theme-consistency
Enforce consistent theming across all prototype mockup screens. Auto-loads theme.yaml, validates CSS variable usage, prevents hardcoded values, and maintains visual consistency session-to-session. Use during /prototype create when generating new screens.
ultrathink
Deep planning philosophy for craftsman-level architecture. Transforms planning from research-then-design to research-question-simplify-design. Use when --deep flag is set, for epics, complex features (30+ tasks), or when auto_deep_mode preference is enabled. Invokes assumption questioning, codebase soul analysis, and ruthless simplification. (project)
anti-duplication
Before implementing new code (endpoints, components, services, models), search the codebase for existing patterns to reuse. Prevent code duplication by finding and suggesting similar implementations. Auto-trigger when user asks to create, implement, add, or build new functionality.
parallel-execution-optimizer
Identify and execute independent operations in parallel for 3-5x speedup. Auto-analyzes task dependencies, groups into batches, launches parallel Task() calls. Applies to /optimize (5 checks), /ship pre-flight (5 checks), /design-variations (N screens), /implement (task batching). Auto-triggers when detecting multiple independent operations in a phase.
analysis-phase
Standard Operating Procedure for /analyze phase. Covers cross-artifact consistency validation and breaking change detection.
checks-phase
Standard Operating Procedure for /fix-ci phase. Fix CI/deployment blockers after PR creation.
clarification-phase
Standard Operating Procedure for /clarify phase. Covers question generation, prioritization, structured formats, and spec integration.
debug-phase
Standard Operating Procedure for /debug phase. Covers error investigation, root cause analysis, systematic debugging, and error documentation.
finalize-phase
Standard Operating Procedure for /finalize phase. Covers workflow completion, artifact archival, roadmap updates, and knowledge preservation.
implementation-phase
Standard Operating Procedure for /implement phase. TDD workflow, anti-duplication checks, task execution, and continuous testing.
optimization-phase
Standard Operating Procedure for /optimize phase. Covers performance benchmarking, accessibility audit, security review, and code quality checks.
planning-phase
Standard Operating Procedure for /plan phase. Covers research depth, code reuse detection, design pattern selection, and architecture planning.