101mare
@101mare
Public Skills
skill-builder
by 101mare
Knowledge for creating Claude Code skill files with SKILL.md format and best practices. Does NOT handle: agent design (use agent-builder), team orchestration (use team-builder), prompt building (use prompt-builder). Use when building skills to teach Claude specialized knowledge or workflows. Recognizes: "create a skill", "new skill for X", "teach Claude how to", "skill that does Y", "SKILL.md format", "skill vs agent?", "add knowledge to Claude", "skill frontmatter"
pr-review
by 101mare
Orchestrates pull request reviews using specialized agents in parallel. Reads PR diff, selects relevant reviewers, aggregates findings. Does NOT handle: plan review (use plan-review), implementation (use tdd), debugging (use systematic-debugging), session verify (use session-verify). Use when reviewing PRs, before merging, or when user asks "review this PR". Recognizes: "pr-review", "review PR", "review pull request", "check this PR", "PR review", "code review", "merge review", "review before merge"
api-design
by 101mare
REST API design with FastAPI: routing, response models, error handling, dependencies. Does NOT handle: architecture (use architecture-builder), exceptions (use exception-builder), frontend clients (use frontend-design), CI/CD (use ci-cd-builder). Use when building APIs, designing endpoints, or setting up FastAPI projects. Recognizes: "api-design", "REST API", "FastAPI", "endpoint design", "response model", "API error handling", "OpenAPI", "build an API", "API patterns", "HTTP endpoints"
error-handling
by 101mare
Patterns for exception handling across application layers: mapping, retry, severity, logging. Does NOT handle: exception hierarchies (use exception-builder), circuit breakers (use resilience-patterns), API errors (use api-design), logging config (use logging-builder). Use when designing error strategies, implementing retry logic, or mapping exceptions between layers. Recognizes: "error-handling", "exception handling", "retry pattern", "error strategy", "exception mapping", "error boundaries", "backoff pattern", "error propagation"
protocol-design
by 101mare
Guides proper use of Python typing.Protocol for structural subtyping and interface design. Does NOT handle: DI containers (use di-container), full architecture (use architecture-builder), mock strategies (use testing-patterns). Use when defining contracts between modules, creating testable interfaces, or choosing between Protocol and ABC. Recognizes: "protocol-design", "typing.Protocol", "structural subtyping", "interface design", "Protocol vs ABC", "duck typing", "mock with spec", "protocol pattern"
session-verify
by 101mare
End-of-session verification skill that validates all changes made during a coding session. Checks for bugs, security vulnerabilities, dead code, efficiency issues, and documentation gaps. Does NOT handle: plan review (use plan-review), PR review (use pr-review), debugging (use systematic-debugging), implementation (use tdd). Use when: finishing a task, before committing, user says "verify", "check my changes", "review session", "are we done?", "everything correct?", or at end of coding sessions. Orchestrates specialized review agents and ensures documentation is updated.
deep-research
by 101mare
Structured research workflow: Question → Sources (web + codebase) → Analyze → Synthesize → Document. Does NOT handle: planning (use plan-review), code review (use pr-review), brainstorming (use brainstorm), architecture (use architecture-builder). Use before technical decisions, when evaluating libraries/tools, or investigating unknowns. Recognizes: "deep-research", "research this", "evaluate options", "which library", "compare approaches", "investigate", "technical decision", "what are the trade-offs", "recherchiere", "welche Library", "Optionen vergleichen", "pros and cons"
resilience-patterns
by 101mare
Resilience patterns for Python: Retry with Backoff, Circuit Breaker, Timeout, Graceful Degradation. Does NOT handle: exception hierarchies (use exception-builder), layer error handling (use error-handling), API errors (use api-design), logging (use logging-builder). Use when building code that depends on external services (APIs, databases, model servers). Recognizes: "resilience-patterns", "retry", "backoff", "circuit breaker", "timeout", "graceful degradation", "fault tolerance", "service unavailable", "connection error", "handle failures", "make it resilient", "retry logic"
brainstorm
by 101mare
Structured brainstorming through divergent-then-convergent thinking. Generates multiple approaches using research-validated techniques (Reverse Brainstorming, SCAMPER, Perspective Shifts, Analogies) before converging on a recommended design. Works for any domain: software features, architecture, thesis structure, process design, concepts, strategies. Recognizes: "brainstorm", "brainstorming", "ideation", "ideas for", "let's think about", "explore options", "what are approaches for", "how could we", "alternatives for" Does NOT handle: implementation planning (use plan-review), prompt writing (use prompt-builder), code writing (use frontend-design/tdd), team coordination (use team-builder).
testing-patterns
by 101mare
pytest patterns, fixtures, mocking, parametrize, and property-based testing. Does NOT handle: TDD orchestration (use tdd), debugging (use systematic-debugging), error handling (use error-handling). Use when writing tests, improving coverage, or setting up test infrastructure. Recognizes: "testing-patterns", "write tests", "pytest patterns", "how to mock", "test fixtures", "parametrize", "property-based testing", "test organization", "improve coverage", "hypothesis tests"
team-builder
by 101mare
Knowledge for orchestrating Claude Code agent teams — multiple independent sessions coordinated by a team lead with shared tasks and inter-agent messaging. Does NOT handle: agent design (use agent-builder), skill creation (use skill-builder), ralph-loop (use ralph-loop). Use when work benefits from parallel exploration with communication between workers. Recognizes: "create a team", "agent team", "team-builder", "parallel teammates", "coordinate multiple agents", "spawn teammates", "team lead", "shared task list"
ralph-loop-prompt-builder
by 101mare
Builds effective prompts for the Ralph Loop autonomous work system. Asks clarifying questions about the task, then generates a structured prompt with clear requirements, verification steps, and completion criteria. Does NOT handle: loop execution (use ralph-loop), general prompts (use prompt-builder). Use this BEFORE starting a ralph-loop — it creates the prompt, not the loop itself. Recognizes: "ralph-loop-prompt-builder", "ralph prompt", "build ralph prompt", "prepare a ralph loop task", "help me write a ralph loop prompt", "structure this for ralph-loop"
di-container
by 101mare
Guides implementation of Dependency Injection containers using Python Protocols. Does NOT handle: architecture (use architecture-builder), interface philosophy (use protocol-design), testing DI (use testing-patterns), scaffolding (use project-scaffold). Use when designing service wiring, managing component lifecycle, or decoupling modules. Recognizes: "di-container", "dependency injection", "container pattern", "service wiring", "inversion of control", "IoC container", "lazy initialization", "protocol-based DI"
ralph-loop
by 101mare
Start an autonomous work loop. Claude keeps working on the given task until it signals completion or the iteration limit is reached. Does NOT handle: prompt building (use ralph-loop-prompt-builder), plan review (use plan-review), code review (use pr-review). Usage: /ralph-loop <task description> Optional: /ralph-loop max=20 <task description> Cancel: delete .claude/ralph-loop.local.md or press Escape/Ctrl+C
agent-builder
by 101mare
Knowledge for designing Claude Code agents with research-backed identity design (Soul Formula). Teaches experiential identities, anti-patterns, multi-file structure, and consolidation patterns. Use when building new agents or improving existing ones. Recognizes: "create an agent", "new agent for X", "agent that does Y", "how do I make an agent?", "agent configuration", "add a subagent", "agent frontmatter", "agent tools", "agent soul", "agent identity", "agent design"