maythyai
OrganizationCSP is an integrated suite of AI-driven coding capabilities. It bridges the gap between essential development workflows into a unified, pluggable framework for enhanced productivity.
Categories
Indexed Skills (51)
csp-agent-teams
Orchestrate multiple AI agents for parallel or sequential task execution. Includes CSP agent-team collaboration (per-task dispatch with two-stage review) and parallel agent dispatch (independent problems solved concurrently). Use when executing implementation plans with independent tasks, or facing 2+ independent failures.
csp-brainstorming
Collaborative design partner that turns raw ideas into fully formed specs. Combines structured divergent-convergent ideation with interactive design dialogue. Use before any creative work — creating features, building components, adding functionality, or modifying behavior. Includes idea refinement, assumption surfacing, and approach exploration.
csp-code-graph
Code knowledge graph methodology and lifecycle orchestration. Use when starting a code review session, exploring codebase structure, or deciding which graph-powered analysis to run. Routes to the correct lifecycle stage: build, impact, review, architecture, or refactor.
csp-context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
csp-doc-review
Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.
csp-doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.
csp-executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
csp-finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
csp-interview-me
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.
csp-mvp-scoping
Cut a product idea down to the smallest shippable version that validates the core hypothesis. Use when facing a long feature wishlist, when planning a new product or feature, or when scope needs to be reduced to ship within a deadline.
csp-party-mode
Multi-agent collaboration for complex problem-solving with specialized AI agents
csp-requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
csp-scope-guard
Detect and resist scope creep during development. Use when a feature request triggers unplanned work, when "while I'm here" changes pile up, or when the current sprint/task is at risk of expanding beyond its original boundary.
csp-skill-optimizer
Use when collecting user feedback on skill behavior, identifying skill coverage gaps, or optimizing existing skills based on real usage patterns. Also triggers when user says "this skill doesn't handle X", "skill X missed", "make skill X better", or "optimize skills".
csp-source-driven-development
Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.
csp-spec-contract
Transform ideas, requirements, or discussions into CSP SPEC contracts with traceable requirements and acceptance criteria. Use when formalizing requirements, generating CSPEC inputs, or validating spec completeness. Triggers on "spec", "specification", "contract", "formalize requirements".
csp-spec-driven-development
CSP-native spec-driven methodology integrated with CSP phase workflows. Use when formalizing requirements before implementation, managing brownfield requirement deltas, or verifying artifact-to-code alignment. Triggers on "spec-driven", "规范驱动", "write spec before code", "delta requirements".
csp-systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
csp-tdd
Test-Driven Development: write failing test first, minimal code to pass, then refactor. Enforces Red-Green-Refactor cycle with 80%+ coverage across unit, integration, and E2E tests. Use when implementing any feature, fixing bugs, or refactoring code.
csp-using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
csp-verification
Verify changes really work before claiming completion. Evidence before assertions, always. Includes 6-phase verification (build, types, lint, tests, security, diff) and continuous mode. Use when about to claim work is complete, before committing or creating PRs.
csp-writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
csp-writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
csp-test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
csp-web-performance-auditor
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
csp-access
Full accessibility audit (WCAG 2.1 AA/AAA). Performs a systematic accessibility compliance check Use when working on design tasks related to access.
csp-agent-introspection-debugging
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
csp-agent-sort
Build an evidence-backed CSP install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when CSP should be trimmed to what a project actually needs instead of loading the full bundle.
csp-agentic-engineering
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when AI agents perform most implementation work and humans enforce quality and risk controls.
csp-api-governance
Governs public and internal APIs with rate limiting algorithms, API key management, usage metering, versioning strategies, error standardization, and monitoring for reliable API operations.
csp-article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
csp-audit
Product Design Suite · Entry C: Redesign UX Audit. First Skill to launch when a designer Use when working on design tasks related to audit.
csp-autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
csp-test-methodology
Choose and combine testing methods so no requirement falls through the cracks. Use when planning test strategy for a feature, when single-layer tests pass but the feature breaks end-to-end, when deciding smoke vs sanity vs E2E vs integration vs contract vs property vs fuzz vs mutation vs exploratory vs chaos vs load vs a11y vs security testing, when mapping requirements to test methods to find untested functionality, or when preventing fragmented ("割裂") testing that validates one function in isolation and misses linked effects. Provides the full testing-method taxonomy, a blind-spot complementarity matrix, and requirement traceability gap analysis. The methodology layer above csp-cross-layer-testing.
csp-receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
csp-using-skills
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
csp-agentic-identity-trust
Identity systems architect for autonomous AI agents — designs cryptographic identity, trust verification, evidence trails, delegation chains, and peer verification for multi-agent environments. Use when building agent authentication, trust scoring, or audit infrastructure.
csp-api-tester
Comprehensive API testing specialist — functional validation, performance testing, security testing (OWASP API Top 10), contract testing, and CI/CD integration. Use for API validation, load testing, and integration quality assurance.
csp-csharp-reviewer
Expert C# and .NET code reviewer specializing in async/await patterns, Entity Framework Core, testing frameworks (MSTest, NUnit, xUnit), and .NET best practices. Use for all C# code changes.
csp-data-engineer
Data pipeline architect specializing in reliable ETL/ELT, lakehouse architectures (Bronze/Silver/Gold), data quality contracts, streaming systems, and cloud data platforms. Use for data pipeline design, schema architecture, and data infrastructure.
csp-document-generator
Programmatic document creation specialist — generates professional PDF, PPTX, DOCX, and XLSX files using code-based approaches with proper formatting, charts, and data visualization. Use for automated report generation, presentation creation, and document templating.
csp-incident-commander
Production and security incident management specialist — severity classification, structured response coordination, data breach blast radius assessment, blameless post-mortems, SLO/SLI tracking, and on-call process design. Use when handling production outages, security incidents, data breaches, designing incident workflows, or building runbooks.
csp-mcp-builder
Model Context Protocol specialist who designs, builds, and tests MCP servers that extend AI agent capabilities with custom tools, resources, and prompts. Use for MCP server development, tool interface design, and agent integration.
csp-minimal-change-engineer
Surgical implementation specialist — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. Use when you need disciplined, minimal diffs that prevent bug-fix PRs from becoming refactor avalanches.
csp-model-qa
Independent ML model QA auditor — end-to-end audits from documentation review, data reconstruction, replication, calibration testing, SHAP interpretability, performance monitoring, to audit-grade reporting. Use for validating ML models before production deployment.
csp-multi-agent-architect
Systems architect for multi-agent AI pipelines — topology selection, context management, inter-agent trust, failure recovery, human-in-the-loop gating, and observability for production-grade agent systems.
csp-project-standards-reviewer
Project standards and code quality reviewer. Extracts coding standards from existing code, identifies high-quality exemplars, and enforces consistency. Use for establishing or reviewing project coding standards.
csp-prompt-engineer
Prompt design and LLM behavior specialist — crafts, tests, and systematically optimizes prompts for LLMs. Use for system prompt design, few-shot example construction, prompt regression testing, and multi-model prompt porting.
csp-springboot-reviewer
Spring Boot code reviewer for Java and Kotlin. Covers JUnit 5 testing, Spring Boot Test, MockMvc, TestContainers, and Kotlin-specific Spring patterns. Use for all Spring Boot applications in Java or Kotlin.
csp-workflow-architect
Workflow design specialist who maps complete workflow trees — happy paths, all branch conditions, failure modes, recovery paths, handoff contracts, and observable states — to produce build-ready specs that agents can implement and QA can test against.
csp-api-codegen
API code generation agent. Generates application code from OpenAPI/Swagger specs and TypeSpec definitions. Covers client SDKs, server stubs, validation schemas, and API plugin scaffolding. Use for "generate from OpenAPI", "create API from spec", "TypeSpec to code".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.