Performance assessment — load testing, capacity planning, bottleneck analysis, caching, CDN, SLAs. Use when the user asks to 'analyze performance', 'design load tests', 'plan capacity', 'optimize caching', 'configure CDN', 'define SLAs', 'find bottlenecks', or mentions latency, throughput, p95, saturation, cache hit ratio, edge compute. [EXPLICIT]

This skill should be used when the user asks to 'create a plugin', 'scaffold a Claude Code plugin', 'convert .claude config to a plugin', 'build a plugin marketplace package', 'add plugin skills, agents, hooks, MCP (Model Context Protocol) servers, LSP (Language Server Protocol) servers, monitors, output styles, or settings', 'validate plugin structure', or 'prepare a Claude Code plugin for local testing, community marketplace review, or official marketplace readiness'. It owns plugin-authoring decisions and distinguishes standalone .claude configuration, shareable namespaced plugins, community marketplace submission, and curated official marketplace inclusion.

Routes the full plugin lifecycle — ideate, build, validate, audit, document, deploy, maintain, fix — to the toolkit's pieces (plugin-builder, check.sh/toolkit-hardener, DEPLOY.md, scaffold/gen scripts, LESSONS-LEARNED). [EXPLICIT] Hub for plugin operations and maintenance. Trigger: 'plugin lifecycle', 'plugin ops', 'maintain plugin', 'deploy plugin', 'plugin maintenance', 'how do I ship this plugin'.

This skill should be used when the user provides a structured prompt contract, acceptance criteria, runbook, SPEC, or automation brief and asks which Claude primitive should own it: prompt, /goal, scheduled task, API tool runtime, agent loop, explicit command, reusable skill, static plan, dynamic workflow, hook, external event push, independent work, coordinated parallelism, cloud routine, headless run, CI, or human review. It normalizes a fail-closed v2.2 operating packet, selects exactly one primary primitive, and records composed primitives separately.

Retrieval-augmented generation and embeddings: retrieval pipeline (chunking, reranking, context assembly, grounding/citation), embedding-model selection, dense/sparse/hybrid retrieval. [EXPLICIT] Trigger: 'rag', 'retrieval augmented', 'embeddings', 'vector search', 'reranking', 'chunking', 'grounding'.

Elicits, structures, and validates software requirements using user stories, acceptance criteria in Given/When/Then format, and traceability matrices. [EXPLICIT] Transforms vague stakeholder needs into precise, testable specifications. [EXPLICIT] Trigger: 'user stories', 'acceptance criteria', 'requirements'

This skill should be used when the user asks to schedule Claude Code work, use /loop, create Claude Code cron tasks, list or delete session crons, use CronCreate, CronList, CronDelete, ScheduleWakeup, choose between Routines, Desktop scheduled tasks, GitHub Actions, channels, hooks, /goal, headless claude -p, or cleanup recurring Claude Code tasks.

Security architecture design — threat modeling, zero trust, identity, encryption, compliance. Use when the user asks to 'design security architecture', 'model threats', 'implement zero trust', 'design IAM', 'plan encryption strategy', 'map compliance requirements', or mentions STRIDE, OWASP, OAuth, RBAC, SOC2, ISO27001, PCI-DSS. [EXPLICIT]

Structured Socratic debate for resolving ambiguities, trade-offs, and low-confidence decisions. Produces auditable thesis-antithesis-synthesis records with constitutional principle alignment. [EXPLICIT] Trigger: 'debate', 'ambiguity', 'resolve conflict', 'low confidence', 'Socratic'

Software and technology viability validator — deep forensic analysis of whether proposed software solutions, AI/ML components, and technology choices are viable substance or speculative smoke. Covers service viability, platform viability, methodology viability, tool viability, and vendor assessment for any service type. Use when the user asks to 'validate technology viability', 'detect vaporware', 'verify AI claims', 'assess software maturity', 'check if this tech actually works', or mentions technology due diligence, software validation, AI feasibility, vendor evaluation, or tech-stack viability. This is the devoted software-specific validator — separate and more critical than the multidimensional feasibility analysis. [EXPLICIT]

End-to-end solution design — system integration, channel orchestration, identity management, observability, and cross-cutting concerns. [EXPLICIT] Use when the user asks to 'design the full solution', 'integrate multiple systems', 'plan API gateway strategy', 'define identity and security architecture', 'set up observability', or mentions C4 containers, BFF, Zero Trust, SLI/SLO, circuit breaker, or migration planning. [EXPLICIT]

Influence/interest matrix. RACI matrix. Communication plan. Power/interest grid. Stakeholder registry. [EXPLICIT]

This skill should be used when the user asks to prototype a UI, generate screens from text, design a web/mobile page, build a design system, edit existing Stitch screens, or iterate on a high-fidelity mockup with Google Stitch.

Designs software architectures using C4 diagrams, Architecture Decision Records (ADRs), quality attribute analysis, and trade-off evaluation. Covers system decomposition from context to code level. [EXPLICIT] Trigger: 'C4 diagram', 'architecture', 'ADR', 'quality attributes', 'system design'

This skill should be used when the user asks to be terse, compress output, reduce tokens, switch to a concise mode, or wants short high-signal answers without losing technical accuracy or evidence.

Test strategy design — pyramid, automation, E2E, contract testing, shift-left, test data management, QA-as-a-service strategy, test factory design, PITT methodology, QA CoE design. Use when the user asks to 'design test strategy', 'build test automation', 'implement contract testing', 'manage test data', 'define quality gates', or mentions test pyramid, Pact, Playwright, Cypress, coverage targets, flaky tests, chaos engineering. [EXPLICIT]

This skill should be used for Claude Code permission rules, modes, settings, MCP permission syntax, and hooks boundaries. Do not use it as the authorization contract for Claude Platform memory, bash, text-editor, computer-use, server tools, or Messages API handlers.

Use when designing or troubleshooting Claude Platform tool contracts: names, descriptions, input_schema, input_examples, strict, tool_choice, cache/privacy, versions, and routing boundaries.

This skill should be used when the user asks to 'harden a toolkit skill', 'check a skill against the Definition of Done', 'audit packet completeness', 'validate a skill against the katas', 'bring a skill to gold-standard', or 'run the excellence gate' for the claude-native-toolkit. Enforces the packet DoD + kata best-practices + the toolkit brand + evidence honesty before a skill is declared done.

Performs structured trade-off analysis using weighted scoring matrices, decision matrices, and ATAM (Architecture Tradeoff Analysis Method) to make defensible architectural and technology decisions. [EXPLICIT] Trigger: 'trade-off', 'decision matrix', 'ATAM', 'weighted scoring', 'pros and cons'