prompt-guard
Token-optimized prompt injection defense. 70% token reduction via tiered pattern loading, 90% reduction for repeated requests via hash cache. 500+ patterns, 11 SHIELD categories, 10 language support.
session-management
Context preservation, tiered summarization, resumability
JIT Compilation
Expert skill for just-in-time compilation including profiling, tiered compilation, and deoptimization
task-complexity-router
Complexity-based task routing for optimal model selection and cost efficiency. Use when deciding which model tier to use, analyzing task complexity, optimizing API costs, or implementing tiered routing. Trigger keywords - "routing", "complexity", "model selection", "tier", "cost optimization", "haiku", "sonnet", "opus", "task analysis".
release
Prepare and execute a release to pub.dev. Bumps versions, validates changelogs, checks pub.dev status, and guides through the tiered publishing process.
personalization
Use when crafting tiered ABM messaging, offers, and creative variants.
api-rate-limiting
Implement API rate limiting strategies using token bucket, sliding window, and fixed window algorithms. Use when protecting APIs from abuse, managing traffic, or implementing tiered rate limits.
api-rate-limiting
Implements API rate limiting using token bucket, sliding window, and Redis-based algorithms to protect against abuse. Use when securing public APIs, implementing tiered access, or preventing denial-of-service attacks.
slb
Simultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered classification, command hash binding, 5 execution gates, client-side execution with environment inheritance. Go CLI.
launch-planning-frameworks
Master product launch planning including launch types (soft, hard, tiered), launch strategies, launch timelines, cross-functional coordination, and launch execution. Use when planning product launches, coordinating cross-functional teams, creating launch plans, timing market entry, executing launches, or building launch playbooks. Covers launch tier frameworks, launch checklists, and launch management best practices.
design
A unified design system for data and ML dashboards. A quick reference for brand vs. data color decisions, component patterns, typography, spacing, and visualization guidance. Auto-invokes when prompts mention styling, CSS, design, colors, UI, or visualization. Employs tiered loading: core tokens and rules are available immediately, while higher-level philosophy and implementation guidance load on demand.
git-commit-message
Auto-generates conventional commit messages from git diffs with tiered format enforcement. Analyzes staged changes to produce meaningful commit messages following Conventional Commits specification.
permission-management
Central authority for Claude Code permissions. Covers the permission system (tiered model: read-only, bash, file modification), permission rules (allow, ask, deny), rule precedence, permission modes (default, acceptEdits, plan, bypassPermissions), tool-specific permission rules (Bash patterns, Read/Edit patterns, WebFetch domains, MCP tools), the /permissions command, and additionalDirectories. Assists with configuring permission rules, understanding permission modes, and troubleshooting permission issues. Official documentation responsibilities are delegated 100% to the docs-management skill.
smart-test
Intelligent test selection based on code changes. Maps source files to tests via import analysis, implements tiered testing (fast < 1 min, impacted < 5 min, full suite), and tracks test reliability. Use when running tests after code changes to optimize feedback loops and CI time.
maintenance-support-packages
Build recurring revenue by creating monthly maintenance packages with support SLAs, feature request quotas, and tiered options that turn one-time $15K projects into $15K + $1K/month recurring income.
willingness-to-pay-discovery
A framework for identifying customer willingness to pay (WTP) and achieving product-market-pricing fit. Use this when prioritizing a product roadmap, validating a new feature idea, or transitioning from a one-size-fits-all model to tiered pricing.
knowledge-discovery
Discover relevant skills and knowledge using tiered approach. SKIP for simple tasks, QUICK for single-skill, STANDARD for multi-skill, DEEP for full feature implementation. Auto-selects tier based on task complexity.
database-patterns
PostgreSQL + Redis database design patterns. Use for data modeling, indexing, and caching strategies. Covers JSONB, tiered storage, and cache consistency.
alert-optimizer
Restructure and optimize alert rules for monitoring platforms (Sentry, PagerDuty, Datadog, OpsGenie). Use when someone asks to "reduce alert noise", "fix alert fatigue", "create alert rules", "set up escalation policies", "tune alerting thresholds", or "create on-call runbooks". Generates platform-specific alert configurations and tiered escalation policies.
afk
AFK (Away From Keyboard) mode — enable tiered modes, check status, and review sessions. Use /afk [operation] where operation is one of: full|plan|research|monitor|off|status|review.
astro-coding
Provides Astro/Starlight implementation patterns, best practices, and critical rules with tiered context loading
detecting-ai-code
Use when auditing code for AI authorship, reviewing acquisitions/contractors, verifying academic integrity, or during code review - provides systematic tiered framework for detecting fully AI-generated AND AI-assisted code patterns with confidence scoring
effect-deep-audit
Deep audit of an Effect-TS codebase against actual Effect core team patterns. Produces a tiered finding list + executable DAG plan, then systematically rewrites non-idiomatic code. USE THIS SKILL WHEN: - "audit this effect code", "is this idiomatic effect", "deep audit" - Starting a new Effect project and want to verify patterns - Refactoring an Effect codebase toward library-grade quality - Reviewing code before it ships to production NOT FOR: Greenfield Effect projects (use effectts skill). Static lint checks (use effect-mega-lint skill if available).
None
Implement Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory. Covers Tier 0/1/2 separation, privileged access workstations (PAWs), administrative f
building-soc-escalation-matrix
Build a structured SOC escalation matrix defining severity tiers, response SLAs, escalation paths, and notification procedures for security incidents.
rltools-build
CMake build system configuration for rl-tools — tiered targets (Core/Backend/Minimal/RLtools), backend auto-detection, embedded platform builds.
verification-scaffold-skill
Use this skill when generating verification artifacts from threat findings — SVA assertion templates, security review checklists, or tiered verification plans. Triggers on "generate assertions for these threats", "verification checklist", "SVA template", "map threats to verification". Expects upstream ThreatFinding input. Do NOT use for threat identification (use threat-model-skill) or compliance gap analysis (use compliance-pipeline-skill).
tiered-review
T1-T2-T3 processing pattern for review agents — deterministic pre-filtering before LLM analysis to reduce token consumption 50-70%.
prompt-guard
Token-optimized prompt injection defense. 70% token reduction via tiered pattern loading, 90% reduction for repeated requests via hash cache. 500+ patterns, 11 SHIELD categories, 10 language support.
Franchise Operations Playbook
Generic parameterized franchise operations playbook engine for ANY business model and product type. Designs franchisee onboarding programs, customer/service delivery playbooks, tiered support models, quality assurance frameworks, and supply chain plans. Use when building franchise operations manuals, designing franchisee onboarding, creating customer delivery or implementation playbooks, setting up tiered support structures, establishing franchise quality and compliance audits, planning franchise supply chains, or generating operations SOPs for SaaS, retail, service, healthcare, fitness, food, education, or hybrid franchise systems.
pricing-strategy
Optimize pricing pages, pricing models, and pricing strategy. Use when the user asks about pricing, pricing pages, how to price a product, tiered pricing, freemium vs. paid, price testing, pricing psychology, or pricing page design. Trigger phrases include "pricing", "pricing page", "how to price", "pricing strategy", "freemium", "tiered pricing", "per-seat pricing", "usage-based pricing", "pricing experiment", "price anchoring", "pricing psychology", "pricing optimization".
slb
Simultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered classification, command hash binding, 5 execution gates, client-side execution with environment inheritance. Go CLI.