The library

agenthub · When a problem benefits from diverse solution approaches and time permits parallel exploration with an objective win criterion.

autoresearch-agent · When optimizing a single file's performance, quality, or cost over time requires hands-off autonomous loops with clear metric tracking.

caveman · When technical writing must fit tight token budgets without sacrificing precision (e.g., API docs, complex prompts, reference material).

chaos-engineering · When improving system resilience requires controlled failure injection with documented hypothesis and error-budget impact, not guesswork.

claude-coach · When a Claude user needs personalized, ranked power-user tips delivered only when they would genuinely save time or improve output quality.

code-tour · When onboarding developers or explaining architecture requires guided walkthroughs tailored to reader expertise level rather than generic comments.

data-quality-auditor · When preparing data for analysis or ML requires systematic audit of quality issues rather than spot-checking a few rows.

docker-development · When production containers require optimized build time, minimal image size, and security hardening rather than default Docker patterns.

feature-flags-architect · When shipping features requires disciplined flag management with rollout rings, stale-flag cleanup, and audit trails rather than ad-hoc toggles.

grill-me · When validating a plan or design requires relentless question-driven stress-testing rather than passive review.

grill-with-docs · Crystallizing terminology and architectural decisions incrementally as a plan develops, preserving them in version-controlled docs instead of tribal knowledge

handoff · Handing work from one agent session to the next without replicating artifacts already in git or project management systems

helm-chart-builder · Accelerating Helm chart authoring by enforcing dependency management, security patterns, and testing discipline from the start

karpathy-coder · Catching unsafe abstractions and unfocused changes before code review by surfacing assumptions, complexity drift, and vague goals

kubernetes-operator · Building production Operators by enforcing the Operator pattern disciplines (CRD design, reconcile loops, idempotency, error handling) rather than generic Kubernetes knowledge

llm-cost-optimizer · Controlling LLM spend in production systems by routing between models, implementing caching, and observing token usage per feature

llm-wiki · Compounding knowledge over time by maintaining a persistent, contradiction-aware wiki instead of repeatedly querying RAG on the same sources

security-guidance · Preventing command injection, XSS, SQL injection, unsafe deserialization, code injection, and GitHub Actions workflow injection at the moment of writing, before code reaches review

slo-architect · Structuring service reliability goals with defensible error budgets instead of ad-hoc alerting or targets disconnected from business risk

statistical-analyst · Validating A/B experiment results with rigorous statistics instead of eyeballing conversion rates or running tests that are too small

universal-scraping-architect · Scraping web content with automatic fallback to local extraction when Firecrawl quota is low, avoiding token blowouts on large batch jobs

write-a-skill · Creating high-quality, reusable skills with consistent structure and documentation instead of ad-hoc prompt files or private scripts

finance-skills · Quickly computing financial health snapshots (ratio analysis, valuation, budget) and SaaS health (ARR, churn, LTV, CAC, Quick Ratio) instead of manual spreadsheets

business-investment-advisor · Making go/no-go decisions on equipment, real estate, hiring, or technology investments by quantifying payback and opportunity cost

markdown-html-skills · Publishing markdown documents (code reviews, long-form guides, slide decks, presentations) as shareable, visually polished single-file HTML instead of raw markdown or PDF

marketing-skills · Running tactical marketing work (copywriting, SEO, A/B testing, email sequences, social growth, paid ads, launch strategy) without reinventing templates for each campaign

aeo · Getting cited in ChatGPT, Claude, Gemini, Perplexity responses by optimizing for LLM E-E-A-T signals instead of traditional SEO ranking signals alone

youtube-full · Rapidly ingesting spoken content (podcasts, tutorials, conference talks) with searchable timestamps and channel monitoring at scale.

landing · Shipping premium visual one-pagers with motion design when positioning is locked and no backend/lead-gen conversion tracking is needed.

product-skills · Product teams building comprehensive product strategy when 2-3 focused skills are insufficient and a full 13-skill suite is available.

agile-product-owner · Agile teams that need rapid user story generation (INVEST format) and sprint planning with velocity-aware capacity math.

apple-hig-expert · iOS/macOS teams shipping premium apps when HIG compliance + accessibility + 2026 Liquid Glass aesthetic are critical brand signals.

code-to-prd · Teams needing to document legacy systems or onboard new engineers when existing PRDs are missing or outdated.

andreessen · Founders and operators who want blunt market-first pressure-testing without validation-seeking bias, using Andreessen's proven frameworks.

capture · Users drowning in mixed thoughts who need fast capture to actionable structure without upfront organization overhead.

email · Email-heavy users who want personalized triage (not generic filters) with automatic KB learning from new patterns.

handoff · Passing work to a fresh agent when session time/token limits are hit, without losing critical context or exposing secrets.

reflect · Breaking out of detail-mode spirals and resetting framing when implementation details are distracting from strategic direction.

compliance-team-eu-ai-act · Compliance teams executing Article-level EU AI Act conformity work when risk classification and assessment routing must be locked down.

research-ops-skills · Research teams spanning clinical, finance, market, and product domains when comprehensive research-ops infrastructure is needed across domains.

dossier · Investors and operators who need decision-grade entity research with hypothesis testing and red-flag scoring before meetings or deals.

grants · Clinical researchers seeking NIH funding when preliminary positioning + institute targeting + submission timeline confidence is required.

litreview · Researchers needing a structured literature orientation (launching pad) when full comprehensive reviews are not required.

notebooklm · Users who want to programmatically control NotebookLM (read, add sources, generate outputs) without manual browser interaction.

patent · Inventors and counsel assessing novelty or freedom-to-operate before filing when prior-art search signals must be high-confidence.

pulse · Taking rapid pulse on trending topics, sentiment, and community problems across multiple platforms when speed and cross-platform patterns matter.

syllabus · Instructors who need to update syllabi with recent peer-reviewed research while maintaining alignment with course learning objectives.

cashflow · Personal finance agents that need live transaction data and recurring bill tracking without maintaining proprietary integrations with each bank.

claude-hud · Claude Code operators who want immediate visual feedback on token consumption and tool execution without context-switching to inspect dialogs.

claude-snapshot · Teams that onboard developers frequently and want to replicate a standardized Claude Code config across machines without manual setup.