The library

bernstein-quality · Gating agent changes on quality metrics before acceptance.

nextjs-supabase-auth · Adding production-grade user authentication to Next.js apps without custom implementation.

cs-ux-researcher · Structured user research that informs product decisions with empirical evidence.

claude-skill-lint · Production skill repos need deterministic validation before publishing; catches hallucinated context bugs CI cannot see.

bernstein-status · Real-time visibility into multi-agent runs; reduces context-switching vs checking logs separately.

send-payload · Broadcast alerts to many surfaces from one LLM call; avoids N sequential sends, reducing latency.

rocketman · Teams where AI agents are primary workers; repo-local PM beats SaaS boards for agent context + version control.

analyst · Killing bad ideas early; composite scoring prevents false positives on cool-sounding unfeasible proposals.

nodejs-keccak256 · Ethereum/EVM teams; one wrong hash breaks selectors/signatures/storage—non-obvious until mainnet.

cs-wiki-librarian · Knowledge reuse over re-deriving; compounding answers back to wiki keeps it fresh and queryable.

notebooklm · Converting research into audio/quiz/infographics; CLI unlocks export unavailable in web UI.

cs-wiki-linter · Weekly audits keep wikis honest; catches disconnected islands, stale claims, orphaned context before they rot.

brand-motion-adapter-skill · Design systems; ensures every animation matches brand motion language instead of default easing.

backend · Backend-heavy products; structured ownership prevents cross-team merge conflicts.

cs-workspace-admin · Multi-service Workspace automation; gws CLI + recipes beat UI clicking for repeatability.

ci-fixer · Unblocking CI; minimal targeted approach reduces test-commit loops.

cto-advisor · CTOs need fast principled evaluation of tech choices; beats design committee meetings.

nuxt4-patterns · Frontend teams standardizing on Nuxt 4; consistency across team.

cto-review · Acquisition/investment due diligence; senior technical eye catches what automated tools miss.

claude-skill-testweaver · Reducing skill flakiness; systematic test coverage prevents regression.

pii-redaction-logging-policy-builder · Compliance-heavy products; automated policy generation reduces manual review burden.

obsidian-bases · Knowledge workers; structured Obsidian vaults compound over years.

frontend · Building type-safe, accessible React components with server-side rendering and CSS performance optimization.

obsidian-cli · Scripting vault operations and plugin development from the shell when GUI automation would be tedious.

customer-success-manager · Scoring customer health and churn risk deterministically using weighted multi-dimension models without external ML.

slack-to-zoom · Migrating Slack apps to Zoom Team Chat with automated feature mapping and gap identification.

manager · Breaking ambitious goals into task-server tasks with clear ownership, acceptance criteria, and completion signals.

obsidian-markdown · Creating notes with wikilinks, embeds, and callouts that render correctly in Obsidian vaults.

data-quality-auditor · Systematically profiling datasets to surface silent nulls, outliers, and distribution shifts before they corrupt downstream analysis.

onboarding-cro · Shortening time-to-value by removing friction before the aha moment and measuring activation drop-off step-by-step.

skill-installer · Installing Stashwise-generated Claude skills with cryptographic signature verification and safe unpacking.

openai-image-gen · Batch-generating variations of structured image prompts and hosting them in a browsable index.html gallery.

database-schema-designer · Designing normalized relational schemas with ERD diagrams and DDL generation from high-level requirements.

qa · Running deterministic test suites and coverage checks to prevent regressions before code merges.

auth-handler · Implementing OAuth/JWT flows with session management and token refresh without reinventing the auth wheel.

openbrand · Generating cohesive brand guidelines, color palettes, and typography systems from a single source of truth.

deal-desk · Configuring deal terms, pricing rules, and approval workflows with audit trails and quote generation.

resolver · Debugging production issues by tracing logs, reproducing errors, and identifying root causes systematically.

web-design-guidelines · Ensuring UI consistency, accessibility (WCAG AA), and performance across responsive designs.

decide · Prevents regressions by preserving dissent from rejected options that often prove correct at kill-criteria time.

claude-skill-vitepress-docs · Keeps docs in sync with code changes automatically—survives merge conflicts and drift that manual documentation cannot.

optimizing-tauri-binary-size · Tauri already produces 3-6MB binaries vs Electron's 120MB—tuning shaves another 30-50% with standard LLVM flags.

decision-logger · DO_NOT_RESURFACE enforcement prevents the system from auto-incorporating rejected debates as if they were settled.

reviewer · Distinguishes blocking issues from nits—allows teams to merge without blocking on style when logic is solid.

osint · Authorization framework prevents unauthorized investigations—checks all compliance gates before any collection starts.

asc-mcp · Sampling-based tools cost zero extra—your own client's model does review clustering, no API charge from the server.

security · Severity classification separates critical auth issues from style nits—allows teams to merge without blocking on low-severity findings.

claude-skill · Single API handles database, auth, storage, and compute—saves hours of wiring up 4 separate cloud services.

vp · Sits above individual cells—resolves conflicts without forcing cells to restructure or hide constraints.

paid-ads · A/B tests creative and targeting simultaneously—catches interactions that single-variable optimization misses.