cyberneticlibrary

The library

Everything we index — ranked by what works, never by stars.

ArtifactsCapabilitiesRecipes
kindallskillworkflowmcp_servercommandsubagentplugin|✓ proven✗ harmfulmeasured only125 artifacts
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
WORKS 48
Access AI ecosystem and regulatory datapluginDataL2
tensorfeed · Auditing code for authorization, RLS, and authentication vulnerabilities before launch.
WORKS 42
Compare pricing across developer toolspluginFinanceL2
agentdeals · Handling specialized tasks that generic agents cannot perform.
WORKS 48
Generate images and videos with AIpluginMarketingL2
fal-ai · Handling specialized tasks that generic agents cannot perform.
WORKS 48
Automate Firefox testing and scrapingpluginEngineeringL2
firefox-devtools · Handling specialized tasks that generic agents cannot perform.
WORKS 39
Debug iOS Safari with WebKit InspectorpluginEngineeringL2
iwdp-mcp · Handling specialized tasks that generic agents cannot perform.
WORKS 52
Browse pages at 97% fewer tokenspluginEngineeringL2
pagemap · Browsing high-token pages (PDFs, documentation, dense paywalls) where 97% compression outweighs loss of formatting.
WORKS 48
Persist planning and progress across AI editorspluginOpsProductivityL2
planning-with-files · Multi-session planning where Markdown context outlives any single LLM conversation, across teams using different coding IDEs.
WORKS 48
Deploy React/Vite web apps on Tencent CloudBasepluginEngineeringL2
cloudbase-sites · Two-stage save→deploy workflow for iterative React/Vite front-end development on CloudBase, inspired by Codex Sites pattern.
WORKS 48
Access Tencent CloudBase models, auth, and backend servicespluginEngineeringL2
cloudbase · Tencent stack full-stack apps needing unified auth, NoSQL+SQL, blob storage, serverless, and WeChat Mini Program integration.
WORKS 48
Delegate work to Codex, Gemini, and OpenCode agentspluginOpsL2
owlex · Multi-agent workflows requiring load-balancing or task-specific agents (Codex for code, Gemini for breadth, OpenCode for spec-driven generation).
WORKS 48
Match tasks to cognitive operations from 679-item librarypluginL2
ejentum · Complex reasoning, code generation, or deception-resistant verification where 679 pre-verified cognitive topologies beat ad-hoc reasoning.
WORKS 55
Run plan-execute-validate loops with parallel work and memorypluginOpsEngineeringL2
forge · Multi-file refactors, full-stack features, or spec-driven work where parallel validation and retry beat sequential manual oversight.
WORKS 48
Execute terminal commands and manage files across formatspluginEngineeringOpsL2
desktop-commander · Local-only automation across text, code, PDFs, spreadsheets where client-side execution avoids cloud egress and latency.
WORKS 55
Access 5 business growth skills with sales and revenue focuspluginSalesOpsL2
business-growth-skills · Startup GTM (customer success manager hiring, sales engineering processes, RevOps setup, contract/proposal templates) via 5 pre-trained skills.
WORKS 48
Map processes, manage vendors, plan capacity, lead changepluginOpsL2
business-operations-skills · BizOps teams needing BPMN→bottleneck→fix workflows, vendor risk management, call-center capacity math, and process documentation with embedded validation.
WORKS 55
Access 33 C-level advisory skills and virtual board agentspluginOpsL2
c-level-skills · Founder, CEO, or board seeking 33-skill C-suite advisory (CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, counsel, data, AI, customer officers, VPE) with forcing-question discipline.
WORKS 48
Run 13 C-suite agents for executive decision-makingpluginOpsL2
c-level-agents · Executive team or board needing multi-role deliberation (CEO, CFO, CRO, CMO, CPO, COO, CHRO, CISO, Counsel, CDO, CAO, CCO, VPE) before major decisions.
WORKS 48
Calculate AI build-vs-buy and assess regulatory riskpluginProductFinanceL2
chief-ai-officer-advisor · CAO or VP Product deciding between API models (Claude, Gemini), fine-tuning, or self-hosted infrastructure when capital and regulatory trade-offs matter.
WORKS 48
Analyze retention, design segments, size CSM hiringpluginOpsSupportL2
chief-customer-officer-advisor · Chief Customer Officer or VP Customer Success sizing the CS org and kill list when GRR is stalling and NRR delta needs targeting.
WORKS 48
Audit training data origins and design data productspluginDataLegalL2
chief-data-officer-advisor · Chief Data Officer or CPO deciding on data moat strategy, training data sourcing, and infrastructure architecture when legal + product + financial trade-offs collide.
WORKS 53
Scan contracts for founder-killer patterns and riskspluginLegalFinanceL2
general-counsel-advisor · Founder or CEO reviewing term sheet or vendor contract pre-signature when red-flag speed matters more than perfect legal interpretation.
WORKS 48
Analyze delivery metrics, hiring funnel, team structurepluginEngineeringOpsL2
vpe-advisor · VP of Engineering or Director of Eng optimizing delivery throughput (DORA), hiring funnel conversion, and org structure when execution velocity stalls.
WORKS 48
Design pricing, route deals, structure partnershipspluginSalesProductL2
commercial-skills · When pricing, channel, partnership, or deal-approval decisions require principled frameworks rather than ad-hoc judgment.
WORKS 59
Access 32 production-ready engineering and security skillspluginEngineeringL2
engineering-skills · When shipping production-grade code requires discipline across architecture, testing, deployment, and security domains rather than isolated linting.
WORKS 48
Audit and fix WCAG 2.2 accessibility violations in frontendpluginEngineeringProductL2
a11y-audit · When shipping accessible UI requires automated detection of common WCAG violations before manual testing.
WORKS 48
Automate Gmail, Drive, Calendar, Sheets, and TaskspluginOpsProductivityL2
google-workspace-cli · When administering Google Workspace across mail, drive, calendar, docs, and tasks requires CLI automation instead of manual UI clicking.
WORKS 48
Generate, fix, and run production Playwright testspluginEngineeringL2
pw · When shipping e2e tests across multiple browsers and platforms requires templates, flaky-failure fixes, and reporter integrations rather than starting from scratch.
WORKS 48
Auto-improve agent memory and rulespluginProductivityL2
si · When an agent must stay sharp by surfacing what it has learned and permanently upgrading its own instructions and tool library.
WORKS 48
Build Snowflake pipelines and SQL queriespluginEngineeringDataL2
snowflake-development · When building production data pipelines in Snowflake requires serverless compute, AI-native SQL functions, and dbt workflow management.
WORKS 48
Master 40 advanced engineering disciplinespluginEngineeringL2
engineering-advanced-skills · When shipping complex agent systems requires principled design across agent logic, retrieval, data layers, operations, and pre-production compliance gates.
WORKS 57
Spawn parallel agents to solve problemspluginEngineeringProductL2
agenthub · When a problem benefits from diverse solution approaches and time permits parallel exploration with an objective win criterion.
WORKS 48
Automatically optimize files by metricspluginEngineeringProductL2
autoresearch-agent · When optimizing a single file's performance, quality, or cost over time requires hands-off autonomous loops with clear metric tracking.
WORKS 48
Cut communication token usage 75%pluginOpsProductivityL2
caveman · When technical writing must fit tight token budgets without sacrificing precision (e.g., API docs, complex prompts, reference material).
WORKS 48
Design and audit chaos experimentspluginEngineeringOpsL2
chaos-engineering · When improving system resilience requires controlled failure injection with documented hypothesis and error-budget impact, not guesswork.
WORKS 48
Get ranked Claude power-user tipspluginProductivityL2
claude-coach · When a Claude user needs personalized, ranked power-user tips delivered only when they would genuinely save time or improve output quality.
WORKS 48
Create guided code walkthroughspluginEngineeringProductL2
code-tour · When onboarding developers or explaining architecture requires guided walkthroughs tailored to reader expertise level rather than generic comments.
WORKS 57
Audit dataset quality and completenesspluginDataProductL2
data-quality-auditor · When preparing data for analysis or ML requires systematic audit of quality issues rather than spot-checking a few rows.
WORKS 48
Build optimized Docker containerspluginEngineeringOpsL2
docker-development · When production containers require optimized build time, minimal image size, and security hardening rather than default Docker patterns.
WORKS 48
Architect and manage feature flagspluginProductEngineeringL2
feature-flags-architect · When shipping features requires disciplined flag management with rollout rings, stale-flag cleanup, and audit trails rather than ad-hoc toggles.
WORKS 48
Interrogate plans with forcing questionspluginProductOpsL2
grill-me · When validating a plan or design requires relentless question-driven stress-testing rather than passive review.
WORKS 48
Grill plans against recorded decisionspluginProductEngineeringL2
grill-with-docs · Crystallizing terminology and architectural decisions incrementally as a plan develops, preserving them in version-controlled docs instead of tribal knowledge
WORKS 48
Generate conversation handoff docspluginOpsProductivityL2
handoff · Handing work from one agent session to the next without replicating artifacts already in git or project management systems
WORKS 48
Build Kubernetes Helm chartspluginEngineeringOpsL2
helm-chart-builder · Accelerating Helm chart authoring by enforcing dependency management, security patterns, and testing discipline from the start
WORKS 48
Enforce Karpathy active coding rulespluginEngineeringL2
karpathy-coder · Catching unsafe abstractions and unfocused changes before code review by surfacing assumptions, complexity drift, and vague goals
WORKS 48
Design Kubernetes OperatorspluginEngineeringOpsL2
kubernetes-operator · Building production Operators by enforcing the Operator pattern disciplines (CRD design, reconcile loops, idempotency, error handling) rather than generic Kubernetes knowledge
WORKS 48
Reduce LLM API costs and tokenspluginOpsFinanceL2
llm-cost-optimizer · Controlling LLM spend in production systems by routing between models, implementing caching, and observing token usage per feature
WORKS 48
Build persistent interlinked knowledge wikipluginProductivityOpsL2
llm-wiki · Compounding knowledge over time by maintaining a persistent, contradiction-aware wiki instead of repeatedly querying RAG on the same sources
WORKS 48
Catch security anti-patterns before deploypluginEngineeringL2
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
WORKS 48
Design SLOs and error budgetspluginOpsEngineeringL2
slo-architect · Structuring service reliability goals with defensible error budgets instead of ad-hoc alerting or targets disconnected from business risk
WORKS 55
Run A/B tests and hypothesis testspluginProductDataL2
statistical-analyst · Validating A/B experiment results with rigorous statistics instead of eyeballing conversion rates or running tests that are too small
page 1 / 3→