cyberneticlibrary

The library

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

WORKS 48
Create new database entity classessubagentEngineeringL1
new-entity · Creating ORM entities when schema design needs code generation.
WORKS 50
Simplify code without changing behaviorsubagentEngineeringL1
code-simplifier · Cleaning code when reuse wins matter more than bug hunting.
WORKS 48
Update and sync documentationsubagentEngineeringL1
docs-agent · Keeping docs fresh when code changes need user-facing explanation.
WORKS 48
Research technical solutions onlinesubagentEngineeringL2
ark-researcher · Analyzing agent-at-scale patterns when McKinsey research needs synthesis.
WORKS 48
Manage Uniswap v3 liquidity positionssubagentFinanceL3
{"{ projectName }":null} · Autonomous LP range management when automated rebalancing within USD bounds beats manual monitoring
WORKS 55
Detect bugs in pull request codesubagentEngineeringL1
pr-reviewer-bugs · Catching null-check gaps and breaking changes when deep code reading and cross-file validation matter
WORKS 48
Create new host configurationsubagentEngineeringL2
gstack-contrib-add-host · Adding agent support to gstack when a new coding assistant needs skill reuse across host ecosystems
WORKS 48
Verify documentation accuracysubagentEngineeringL1
documentation-accuracy-reviewer · Ensuring user docs match implementation when multi-layered documentation must stay in sync
WORKS 48
Normalize React and TypeScript codesubagentEngineeringL2
react-normalizer · Applying company standards consistently when 2-iteration cap and business-logic preservation matter
WORKS 48
Analyze weather patterns and trendssubagentDataL2
weather-analyst · Multi-period weather analysis when hour-by-hour comparisons and extreme event detection beat simple forecasts
WORKS 48
Optimize performance with SIMD and GPU kernelssubagentEngineeringL4
perf-dev · Quantization/numerical compute when measured speedup with verified correctness beats speculation
WORKS 48
Plan API-first compiler and orchestration changessubagentEngineeringL4
compiler-architect · Compiler architecture when API-first IR design and provider-agnostic core logic matter
WORKS 48
Build art pipeline and shader optimizationsubagentEngineeringL4
Technical Artist · Maintaining visual quality within hard performance budgets when per-platform constraints and LOD discipline matter
WORKS 48
Map sensitive data flows for securitysubagentEngineeringL3
data-flow-tracer · Security audit when complete data-flow visualization and validation-gap discovery outweigh endpoint lists
WORKS 48
Explore read-only vault documentationsubagentEngineeringL2
explorer · Non-mutating intelligence gathering when read-only analysis and pattern detection matter
WORKS 48
Improve structured logging and observabilitysubagentEngineeringL3
logging-subagent · High-concurrency Rust when structured field logging and span-based context tracing beat free-text logs
WORKS 48
Maintain AI instructions and agent architecturesubagentEngineeringL3
vibe-architect · Multi-skill governance when durable rule files and centralized routing beat scattered configs
WORKS 48
Conduct deep technical auditssubagentEngineeringL3
reasoner · Honest technical assessment when architectural health and productization readiness matter
WORKS 48
Manage events lifecycle and sponsorshipssubagentMarketingL2
events-agent · Full event coordination when checklist-driven lifecycle beats fragmented spreadsheets
WORKS 48
Review econometric identification strategysubagentDataL3
causal-inference · Causal inference when observational data and rigorous assumption testing beat correlation studies
WORKS 48
Analyze codebase and generate intelsubagentEngineeringL3
gsd-intel-updater · Intelligence database maintenance when automated updates and validation matter
WORKS 48
Write idiomatic C++ with modern patternssubagentEngineeringL3
cpp-pro · C++ performance tuning when measured improvements and correctness verification matter
WORKS 48
Answer mid-session repo questionssubagentEngineeringL2
qa-agent · QA automation when systematic test execution and coverage metrics beat ad-hoc testing
WORKS 48
Triage backlog and prioritize worksubagentProductL2
pm · Project coordination when centralized status tracking and risk visualization matter
WORKS 49
Review Rust code for safety and idiomssubagentEngineeringL2
code-reviewer · Catching Rust safety bugs in compiler code reviews without full AST context.
WORKS 48
Develop Flutter mobile applicationssubagentEngineeringL3
flutter-expert · Mentoring a team on Flutter patterns when Riverpod state is complex.
WORKS 48
Advise on SaaS tax and accountingsubagentFinanceL2
felix · Configuring entity structure and tax planning at SaaS hire-time.
WORKS 49
Audit and generate tests across repossubagentEngineeringL3
README · Parallel auditing of unfamiliar legacy code when multiple specialists are needed.
WORKS 48
Organize and triage note inboxsubagentProductivityL2
sorter · Batching daily Obsidian inbox triage to maintain project momentum.
WORKS 49
Audit SEO health and crawl sitesubagentMarketingL3
seo-auditor · Detecting SEO regressions after major Vercel deploys without manual crawling.
WORKS 48
Refactor Rails code after tests passsubagentEngineeringL2
rails-refactoring-expert · Cleaning up working Rails code while keeping tests green.
WORKS 48
Formalize plans into specificationssubagentProductL2
architect · Turning approved plans into precise specs before dev teams start coding.
WORKS 48
Write clear documentation and ADRssubagentEngineeringL2
documenter · Writing consistent architecture docs when live code outpaces documentation.
WORKS 49
Review code quality and securitysubagentEngineeringL2
quality-reviewer · Universal PR quality checks when no role-specific reviewer exists.
WORKS 49
Review technical designs and feature planssubagentEngineeringL3
sqlbuildingblocks-plan-reviewer · Stress-testing feature plans against dialect complexity and NonTerminal dispatch.
WORKS 48
Write and run tests for leto-rssubagentEngineeringL2
leto-tester · Applying deep expertise to a focused scope.
WORKS 48
Create executable phase plans with task breakdownsubagentOpsL2
gsd-planner · Turning approved plans into detailed specifications.
WORKS 48
Verify code ready for push and mergesubagentEngineeringL2
pr-preflight · Applying deep expertise to a focused scope.
WORKS 48
Audit OAuth security in vestibulesubagentEngineeringL2
oauth-security-reviewer · Finding domain-specific issues in technical reviews.
WORKS 48
Fix Flutter build and analyze errorssubagentEngineeringL2
flutter-build-fixer · Applying deep expertise to a focused scope.
WORKS 48
Validate tier implementations against contractssubagentEngineeringL2
spec-reviewer · Finding domain-specific issues in technical reviews.
WORKS 49
Review production CLI and git codesubagentEngineeringL1
code-reviewer · Catching Rust safety bugs in compiler code reviews without full AST context.
WORKS 48
Test Trustify performance and scalesubagentEngineeringL3
trustify-perf · Applying deep expertise to a focused scope.
WORKS 48
Build Super STT COSMIC desktop featuressubagentEngineeringL3
cosmic-app-architect · Turning approved plans into precise specs before dev teams start coding.
WORKS 48
Create project roadmaps with phasessubagentProductOpsL2
gsd-roadmapper · mapping requirements into executable phases with observable success criteria
WORKS 48
Approve and deploy code changessubagentOpsEngineeringL2
ship-agent · deploying features to staging automatically and requesting approval for production
WORKS 48
Test gcx parser against real repossubagentEngineeringL3
gcx-lang-tester · validating parser changes and compiler correctness across multiple languages
WORKS 48
Validate bot branch before mergesubagentEngineeringL2
integrate-gater · validating code changes before merge (TypeScript, linting, unit tests)
WORKS 39
Review Rust code and ownership patternssubagentEngineeringL1
rust-specialist · reviewing Rust code for memory safety, ownership patterns, and async correctness
WORKS 48
Implement generation battle mechanicssubagentEngineeringL2
gen-implementer · implementing Pokemon battle mechanics for new game generations
page 3 / 10