cyberneticlibrary

The library

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

WORKS 48
Check PersonalizationMCP healthskillOpsL1
personalhub-status · Specialized use case not specified in body.
WORKS 48
Design brutalist data dashboardsskillProductEngineeringL1
industrial-brutalist-ui · When building data-heavy dashboards or technical portfolios that need to feel like declassified blueprints.
WORKS 48
Execute implementation plans with subagentsskillOpsL2
do · When executing a plan requires coordination of multiple subagents across distinct work phases.
WORKS 48
Create detailed phased implementation plansskillOpsL1
make-plan · When a task requires phased, documented implementation with pre-discovery of actual APIs and patterns.
WORKS 48
Generate premium frontend design sectionsskillMarketingProductL1
imagegen-frontend-web · When creating section-by-section frontend design references that developers can accurately implement.
WORKS 48
Design clean editorial-style interfacesskillProductMarketingL1
minimalist-ui · When designing clean, document-like workspaces that reject generic SaaS defaults.
WORKS 53
Monitor pull requests until merge-readyskillEngineeringL2
babysit · When a PR needs active monitoring until all checks, reviews, and threads are truly resolved.
WORKS 48
Enforce complete code output without truncationskillEngineeringL1
full-output-enforcement · When complete, unabridged output is critical and default truncation patterns would break the deliverable.
WORKS 48
Audit designs against Dieter Rams principlesskillProductMarketingL1
design-is · When auditing existing designs against foundational principles before committing to refine or redesign.
WORKS 48
Upgrade websites to premium qualityskillMarketingProductL2
redesign-existing-projects · When auditing existing designs against foundational principles before committing to refine or redesign.
WORKS 55
Design like a high-end agencyskillMarketingProductL1
high-end-visual-design · When auditing existing designs against foundational principles before committing to refine or redesign.
WORKS 48
Understand claude-mem architecture and dataskillEngineeringL1
how-it-works · When applying how-it-works patterns to specialized interface challenges.
WORKS 48
Build premium design systems for agentsskillProductEngineeringL2
stitch-design-taste · When applying stitch-design-taste patterns to specialized interface challenges.
WORKS 48
Build AI-powered knowledge bases from observationsskillOpsProductL2
knowledge-agent · When applying knowledge-agent patterns to specialized interface challenges.
WORKS 48
Design frontend interfaces (legacy v1)skillProductL1
design-taste-frontend-v1 · When applying design-taste-frontend-v1 patterns to specialized interface challenges.
WORKS 48
Prime codebase by reading all source filesskillEngineeringL1
learn-codebase · When applying learn-codebase patterns to specialized interface challenges.
WORKS 48
Ship premium frontend interfaces without templatesskillMarketingProductL1
design-taste-frontend · When applying design-taste-frontend patterns to specialized interface challenges.
WORKS 48
Coach startup-track career decisionsskillHRL1
ent-career-coach · When applying ent-career-coach patterns to specialized interface challenges.
WORKS 48
Search persistent cross-session memoryskillOpsProductivityL1
mem-search · When applying mem-search patterns to specialized interface challenges.
WORKS 48
Draft winning cold outreach messagesskillSalesHRL1
ent-cold-email · When applying ent-cold-email patterns to specialized interface challenges.
WORKS 48
Cluster GitHub issues by root causeskillEngineeringL2
oh-my-issues · When applying oh-my-issues patterns to specialized interface challenges.
WORKS 56
Design cheap fast concept testsskillProductMarketingL1
ent-concept-test · Testing whether a desperate customer would want your solution before building—the fastest way to validate demand in days instead of weeks.
WORKS 48
Map codebase to unified architectureskillEngineeringL2
pathfinder · Extracting duplicated concerns across features and proposing the simplest unified design before committing to a refactor.
WORKS 56
Track customer discovery interview patternsskillProductSalesL1
ent-customer-discovery · Synthesizing signal from 20-80 interviews to identify desperate customers, surface recurring patterns, and detect when you have enough evidence to graduate.
WORKS 48
Search code structure with token efficiencyskillEngineeringL1
smart-explore · Token-efficient code navigation through symbols, functions, and dependencies—use instead of reading full files to map structure before diving into implementation.
WORKS 48
Identify and manage design partner relationshipsskillSalesProductL1
ent-design-partners · Structuring early B2B customer relationships that are committed, paid, and co-creative—avoiding big-logo traps and tire-kickers.
WORKS 48
Convert research insights into falsifiable betsskillProductL1
ent-idea-coach · Distinguishing wishes from ideas from insights—harvesting structural blindspots that incumbents can't pursue, not just consensus trends.
WORKS 48
Generate project development journey narrativeskillProductL1
timeline-report · Analyzing a project's entire development history from persistent memory—tracing architectural evolution, breakthroughs, and work patterns across the full timeline.
WORKS 48
Interview founder and set up workspaceskillProductL1
ent-intake · Cold-start placement of a founder on the 00→07 journey—replacing blank forms with conversational state capture and automatic file writes.
WORKS 48
Score and structure customer interview debriefskillProductL1
ent-interview-debrief · Provide expert guidance at a specific stage.
WORKS 48
Split timeline into week-by-week narrative digestskillProductL1
weekly-digests · Provide expert guidance at a specific stage.
WORKS 48
Build focused script for customer discoveryskillProductL1
ent-interview-prep · Provide expert guidance at a specific stage.
WORKS 48
Turn document into shareable slide deckskillMarketingProductivityL1
wowerpoint · Provide expert guidance at a specific stage.
WORKS 48
Run two-week MVP product reviewskillProductL1
ent-mvp-review · Provide expert guidance at a specific stage.
WORKS 48
List unpublished code changes by release layerskillEngineeringL1
get-unpublished-changes · Provide expert guidance at a specific stage.
WORKS 48
Define minimum viable MVP to test leap of faithskillProductL1
ent-mvp-scoper · Provide expert guidance at a specific stage.
WORKS 48
Analyze GitHub issues and PRs with evidenceskillEngineeringL2
github-triage · Provide expert guidance at a specific stage.
WORKS 48
Interrogate product idea YC office-hours styleskillProductL1
ent-office-hours · Provide expert guidance at a specific stage.
WORKS 48
Run adversarial multi-agent planning debateskillProductOpsL2
hyperplan · Provide expert guidance at a specific stage.
WORKS 48
Run structured pivot-or-persevere decisionskillProductL1
ent-pivot-coach · When a founder faces a critical go/no-go decision after PMF stall and needs data-driven clarity, not narrative hope.
WORKS 48
Run honest product-market fit self-checkskillProductL1
ent-pmf-evaluator · When a team asks 'do we have PMF?' and you need to give an honest, rubric-backed answer that stands up to VC scrutiny.
WORKS 48
QA opencode CLI, plugins, and databaseskillEngineeringL2
opencode-qa · When you need to prove a specific hook fired or a CLI command works without manual testing overhead.
WORKS 48
Synthesize journey into PMF investor memoskillProductL1
ent-pmf-memo · When you need a single shareable document that honestly answers 'where are you on PMF?' for investors or early hires.
WORKS 48
Turn discovery notes into problem statementskillProductL1
ent-problem-statement · When a founder has finished a discovery batch and needs to crystallize one sharp problem before designing a solution.
WORKS 48
Publish npm package via GitHub ActionsskillEngineeringL2
publish · When you need end-to-end release orchestration across npm, GitHub, lazycodex, and Discord in a single coordinated workflow.
WORKS 48
Fix AI prompts that produce generic outputskillEngineeringProductL1
ent-prompt-troubleshoot · When AI output is disappointing and the fix is in the prompt, not the model — saves time vs trying new models.
WORKS 48
Remove unused code with safety verificationskillEngineeringL2
remove-deadcode · When you need to clean dead code at scale without manually hunting — LSP verification prevents false positives.
WORKS 48
Coach through research-driven inspiration methodologyskillProductL1
ent-rdi-coach · When a team is at 2–3/6 PMF and needs a framework to prioritize what retention/desperation lever to pull next.
WORKS 51
Red-team your strategy and assumptionsskillProductOpsL1
ent-red-team · When you're about to commit to a high-stakes decision and need multi-agent critique to surface blind spots before shipping.
WORKS 48
Match your stage to the right playbookskillProductL1
ent-stage-router · When a founder asks 'what do I do next?' and you need to route them to the right playbook without skipping prerequisites.
page 17 / 121