cyberneticlibrary

The library

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

ArtifactsCapabilitiesRecipes
kindallskillworkflowmcp_servercommandsubagentplugin|✓ proven✗ harmfulmeasured only1,482 artifacts
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
WORKS 19
Prepare for meetings with structured intelligenceskillOpsSalesL2-16pp measured
meeting-prep · When preparing for high-stakes meetings with key stakeholders and you need structured context on who, what, and how to position.
WORKS 27
Report progress across active sessionscommandOpsL1-8pp measured
sprint-status · Quick snapshot of progress across parallel Claude Code sessions before switching contexts.
WORKS 11
Compress meeting prep into sharper follow-upskillSalesOpsL2-24pp measured
meeting-prep · Sales reps and founders who have back-to-back meetings and need to compress 30-minute research into 2 minutes while walking to the meeting, with a follow-up email sent before they close their laptop.
WORKS 56
Audit milestones with adversarial reviewworkflowOpsEngineeringL3
wf-milestone-audit · Accelerating milestone validation with parallel dimension checks and adversarial bias detection.
WORKS 60
Audit codebases for security and performanceworkflowEngineeringOpsL3
code_audit · Parallel 3-phase security/style/synthesis audit with cross-file pattern detection.
WORKS 57
Score items with adversarial votingworkflowDataOpsL3
wf-swarm-score · Verifying adversarial score spreads and detecting hallucinating ants via 3-role consensus.
WORKS 58
Scan and fix AI patterns deterministicallyworkflowEngineeringOpsL4
de-ai-pipeline · Data-driven de-AI fix loop where detection is deterministic and fixing is AI-driven and bounded.
WORKS 56
Reduce SaaS churn with retention strategiesskillMarketingOpsL2
churn-prevention · SaaS products where involuntary churn exceeds 20% or voluntary churn lacks targeting.
WORKS 53
Route ticket through verification gatesworkflowOpsL3
forge-run-ticket · Executing complex multi-phase workflows with typed outputs.
WORKS 59
Extract and aggregate sprint lessonsworkflowOpsL3
sprint-lessons · Executing complex multi-phase workflows with typed outputs.
WORKS 53
Document processes with verification checkpointsskillOpsL1
sop-builder · Critical repeatable processes (deployments, migrations, incident response) where precise step order and verification prevent outages and tribal knowledge loss.
WORKS 57
Generate workshop slides and notesworkflowEngineeringOpsL3
workshop-generate · Generating workshop slides in phases: per-SECTION fan-out enforces intra-section flow and composability; assembly gate catches compile errors before marking success.
WORKS 55
Run parallel area auditsworkflowEngineeringOpsL3
area-audit · Fast multi-perspective code audits with adversarial filtering of false positives; HIGH findings must be independently verified before inclusion in report.
WORKS 58
Cluster feedback into themesworkflowProductOpsL2
feedback-themes · Digesting user feedback batches without manual labeling.
WORKS 55
Generate German learning programworkflowOpsProductL3
german-program · Managing multi-stage product lifecycles with validation gates between phases.
WORKS 57
Scaffold eight-role dev pipelineworkflowEngineeringOpsL4
dev-team-pipeline · End-to-end feature delivery when structured handoff-by-file-path and invariant gates matter more than ad-hoc coordination
WORKS 59
Produce validated ebooksworkflowOpsProductL3
ebook · Long-form knowledge products where source verification + adversarial claim-checking beats single-author trust
WORKS 59
Audit and fix paper digitization end-to-endworkflowOpsL3
full-pass · Quick full-pass paper review when single-agent depth sufficient
WORKS 59
Assess release readiness with parallel risk checksworkflowOpsL2
release_check · Assessing release safety before shipping with parallel risk checks.
WORKS 58
Generate daily standup from agent dataskillOpsL2
daily-standup · Team standup where you need to map Claude Code activities to business outcomes without manual log review.
WORKS 55
Build complete client onboarding packagesskillOpsL1
client-onboarding · New service engagements where alignment and clear expectations prevent early-stage friction and rework—eliminates the typical 2-week ramping chaos.
WORKS 55
Coordinate release prep phases 1A and 1BworkflowEngineeringOpsL3
release-prep-phase1 · Best for: complex multi-phase orchestration with parallelization and adversarial gates.
WORKS 54
Execute 10-phase major release workflowworkflowEngineeringOpsL3
v5-0-full-lifecycle · Coordinating a major release with 10 phases and cross-team dependencies.
WORKS 59
Generate sprint summary with velocity metricsskillOpsEngineeringL2
sprint-summary · Engineering/product leads presenting sprint progress to stakeholders with data-driven efficiency and cost trends.
WORKS 52
Decide when to hire vs use AIskillOpsHRL1
hiring · Solo founders deciding whether to invest in hiring before scaling to a team, when the line between AI-capable and human-necessary work is blurry.
WORKS 55
Forge and validate ideas across lensesworkflowProductOpsL3
idea-forge · When forging novel research ideas for a specific venue and you want adversarial judges to rank by feasibility and contribution.
WORKS 60
Score and route agent descriptionsworkflowEngineeringOpsL3
routing-rubric-pass · Managing multi-stage product lifecycles with validation gates between phases.
WORKS 59
Plan discovery interviews that validate ideasskillProductOpsL1
discovery-interview-prep · Product managers validating new markets or churn problems who need to avoid wasting customer time and research budget on misaligned interview design.
WORKS 57
Generate weekly productivity reportskillOpsProductivityL2
weekly-report · Individual contributor or team lead reviewing personal/team productivity—weekly check-in on what worked and what to optimize.
WORKS 56
Run fierce debate on high-stakes decisionsworkflowOpsProductL3
fierce-debate · High-stakes architectural or strategic decisions requiring adversarial pressure-testing.
WORKS 57
Run 15-minute weekly review for CEO clarityskillOpsProductivityL1
weekly-review · Founder-CEOs who feel unmoored without a dashboard, or whose weeks blur together, and need ONE repeatable habit that compounds toward clarity and course-correction discipline.
WORKS 55
Archive completed project plansworkflowOpsL2
organize-completed-plans · Bulk file reorganization tasks with frontmatter-based categorization.
WORKS 55
Conduct deep research with verified sourcesworkflowProductOpsL3
deep_research · Multi-source research with synthesis and adversarial fact-checking.
WORKS 58
Plan work with time estimatesskillOpsProductivityL1
productivity · Breaking work into shippable vertical slices with time estimates and energy-aware scheduling.
WORKS 59
Run weekly site health check reportworkflowOpsProductL3
weekly-checkin · Unattended weekly health checks (GSC, deploy, links, schema, CWV).
WORKS 55
Analyze site structure deeplyworkflowProductOpsL3
site-deep-analyze · Deep site analysis combining Playwright crawl, static DOM/CSS inspection, and vision-based UI classification.
WORKS 54
Orchestrate executive priorities and meetingsskillOpsL3
chief-of-staff · Early-stage startups or scale-ups with busy executives who need someone to enforce decision discipline and meeting structure.
WORKS 58
Migrate research workflow to productionworkflowEngineeringOpsL3
weekly-research-workflow-poc · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 55
Get Claude Code metrics at a glanceskillOpsL2
quick-stats · Quick status check in a terminal prompt without leaving your REPL—scan cost/token/session health in 5 seconds.
WORKS 59
Create live dashboards in ObsidianskillOpsL2
wiki-dashboard · Custom Obsidian vault dashboards when native Bases (no plugin) is available and views should filter/group by folder, tag, or property.
WORKS 53
Update GEO-SEO toolkit to latest versionskillOpsEngineeringL2
geo-update · Keeping GEO-SEO toolkit in sync with upstream without manual file management.
WORKS 54
Produce evidence-based weekly business retrosskillOpsL3
money-retro · Founders and business owners doing regular business retros grounded in actual disk state (snapshots, learnings, skill usage) rather than memory.
WORKS 58
Delegate tasks and rebalance team workloadcommandOpsL2
team-delegate · Quick team task delegation with workload balancing, member messaging, and unassigned task triage.
WORKS 59
Review and approve plans before implementationcommandOpsL3
plan-review · Multi-turn agent workflows where a human must review a plan before expensive implementation decisions are locked in.
WORKS 43
Audit system health and deviationsworkflowOpsL3
audit-loop · Run on the recurring /loop audit fire to deterministically check gm + rs-* for drift from the paper MO
WORKS 58
Identify and delegate tasks to scale fastskillOpsL1
delegation · Founders stuck between Level 1–2 (Doer/Delegator transition, $0-$1.5M revenue) who feel bottlenecked but haven't systematized delegation, and need permission to stop doing everything personally.
WORKS 55
Conduct blameless incident postmortemworkflowOpsL2
incident-postmortem · After any production incident or near-miss. Output is a blameless postmortem ready for team review and action-item tracking.
WORKS 52
Write scannable sprint briefsskillOpsL1
sprint-brief · Mixed teams (eng, design, PM) needing a single source of truth that every role can scan before standup.
WORKS 55
Synthesize multi-source research with verificationworkflowOpsDataL3
research · Exploratory research with parallel hypothesis agents and cross-check synthesis.
WORKS 59
Translate and iteratively refine contentworkflowMarketingOpsL3
translation-qa · Iterative quality improvement where an analyzer-editor loop converges until no issues are found twice in a row.
page 1 / 30→