The library

sverklo · When sverklo capability is needed

openspec-explore · When Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change

haus-workflow · When haus workflow capability is needed

ai-fob · When ai fob capability is needed

sql-escaper · When sql escaper capability is needed

pi-dynamic-workflows · When pi dynamic workflows capability is needed

nexo-brain · When nexo brain capability is needed

doccraft-adr · - A chat or design exploration reached a conclusion worth keeping (yes, no, defer, or "use X instead of Y").

whyline · When you want to preserve the why behind code changes so future context windows recall intent without re-reading chat.

harnessed · When you want structured three-layer-stack workflow without learning each upstream terminology or manually routing stages.

adversarial-workflow · When you want battle-tested output that survives independent scrutiny rather than single-agent rubber-stamping.

anthropic · When integrating Claude calls into a Genkit pipeline or you need prompt caching and citations for reliability.

SKILL · When you need automated execution of this workflow.

pluxx · When you want real-time prospect relationship tracking without manual CRM data entry.

superpowers-streamer-cli · When you want live feedback on autonomous phone agent execution instead of post-execution logs.

pro-workflow · When you want structured project governance with explicit milestone tracking and risk visibility.

quien · When you need to understand relationships between entities in a graph instead of flat lookup.

claude-sdlc-kit · Teams that want issue-to-PR automation with design-plan-TDD-preview-e2e-merge in GitHub Actions.

skill · Wallets and block explorers needing fast account balances and token holdings without running a full NEAR node.

ai-kit · Teams setting up AI agents for the first time with standard documentation (PROJECT_OVERVIEW.md, CODING_CONVENTIONS.md).

software-teams · Development teams wanting end-to-end feature delivery without orchestrating agents manually.

SKILL · Teams with frequent parallel edits needing semantic merge without conflict markers.

runegard · Practitioners of Norse traditions wanting structured interpretation frameworks.

universal-scraping-architect · Data engineers needing flexible web scraping without writing per-site parsers.

pup · Quick one-off data extraction without setting up a full scraper framework.

vault-sync · Making a Vault readable via standard filesystem tools without needing Vault client.

SKILL · Decentralized apps (dapps) querying blockchain data without running a full node.

markdown-html-orchestrator · Sharing long-form documents (specs, RFCs, reports) with non-technical stakeholders via email.

md-document · Sharing long-form documents (specs, RFCs, reports) with non-technical stakeholders via email.

md-review · Single-file PR reviews with margin annotations and severity breakdowns.

skill · Injecting auditable, curated expertise into agentic systems with full source traceability.

cloud-identity-and-auth · Building cloud platforms with federated identity, zero over-privilege, and auditability.

distributed-consensus · Replicating state machines, electing leaders, and ensuring split-brain safety without blockchain.

distributed-storage · Apply distributed-storage when appropriate to your use case.

feishu-bridge · Tunneling agentic system messages to Feishu IM without polling when team uses Feishu-native workflows.

network-fundamentals-cloud · Building reliable cloud network topologies resistant to partitions and outages.

haskell-agent · Building provably-safe agents in Haskell when imperative patterns are error-prone.

reliability-engineering-cloud · Building infrastructure that humans can reliably operate and improve with data.

service-architecture · Building scalable systems where services fail independently without cascade.

algorithms-data-structures · Solving programming interview problems and building efficient systems without trial-and-error.

computational-thinking · Tackling novel algorithmic problems when no pre-built library fits.

debugging-testing · Finding production bugs and preventing them via systematic testing rather than trial-and-error

programming-fundamentals · Teaching programming from first principles when you need mental models, not just syntax

software-design · Making architectural decisions that reduce coupling, improve testability, and make wrong things hard

systems-programming · Understanding and optimizing code that cannot ignore hardware constraints (kernels, embedded, HFT, databases)

skill · Structuring a multi-phase implementation of a full-stack mobile app with modern UI and backend auth

skill · Quick baseline review when no domain expert is available

skill · Ensuring consistency and preventing forgetting standard steps in recurring processes

skill · Ensuring consistent execution of repeatable tasks where quality is critical

skill · When this is the appropriate approach for the task.