All authors
Claude Skills by tylerjrbuell
github.com/tylerjrbuell53 skills0 installs7 views
- Agent TddTest-Driven Development for the Reactive Agents codebase. Effect-TS aware TDD with mandatory timeout flags, Effect.flip error testing, Layer isolation, and dangling-server prevention. Use when implementing any feature or fixing any bug.Votes: 0GitHub stars: 28
- Architecture AuditUse when the architecture may have drifted from documentation, packages have grown complex, dead code or disabled systems are suspected, or before planning a major refactor — scoped to the reactive-agents-ts 22-package monorepo.Votes: 0GitHub stars: 28
- Architecture ReferenceReactive Agents framework architecture — layer stack, dependency graph, build order, and package structure. Use when planning work, understanding package relationships, or determining build dependencies.Votes: 0GitHub stars: 28
- Build CoordinatorCoordinate cross-cutting changes, incremental features, and multi-package modifications across the Reactive Agents monorepo. Defines team structure, task assignment, parallelization strategy, and inter-package dependency gates.Votes: 0GitHub stars: 28
- Build PackageAdd a new package to the Reactive Agents monorepo. Covers scaffolding, package.json, tsconfig, layer wiring, and index exports. Use when creating a net-new @reactive-agents/* package.Votes: 0GitHub stars: 28
- Codebase Health SweepUse when the codebase may have accumulated bugs, failing tests, type errors, dead code, inefficiencies, or drift from known quality standards — before a release, after a large feature merge, or on a recurring maintenance cadence. Also triggers when build is red, `bun test` has unexpected failures, or TypeScript errors spiked after refactors.Votes: 0GitHub stars: 28
- Effect Abstraction AuditUse when analyzing the Reactive Agents codebase for architectural improvements, abstraction opportunities, composability gaps, or Effect-TS engineering quality — before proposing refactors, during design reviews, or when codebase complexity is growing.Votes: 0GitHub stars: 28
- Effect Ts PatternsMandatory Effect-TS coding patterns for the Reactive Agents framework. Use when writing any TypeScript code, creating services, defining types, handling errors, or composing layers in this project.Votes: 0GitHub stars: 28
- Execute BacklogUse when ready to attack the GitHub issue backlog with discipline. Scans open issues, bundles related work into an efficient execution plan, executes the bundle with verification, then closes issues + writes a retrospective that includes self-improvement notes for this skill. Trigger phrases — "execute backlog", "work the backlog", "knock down P1 issues", "ship a bundle", "/execute-backlog".Votes: 0GitHub stars: 28
- Harness Improvement LoopAgentic harness diagnostic + improvement loop. Probes the framework with real model runs, uses the rax-diagnose CLI to root-cause failures from structured trace data, ships ONE coordinated architectural fix, verifies via before/after diff, commits with empirical evidence. Use at the start of any harness improvement session — replaces ad-hoc grep + log-spelunking with a deterministic feedback loop.Votes: 0GitHub stars: 28
- Implement ServiceCreate a new Effect-TS service following the mandatory Reactive Agents patterns. Use when adding a service to any package.Votes: 0GitHub stars: 28
- Implement TestWrite tests for a Reactive Agents package or service using Bun test runner and Effect-TS patterns. Use when creating tests for any module in this project.Votes: 0GitHub stars: 28
- Kernel DebugDebug agent reasoning failures using the composable kernel phase map. Maps symptoms to specific files and grep commands. Use when an agent is not calling tools, looping, producing wrong output, or failing silently.Votes: 0GitHub stars: 28
- Kernel ExtensionAdd new behavior to the composable kernel — new Phase, Guard, MetaTool, or custom kernel variant. Use when extending agent reasoning, adding tool call filtering, or building a custom kernel for a new strategy.Votes: 0GitHub stars: 28
- Llm Api ContractLLMService API contract — the correct signatures for complete(), stream(), embed(), and response types. Use when calling LLMService from any layer, writing reasoning strategies, or building LLM-dependent features.Votes: 0GitHub stars: 28
- Mcp IntegrationMCP client integration patterns for packages/tools/src/mcp/. Docker container lifecycle, transport auto-detection, two-phase container naming, and cleanup. Use when working on MCP server configuration, docker-based MCP tools, or the mcp-client.Votes: 0GitHub stars: 28
- Memory PatternsSQLite and memory system patterns specific to the @reactive-agents/memory package. Use when working on the memory layer, database operations, FTS5 search, Zettelkasten, or sqlite-vec KNN.Votes: 0GitHub stars: 28
- Mission BriefCompose a MissionBrief YAML block to prepend to any Agent dispatch to a warden. Use BEFORE spawning kernel-warden or any other warden. Fails if missing end-state, why, authority-bounds, or success-criteria.Votes: 0GitHub stars: 28
- Prepare ReleaseUse when cutting, tagging, or publishing a new Reactive Agents version, or when a release/publish run fails and needs resuming. Covers the tag-driven lockstep flow (scripts/release.ts + .github/workflows/publish.yml).Votes: 0GitHub stars: 28
- Provider StreamingLLM provider streaming patterns and per-provider quirks. Use when adding a new provider, implementing adapter hooks, or debugging streaming tool call behavior in packages/llm-provider.Votes: 0GitHub stars: 28
- Prune MemoryAudit project memory (.agents/MEMORY.md and ~/.claude/.../memory/MEMORY.md) against current code and remove stale claims to prevent bad signals in future sessionsVotes: 0GitHub stars: 28
- Reactive Feature DevComplete feature development workflow for Reactive Agents. Orchestrates the correct sequence of skills for any feature type. Use at the start of any non-trivial implementation task to route to the right skills and follow the right order.Votes: 0GitHub stars: 28
- Review PatternsReview code changes for Effect-TS pattern compliance in the Reactive Agents framework. Use when reviewing PRs, completed packages, or any code changes to enforce project conventions.Votes: 0GitHub stars: 28
- Session RecapGenerate structured session recap and auto-extract high-confidence learnings into project memoryVotes: 0GitHub stars: 28
- Update DocsFull docs lint, validate, and update pass — Starlight docs (incl. What's New release banners), README, AGENTS, CAPABILITIES manifest, CHANGELOG, skills, memory. Use after completing a feature, fixing bugs, changing public APIs, or cutting a release, and whenever docs need a truthfulness/drift audit across the board.Votes: 0GitHub stars: 28
- Upward ReportMandatory output contract for warden agents. Warden agents append a YAML upward-report block as the last content of their response. Parent (main thread) parses and routes via dispatcher FSM. Use when you are a warden agent finishing a task, OR when you are the parent consuming a warden's output.Votes: 0GitHub stars: 28
- Validate BuildValidate a completed package against its spec. Checks patterns, types, exports, dependencies, and test coverage after building a package.Votes: 0GitHub stars: 28
- Surface High Leverage WorkUse when picking what to work on next — finding and ranking the bug fixes or new capabilities that would most impact users, before a sprint or backlog session. Triggers — "what should I work on next", "find high-leverage work", "prioritize the backlog", "update recommended enhancements", "/surface-high-leverage-work".Votes: 0GitHub stars: 28
- TestSmoke-test skill for the Cortex desk. Use to verify Living skills paths (e.g. apps/cortex/.agents/skills) load via withSkills. No side effects.Votes: 0GitHub stars: 28
- A2a Agent NetworkingExpose agents as A2A JSON-RPC servers discoverable via Agent Cards, and connect agents to remote A2A agents using the client discovery and capability-matching APIs.Votes: 0GitHub stars: 28
- Builder Api ReferenceConfigure a ReactiveAgentBuilder with the correct layer composition for any agent use case.Votes: 0GitHub stars: 28
- Context And ContinuityManage context pressure, configure message windowing, and use checkpoint tools to preserve critical findings across context compaction.Votes: 0GitHub stars: 28
- Cost Budget EnforcementSet per-request, per-session, daily, and monthly spend limits, configure rate limiting and circuit breakers, and isolate costs per user or tenant.Votes: 0GitHub stars: 28
- Gateway Persistent AgentsBuild always-on agents with heartbeats, cron scheduling, webhook triggers, and a persistent policy engine using the Gateway layer.Votes: 0GitHub stars: 28
- Identity And GuardrailsEnable prompt injection detection, PII masking, behavioral contracts, kill switch controls, and audit logging for safe production deployments.Votes: 0GitHub stars: 28
- Interaction AutonomyControl agent autonomy with durable human-in-the-loop approval gates, agent-initiated user-input pauses, and runtime pause/resume/stop controls.Votes: 0GitHub stars: 28
- Mcp Tool IntegrationConnect agents to MCP servers using stdio or HTTP transport, with automatic Docker lifecycle management and transport auto-detection.Votes: 0GitHub stars: 28
- Memory PatternsConfigure the 4-layer memory system with SQLite/FTS5/vec storage for persistent agent knowledge that survives sessions.Votes: 0GitHub stars: 28
- Multi Agent OrchestrationCompose multiple agents as callable tools, spawn dynamic sub-agents at runtime, and wire remote A2A agents into a coordinated pipeline.Votes: 0GitHub stars: 28
- Observability InstrumentationConfigure verbosity levels, live log streaming, JSONL file export, model I/O logging, and audit trails for monitoring agent execution.Votes: 0GitHub stars: 28
- Provider PatternsConfigure per-provider behavior, understand streaming quirks, and use the 5-hook adapter system for optimal performance across LLM providers.Votes: 0GitHub stars: 28
- Quality AssuranceEnable output verification (hallucination detection, semantic entropy, self-consistency), add post-run verification steps, and run LLM-scored evals across 5 quality dimensions.Votes: 0GitHub stars: 28
- Reactive AgentsOrient to the Reactive Agents framework, understand the builder API shape, and select the right capability skills for your task.Votes: 0GitHub stars: 28
- Reasoning Strategy SelectionSelect and configure the right reasoning strategy, native FC behavior, and output quality pipeline for any task type.Votes: 0GitHub stars: 28
- Recipe Code AssistantFull recipe for a code assistant with shell execution, file read/write, git integration, and sandboxed code running.Votes: 0GitHub stars: 28
- Recipe Embedded App AgentFull recipe for embedding an agent in a Next.js app with streaming API routes, React hooks, progressive disclosure of reasoning steps, and error handling.Votes: 0GitHub stars: 28
- Recipe Orchestrated WorkflowFull recipe for a 3-agent pipeline (researcher → writer → reviewer) coordinated by a lead orchestrator agent using withAgentTool().Votes: 0GitHub stars: 28
- Recipe Persistent MonitorFull recipe for a persistent monitoring agent with heartbeats, daily cron reports, webhook triggers, daily token budgets, and graceful shutdown.Votes: 0GitHub stars: 28
- Recipe Research AgentFull recipe for a web research agent with memory, semantic search, hallucination verification, and source-cited synthesis.Votes: 0GitHub stars: 28
- Recipe Saas AgentFull recipe for a production-ready SaaS agent with guardrails, per-user cost isolation, rate limiting, A2A exposure, audit logging, and graceful error handling.Votes: 0GitHub stars: 28