2.5K skills · sorted by relevance
Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.
Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.
Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.
Coordinate multiple AI agents with agentic-flow to run tasks in parallel or through ordered stages. Configure shared memory, team structure, workload distribution, retries, and task reassignment, then monitor how the group performs.
Implement agents that use recorded task outcomes to choose future approaches. ReasoningBank supports matching past patterns, comparing strategies, retaining experience in AgentDB, and tracking how strategy success and learning change over time.
Coordinate 15 agents implementing claude-flow v3 across security, core systems, integration, testing, performance, and release work. Provides role assignments, task dependencies, GitHub tracking examples, and a four-phase schedule spanning 14 weeks.
Find official documentation for a library, framework, or API and apply it to the task at hand. Check the relevant version, distinguish documented facts from assumptions, and verify code changes with a focused test or concrete command.
Build features or fix bugs by writing a small test first, checking that it fails for the expected reason, and making the smallest code change needed. Run related tests and review the changes for unintended effects.
Audit a codebase for unnecessary complexity, including dead code, duplicated state, redundant interfaces, and obsolete compatibility paths. Receive evidence-backed simplification candidates, or authorize changes that remove justified targets and validate the behavior that must remain.
Evaluate substantial software changes against the actual problem, current system, and concrete users or components that need them. Choose a sufficient scope, assess consequences, and, when implementation is requested, make the change and verify its behavior.
Implement and manage Raft, a method for keeping distributed servers in agreement. Covers leader election, log replication, node membership changes, and recovery after network disruptions to maintain consistent state across the cluster.
Improve existing code through repeated cycles of testing, implementation, and refactoring. The skill covers performance bottlenecks, error recovery, code coverage, and documentation, helping developers refine behavior and structure while keeping tests passing.
Implement distributed data synchronization with CRDTs, data structures designed to merge concurrent updates. Covers counters, sets, shared values, and sequences, with incremental updates and tracking of dependencies between operations.
Turn specifications and designs into working code using test-driven development: write failing tests, implement enough code to pass, then refactor. The workflow also covers error handling, performance improvements, documentation, and coordinated changes across components.
Build a Claude Code mod, a plugin that extends behavior through event hooks, from ruflo’s template. Sets up function hooks with a classic fallback, user options, status reporting, validation, and tests.
Develop features through a test-first workflow using mocks, or stand-ins for dependencies. Write a failing behavior test, implement the minimum code, refactor, and record observed results from final target and regression tests.
Turn an approved specification into pseudocode, a plain outline of program logic, and an architecture defining module responsibilities and API inputs and outputs. After user confirmation, proceed with implementation and unit tests based on those designs.
Automatically repair source code against a failing test while preserving the test itself. Set a spending limit and attempt count, then receive verification results and usage costs based on rerunning the test command.
Set up a coordinated team of three or more AI agents for development tasks spanning multiple files. Configure the team structure, assign specialized roles, and prepare parallel work with named agents and messaging.
Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.
Build agents that record task outcomes and use past experience to choose future approaches. Implement pattern matching, strategy comparisons, persistent learning records, and metrics for checking how recommendations and results change over time.
Coordinate 15 agents implementing claude-flow v3 across security, core systems, integration, testing, performance, and release work. Provides role assignments, task dependencies, GitHub tracking examples, and a four-phase schedule spanning 14 weeks.
Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.
Coordinates multiple AI agents with agentic-flow to run tasks in parallel or through dependent stages. It covers team communication structures, shared memory, workload balancing, failure recovery, and performance monitoring for complex workflows.