165 skills · sorted by relevance
Set up Pact tests that record what a frontend expects from an API and verify those expectations against the backend. Review these contract tests to catch incompatible changes and help services be tested and deployed independently.
Take implementation work through small, independently mergeable pull requests. Use a separate working directory for each PR, record manual QA evidence, write English review descriptions, resolve CI and review findings, then merge and clean up.
Restructure claude-flow v3 into focused modules using Domain-Driven Design, which groups code by responsibility. Define module boundaries, event communication, and plugin interfaces to support a modular architecture with independently testable business logic.
Restructure claude-flow v3 into focused modules using Domain-Driven Design, which groups code by responsibility. Define module boundaries, event communication, and plugin interfaces to support a modular architecture with independently testable business logic.
Design separate paths for updating and reading data using CQRS, an approach that splits these responsibilities. Organize read models, event handling, and validation to support complex queries and scale reads independently from writes.
Connect TanStack Table v9 state to lit rendering. Manage state such as pagination through reactive properties, choose which changes trigger component updates, and subscribe to selected state so individual template regions can update independently.
Turn a named NemoClaw issue into an implementation plan with clear ownership, scope, completion criteria, and validation evidence. For larger changes, define independently useful steps, their dependencies, and delivery order.
Apply Apache ShardingSphere’s written coding standards during implementation or review, covering naming, Java constructs, tests, and Maven dependencies. Also audit a specified scope without editing files, combining automated checks with manual inspection of applicable rules.
Delegate coding, analysis, planning, and reviews from Codex to Claude Code through its command-line interface. Capture responses, resume sessions, or run independent tasks in parallel, then verify changed files and test results independently.
Independently checks code changes against the original issue, runs tests, and verifies that edits stay within scope. Produces an approval, rejection, or request for human judgment, supported by test results and specific findings.
Split a large commit or branch into a Graphite PR stack, a series of dependent review requests. Group changes by purpose, preserve changes that must stay together, and verify that each lower layer builds and passes tests independently.
Turn development requirements into an implementation plan with specific files, function signatures, tests, and verification commands. Use it before coding to document decisions and divide the work into independently testable tasks.
Plan personalized video outreach for prospective customers, from useful sample deliverables and short scripts to tool selection and follow-up sequences. Use viewing data to guide next steps and design product demos prospects can watch independently.
Splits a body of context into a sequence of vertical-slice build phases where each phase is independently demonstrable to a real user and each builds on the previous. Use when the user wants to plan, sequence, phase, slice, break down, or order the build of a feature, capability, system, or initiative, and produces a plain-language phased build outline. Does not produce implementation detail — use plan-implementation. Does not specify behavior that has not been decided — use plan-a-feature. Does not perform gap analysis between two artifacts — use gap-analysis. Does not break a plan into independently-grabbable work items — use plan-work-items.
The English summary is being prepared. Showing the original description.
Autonomous Agents workflow skill. Use this skill when the user needs Autonomous agents are AI systems that can independently decompose and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
The English summary is being prepared. Showing the original description.
Autonomous Agents workflow skill. Use this skill when the user needs Autonomous agents are AI systems that can independently decompose and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
The English summary is being prepared. Showing the original description.
Browse available specialist agents by domain, select up to five, and run them independently on the same task in parallel. Receive a combined report showing each agent’s findings, shared conclusions, conflicting recommendations, and suggested next steps.
Organize engineering work carried out by AI agents with clear completion criteria, small verifiable tasks, and evaluations before and after implementation. Match model choice to task complexity and track tokens, retries, time, and outcomes to manage cost.
Independently reviews deliverables handed over through Kanban, checks them against acceptance criteria and test evidence, and records an approval, actionable change request, or escalation when a human decision or external prerequisite is needed.
Turn an unclear feature idea into a structured specification with goals, boundaries, and testable success criteria. Split broader requests into independent modules when needed, then move through planning, task breakdown, and implementation with human review.
Create or update a SOUL.md file that defines an AI partner’s behavior through a guided conversation. Clarify communication style, autonomy, honesty, and expectations, then review a concise English profile before saving it with setup_agent.
Create a fixed JSON evaluation suite from a repository's existing tests and check its structure for errors. Use the suite with harness-evolve to compare variants against consistent tasks, independently of the repository's normal test command.
Plan HyperFrames videos so motion flows continuously between scenes. Match movement direction and speed across cuts, connect actions through visible causes, and verify scene boundaries while keeping each scene active through meaningful reveals or interactions.
Validate particle data and run RELION refinement for single-particle cryo-electron microscopy. Check independently refined half maps, calculate diagnostic map correlations, and perform soft-mask postprocessing while preserving execution logs and restart information.