Claude Skills by seaworld008

根据项目代码自动生成贴合仓库约定的技能。

Design agent orchestration, handoffs, state, recovery, and evaluation when a workflow needs multiple coordinated agents or tools.

Karpathy-inspired coding discipline for AI agents: think before coding, keep changes simple, edit surgically, and define verifiable success criteria before implementation.

Design REST/GraphQL APIs, module interfaces, and type contracts when creating endpoints or changing public boundaries.

Use before creative product or engineering work when the user wants to design a feature, component, workflow, behavior change, or other solution whose goals, constraints, and tradeoffs need exploration before implementation.

Inspect browser DOM, network, console, screenshots, and performance with Chrome DevTools MCP when validating or debugging web behavior.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Review code changes for correctness, maintainability, security, and validation evidence before integration or when a review is requested.

Refactor working code for clarity and maintainability while preserving behavior; use when complexity or duplication obstructs changes.

Diagnose missing or overloaded agent context and configure project instructions when setup or context quality is the task.

Diagnose failing tests, broken builds, and unexpected runtime behavior through reproduction, evidence, root-cause analysis, and focused recovery.

Produce source-backed research reports, literature reviews, or technical and market briefs when evidence tracking and a defined report format matter.

Plan deprecation and migration of systems, APIs, and production schemas, including expand-contract changes with compatibility and rollback requirements.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Review high-risk or uncertain engineering decisions adversarially when independent verification can expose costly assumptions before implementation.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when users do not know which skill fits a task, need to search available skill catalogs, compare candidates, install a matching skill, or route work to the best existing capability.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Build accessible, responsive interfaces and components with production UI states, project conventions, and browser validation.

Manage branches, commits, conflicts, semantic versions, and changelogs when preparing Git changes or releases.

Explore alternatives and stress-test assumptions when refining a vague idea into a concrete concept or evaluating an early plan.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you''re about to write a large amount of code at once, or when a task feels too big to land in one step.

Interview the user when they request guided discovery or when unresolved goals, audience, or constraints materially affect a proposed solution.

多智能体任务分解、链路编排、执行协调和结果整合。

Audit SKILL.md, AGENTS.md, prompts, hooks, and plugin manifests for instruction conflicts, quality, broken references, and manifest-to-disk drift.

Add or improve logs, metrics, traces, and alerts when services need diagnosable production behavior or operational acceptance evidence.

Investigate and improve measured frontend, backend, query, or database bottlenecks; use profiling and workload evidence to protect the gains.

Turn clear requirements into ordered tasks, dependencies, and acceptance checks; preserve unfinished work when revising an existing plan.

Refine prompts or ambiguous requirements into testable specifications when the user asks to improve wording, scope, constraints, or acceptance criteria.

多会话并行执行编排，协调多个智能体共同完成任务。

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Harden authentication, input handling, storage, and integrations when implementing security controls or remediating concrete vulnerabilities.

把复杂任务拆成短步骤，控制漂移并推进交付。

Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

Create or improve agent skills, trigger descriptions, and evaluation cases; use when packaging a workflow or measuring skill behavior.

Review and improve agent skills for clear triggers, actionable instructions, progressive disclosure, reliable resources, and evidence-backed validation.

Verify implementation against official documentation when the task requests source-backed changes or depends on unfamiliar or changing framework APIs.

Specify new features or substantial behavior changes when goals, boundaries, and acceptance criteria need agreement before implementation.

Use when executing implementation plans with independent tasks in the current session

Develop testable logic or fix behavioral bugs with focused regression tests and a red-green-refactor loop where it provides useful evidence.

Find the most relevant engineering skill when task routing is unclear; load only the guidance needed for the current work.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Select relevant Superpowers workflow skills when the user requests that workflow or a concrete development task benefits from its process guidance.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Write a practical implementation plan when multi-step work needs task boundaries, dependencies, and acceptance checks.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.