Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Unified lifecycle management for all framework artifacts (skills, agents, hooks, workflows, templates, schemas)
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Convenience wrapper for the unified artifact lifecycle workflow.
This skill provides a simplified interface to the comprehensive artifact lifecycle management workflow at .claude/workflows/core/skill-lifecycle.md.
Use this skill when you need to:
// Invoke this skill
Skill({ skill: 'artifact-lifecycle' });
Full Workflow: .claude/workflows/core/skill-lifecycle.md
Check if artifact exists, compare versions.
Agent: architect Output: Discovery report with recommendations
Determine action: CREATE, UPDATE, or DEPRECATE.
Agent: planner Output: Action plan with tasks
Execute the determined action.
Agent: developer + appropriate creator skill Tools:
Skill({ skill: "skill-creator" }) for skillsSkill({ skill: "agent-creator" }) for agentsSkill({ skill: "hook-creator" }) for hooksSkill({ skill: "workflow-creator" }) for workflowsUpdate registries, catalogs, and CLAUDE.md.
Agent: developer Updates:
Test integration and verify references.
Agent: qa Checks:
User: "Create a skill for Kubernetes deployment"
Router spawns with:
Skill({ skill: "artifact-lifecycle" })
Workflow determines: CREATE mode
Invokes: skill-creator
Updates: registry, catalog, CLAUDE.md
Validates: skill invocable
User: "Update the devops agent to support Terraform Cloud"
Router spawns with:
Skill({ skill: "artifact-lifecycle" })
Workflow determines: UPDATE mode
Version: 1.0.0 → 1.1.0
Updates: agent file, CHANGELOG
Validates: agent referenced correctly
User: "Deprecate the old deployment workflow"
Router spawns with:
Skill({ skill: "artifact-lifecycle" })
Workflow determines: DEPRECATE mode
Adds: deprecation notice, migration guide
Updates: CLAUDE.md with replacement reference
Validates: no broken references
| Parameter | Values | Default |
|---|---|---|
| artifact_type | skill, agent, hook, workflow, template, schema | auto-detect |
| operation | create, update, deprecate, integrate | auto-detect |
| version_bump | major, minor, patch | minor |
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Skipping research-synthesis before CREATE | Risk of creating a duplicate or outdated artifact | Always run research-synthesis first |
| Starting action before Phase 2 decision | Wrong operation applied; CREATE when UPDATE needed | Complete Phase 2 before Phase 3 |
| Skipping Phase 5 validation | Broken artifacts delivered as complete | Always run invocability check |
| No catalog/registry update in Phase 4 | Artifact is invisible to agents and router | Always update catalog, registry, and CLAUDE.md |
| Using artifact-lifecycle for simple version bumps | Heavyweight process for lightweight work | Use skill-updater/agent-updater for UPDATE mode |
| Not specifying artifact_type | Wrong creator skill invoked silently | Always specify or verify artifact_type in Phase 1 |
.claude/context/memory/learnings.md before starting.claude/context/memory/decisions.md.claude/context/memory/issues.mdskill-creator - Direct skill creationagent-creator - Direct agent creationworkflow-creator - Direct workflow creationcodebase-integration - External artifact integration.claude/workflows/core/skill-lifecycle.md - Full lifecycle workflow.claude/workflows/core/external-integration.md - External artifact integration.claude/workflows/core/router-decision.md - Router decision flow还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
中文简介正在准备中。当前显示原文说明。
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
中文简介正在准备中。当前显示原文说明。
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
中文简介正在准备中。当前显示原文说明。