docs/zh-CN/skills/ecc-guide/SKILL.md
在回答之前先读取仓库的实时状态,引导用户了解 ECC 当前的 agents、skills、命令、hooks、规则、安装配置档案以及项目接入流程。
npx skillsauth add affaan-m/everything-claude-code ecc-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
当用户需要帮助来理解、浏览、安装 Everything Claude Code 或在其中做选择时,使用此技能。
当用户出现以下情况时使用此技能:
依据当前文件回答,而不是凭记忆。ECC 变化很快,硬编码的目录数量、功能列表和安装说明都会过时。
当 ECC 仓库可用时,先检查相关文件再给出具体答案:
node scripts/ci/catalog.js --json
find skills -maxdepth 2 -name SKILL.md | sort
find commands -maxdepth 1 -name '*.md' | sort
find agents -maxdepth 1 -name '*.md' | sort
node scripts/install-plan.js --list-profiles
node scripts/install-plan.js --list-components --json
只读取回答用户问题所需的最小文件集。
README.md:安装路径、卸载/重置指引、对外定位、常见问题AGENTS.md:贡献者指引和项目结构agent.yaml:导出的 gitagent 接口和命令列表commands/:持续维护的斜杠命令兼容垫片skills/*/SKILL.md:可复用的工作流和领域手册agents/*.md:用于委派的子代理角色提示词rules/:语言规则和运行环境规则hooks/README.md、hooks/hooks.json、scripts/hooks/:hook 行为和安全门控manifests/install-*.json:选择性安装的模块、组件、配置档案和目标支持docs/:运行环境指南、架构笔记、翻译文档、发布文档先给答案,再给下一步动作。大多数用户不需要完整的目录倾倒。
良好的首次回复结构:
避免:
给出一份简短菜单:
安装/重置指向 README.md,项目级接入指向 /project-init。
对于"我该用什么来做 X?":
skills/、commands/ 和 agents/。有用的搜索:
rg -n "<query>" skills commands agents docs
find skills -maxdepth 2 -name SKILL.md | sort
使用托管安装路径:
node scripts/install-plan.js --list-profiles
node scripts/install-plan.js --profile minimal --target claude --json
node scripts/install-apply.js --profile minimal --target claude --dry-run
针对特定 skill 的安装:
node scripts/install-plan.js --skills <skill-id> --target claude --json
node scripts/install-apply.js --skills <skill-id> --target claude --dry-run
提醒用户不要同时叠加插件安装和完整的手动/档案安装,除非他们有意要重复的组件面。
当用户想为目标仓库配置 ECC 时,使用 /project-init。预期顺序为:
CLAUDE.md 和设置文件先询问目标运行环境和安装路径,然后检查:
.claude/、.cursor/、.codex/、.gemini/、.opencode/、.codebuddy/、.joycode/ 或 .qwen/hooks/hooks.json针对仓库健康度,建议:
npm run harness:audit -- --format text
npm run observability:ready
npm test
Use <skill-or-command>. It fits because <reason>.
Canonical file: <path>
Verify with: <command>
Next: <one concrete action>
Best matches:
- <path>: <why it matters>
- <path>: <why it matters>
Recommendation: <which one to use first and why>
Detected: <stack evidence>
Target: <harness>
Plan: <profile/modules/skills>
Dry run: <command>
Would change: <paths>
Needs approval before apply: <yes/no>
/project-init:面向目标仓库的技术栈感知接入计划/harness-audit:确定性的就绪度评分卡/skill-health:skill 质量审查/skill-create:从本地 git 历史生成新 skill/security-scan:检查 Claude/OpenCode 配置安全性tools
Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.
data-ai
当用户希望通过并行工作、并发 agents、批量工具调用、隔离 worktree 或多条独立验证通道来大幅加速任务、同时不损失正确性时使用。
testing
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
tools
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.