Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ECC の現在のエージェント、スキル、コマンド、フック、ルール、インストールプロファイル、およびプロジェクトオンボーディングをガイドしています。ライブリポジトリサーフェスを読んでから回答するようユーザーをガイドします。
.claude/skills/affaan-m-ecc-guide/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -4% | 0% |
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：
bashnode 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：
bashrg -n "<query>" skills commands agents docs find skills -maxdepth 2 -name SKILL.md | sort
使用托管安装路径：
bashnode 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：
bashnode 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：
bashnpm run harness:audit -- --format text npm run observability:ready npm test
textUse <skill-or-command>. It fits because <reason>. Canonical file: <path> Verify with: <command> Next: <one concrete action>
textBest matches: - <path>: <why it matters> - <path>: <why it matters> Recommendation: <which one to use first and why>
textDetected: <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| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→pass | 9,996 | 5,375 | -46% | 1 | 1 | 0% | 1,713 | 2,238 | +31% | 0 | 0 | — |
case-07 | fail→pass | 15,890 | 3,065 | -81% | 1 | 1 | 0% | 2,062 | 1,885 | -9% | 0 | 0 | — |
case-01 | fail→fail | 5,731 | 5,778 | +1% | 1 | 1 | 0% | 979 | 1,683 | +72% | 0 | 0 | — |
case-02 | fail→fail | 10,699 | 5,971 | -44% | 1 | 1 | 0% | 1,732 | 1,670 | -4% | 0 | 0 | — |
case-03 | fail→fail | 3,968 | 4,572 | +15% | 1 | 1 | 0% | 189 | 1,669 | +783% | 0 | 0 | — |
case-04 | fail→pass | 8,412 | 5,508 | -35% | 1 | 1 | 0% | 1,500 | 2,403 | +60% | 0 | 0 | — |
case-05 | fail→fail | 4,709 | 5,252 | +12% | 1 | 1 | 0% | 834 | 1,757 | +111% | 0 | 0 | — |
case-06 | fail→pass | 9,538 | 2,152 | -77% | 1 | 1 | 0% | 1,342 | 1,722 | +28% | 0 | 0 | — |
case-09 | fail→pass | 16,925 | 6,708 | -60% | 1 | 1 | 0% | 2,167 | 2,076 | -4% | 0 | 0 | — |
case-10 | fail→pass | 7,524 | 4,125 | -45% | 1 | 1 | 0% | 1,088 | 1,925 | +77% | 0 | 0 | — |
case-11 | fail→pass | 25,534 | 4,974 | -81% | 1 | 1 | 0% | 2,196 | 2,235 | +2% | 0 | 0 | — |
case-12 | fail→pass | 10,230 | 2,540 | -75% | 1 | 1 | 0% | 1,783 | 1,876 | +5% | 0 | 0 | — |
case-13 | fail→pass | 11,817 | 2,805 | -76% | 1 | 1 | 0% | 1,892 | 1,807 | -4% | 0 | 0 | — |
case-14 | fail→pass | 11,827 | 3,160 | -73% | 1 | 1 | 0% | 1,683 | 1,811 | +8% | 0 | 0 | — |
case-15 | fail→pass | 8,307 | 3,702 | -55% | 1 | 1 | 0% | 1,398 | 2,036 | +46% | 0 | 0 | — |
case-16 | fail→fail | 12,284 | 5,089 | -59% | 1 | 1 | 0% | 2,075 | 1,597 | -23% | 0 | 0 | — |
case-17 | fail→pass | 14,233 | 2,780 | -80% | 1 | 1 | 0% | 2,275 | 1,843 | -19% | 0 | 0 | — |
case-18 | fail→fail | 21,927 | 6,753 | -69% | 1 | 1 | 0% | 3,850 | 1,855 | -52% | 0 | 0 | — |
case-19 | fail→pass | 9,577 | 5,409 | -44% | 1 | 1 | 0% | 1,530 | 2,250 | +47% | 0 | 0 | — |
case-20 | pass→pass | 15,718 | 9,134 | -42% | 1 | 1 | 0% | 3,133 | 3,265 | +4% | 0 | 0 | — |
case-21 | pass→pass | 12,357 | 8,984 | -27% | 1 | 1 | 0% | 2,550 | 3,188 | +25% | 0 | 0 | — |
case-22 | pass→pass | 8,939 | 4,347 | -51% | 1 | 1 | 0% | 1,697 | 2,070 | +22% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 16 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +59 percentage points is the difference between those two pass rates over the 16 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.