Improve agent documentation and prose / 改进 Agent 文档与 Markdown 文案

[adibarra]

Description

• Establish docs/index.md as the low-context documentation hub for contributors and agents.
• Add synchronized English and Simplified Chinese guides for architecture, configuration, CI, evaluations, AgentX, testing, troubleshooting, recovery, results ingestion, and documentation maintenance.
• Canonicalize reusable agent skills under .agents/skills/ with Claude compatibility links.
• Require a new tail-appended perf-changelog.yaml entry for every benchmark-performance-affecting change and every added or modified recipe.
• Humanize Markdown prose while preserving commands, links, numeric values, and technical behavior.

Related Issue

None.

Type of Change

• Bug fix
• New feature
• Configuration change
• Documentation update
• Other (please describe)

Checklist

• I have tested my changes locally
• I have updated documentation if necessary
• For every change that can affect benchmark performance and every recipe addition or modification, I have appended a new entry to the physical end of perf-changelog.yaml and have not edited historical entries. This PR does not change benchmark behavior or recipes, so no changelog entry is required.
• Before merging via reuse, an authorized maintainer (OWNER/MEMBER/COLLABORATOR) has commented /reuse-sweep-run on this PR. This remains pending until merge approval.

Verification

• Scanned all 82 Markdown files with zero unprotected ASCII semicolons or U+2014 em dashes.
• Checked 953 local links and anchors with zero failures.
• Confirmed all 14 new bilingual pairs have matching heading structures and language switchers.
• Parsed .github/workflows/claude.yml successfully.
• Smoke-tested the public results API with a valid DeepSeek-V4-Pro 8k1k result.
• Ran git diff --cached --check successfully before committing.
• Independent reviews found no remaining issues in the root documentation, operational guides, command files, or CollectiveX methodology.

中文说明

变更内容

• 将 docs/index.md 建设为面向贡献者与 Agent 的低上下文文档入口。
• 新增中英文同步的架构、配置、CI、评估、AgentX、测试、故障排查、恢复、结果摄取与文档维护指南。
• 将可复用的 Agent 技能统一维护在 .agents/skills/，并保留 Claude 兼容链接。
• 明确要求所有可能影响基准测试性能的变更，以及所有新增或修改的配方，都必须在 perf-changelog.yaml 物理末尾追加新条目。
• 在保持命令、链接、数值和技术行为不变的前提下，统一优化 Markdown 文案。

关联 Issue

无。

变更类型

文档更新。

验证结果

• 扫描全部 82 个 Markdown 文件，普通正文中没有未受保护的 ASCII 分号或 U+2014 长破折号。
• 检查 953 个本地链接与锚点，未发现错误。
• 确认 14 组新增双语文档的标题结构和语言切换链接一致。
• .github/workflows/claude.yml 解析成功。
• 使用 DeepSeek-V4-Pro 8k1k 有效结果完成公开结果 API 冒烟验证。
• 提交前 git diff --cached --check 通过。
• 独立审查确认根目录文档、运维指南、命令文档和 CollectiveX 方法说明均无遗留问题。

[github-actions]

Thanks for the contribution! Please reach out to respective companies' CODEOWNER to fill in the latest PR_REVIEW_CHECKLIST.md before pinging core maintainer on Slack for review. In order for the signoff PR check bot to trigger, you must follow the PR_REVIEW_CHECKLIST.md template correctly, including the phrase As a PR reviewer and CODEOWNER, I have reviewed this and have.

For PR verification, add the full-sweep-fail-fast label (strongly recommended) to this PR — the benchmark sweep only runs on labeled PRs. Use full-sweep-enabled only if you need matrix jobs to keep running past a failure.

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. See GitHub's docs on re-running failed jobs

---

感谢你的贡献！请联系相应公司的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，然后再在 Slack 上联系核心维护者进行审阅。为了触发 signoff PR 检查机器人，你必须正确遵循 PR_REVIEW_CHECKLIST.md 模板，包括保留英文语句 As a PR reviewer and CODEOWNER, I have reviewed this and have。

如需进行 PR 验证，请为此 PR 添加 full-sweep-fail-fast 标签（强烈推荐）— 基准测试 sweep 仅在带有标签的 PR 上运行。仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled。

PR 作者有责任确保合并后所有 GitHub Action 任务完全通过。 很多时候失败只是偶发抖动（flake），重新运行失败的任务即可解决。参见 GitHub 关于重新运行失败任务的文档

[github-actions]

Thanks for the contribution! Please reach out to respective companies' CODEOWNER to fill in the latest PR_REVIEW_CHECKLIST.md before pinging core maintainer on Slack for review. In order for the signoff PR check bot to trigger, you must follow the PR_REVIEW_CHECKLIST.md template correctly, including the phrase As a PR reviewer and CODEOWNER, I have reviewed this and have.

For PR verification, add the full-sweep-fail-fast label (strongly recommended) to this PR — the benchmark sweep only runs on labeled PRs. Use full-sweep-enabled only if you need matrix jobs to keep running past a failure.

PR authors are responsible for ensuring that after merging, all GitHub Action jobs fully pass. A lot of the time, failures are just flakes and simply re-running the failed jobs will fix it. See GitHub's docs on re-running failed jobs

---

感谢你的贡献！请联系相应公司的 CODEOWNER 填写最新的 PR_REVIEW_CHECKLIST.md，然后再在 Slack 上联系核心维护者进行审阅。为了触发 signoff PR 检查机器人，你必须正确遵循 PR_REVIEW_CHECKLIST.md 模板，包括保留英文语句 As a PR reviewer and CODEOWNER, I have reviewed this and have。

如需进行 PR 验证，请为此 PR 添加 full-sweep-fail-fast 标签（强烈推荐）— 基准测试 sweep 仅在带有标签的 PR 上运行。仅当需要矩阵任务在失败后继续运行时才使用 full-sweep-enabled。

PR 作者有责任确保合并后所有 GitHub Action 任务完全通过。 很多时候失败只是偶发抖动（flake），重新运行失败的任务即可解决。参见 GitHub 关于重新运行失败任务的文档