talk-stage2-research
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseTalk Stage 2: Research (REX mode only)
演讲第二阶段:调研(仅REX模式)
Builds the git proof for a REX talk. Cross-references git history, CHANGELOG, and the Stage 1 summary to produce a verified timeline and velocity analysis.
Automatically skipped in mode — only runs when the source material is a REX with git repository access.
--concept为REX演讲构建Git证据。交叉引用Git历史、CHANGELOG和第一阶段的摘要,生成可验证的时间线和速度分析。
在模式下自动跳过 —— 仅当源材料是带有Git仓库访问权限的REX时才运行。
--conceptWhen to Use This Skill
何时使用此技能
- After Stage 1 (Extract) when building a REX talk
- When you have access to the project's git repository
- To verify metrics mentioned in the source material against actual git data
- 构建REX演讲时,在第一阶段(提取)之后使用
- 当你有权访问项目的Git仓库时
- 用于对照实际Git数据验证源材料中提到的指标
What This Skill Does
此技能的功能
- Reads the summary — understands the period and themes from Stage 1
- Git archaeology — extracts velocity metrics (read-only commands only)
- Changelog analysis — scans releases, features, documented metrics
- Cross-references — aligns git, CHANGELOG, and summary
- Builds the timeline — verified dates, not estimated
- Writes 3 output files
- 读取摘要 —— 理解第一阶段中的时间段和主题
- Git考古 —— 提取速度指标(仅使用只读命令)
- 变更日志分析 —— 扫描版本发布、功能、已记录的指标
- 交叉引用 —— 对齐Git记录、CHANGELOG和摘要
- 构建时间线 —— 可验证的日期,而非估算值
- 生成3个输出文件
Input
输入
- (from Stage 1 — required)
talks/{YYYY}-{slug}-summary.md - — absolute path to the git repository
repo_path - Optional: CHANGELOG path if different from
{repo_path}/CHANGELOG.md
- (来自第一阶段——必填)
talks/{YYYY}-{slug}-summary.md - —— Git仓库的绝对路径
repo_path - 可选:如果CHANGELOG路径与不同,需指定
{repo_path}/CHANGELOG.md
Output
输出
Three files:
talks/{YYYY}-{slug}-git-archaeology.mdtalks/{YYYY}-{slug}-changelog-analysis.mdtalks/{YYYY}-{slug}-timeline.md
三个文件:
talks/{YYYY}-{slug}-git-archaeology.mdtalks/{YYYY}-{slug}-changelog-analysis.mdtalks/{YYYY}-{slug}-timeline.md
Git Commands (read-only only)
Git命令(仅只读)
bash
undefinedbash
undefinedCommits by month
按月份统计提交
git -C {repo_path} log --pretty=format:"%Y-%m" | sort | uniq -c
git -C {repo_path} log --pretty=format:"%Y-%m" | sort | uniq -c
Commits by contributor
按贡献者统计提交
git -C {repo_path} shortlog -sn --no-merges
git -C {repo_path} shortlog -sn --no-merges
First and last date
首次和末次提交日期
git -C {repo_path} log --pretty=format:"%ad" --date=short | tail -1
git -C {repo_path} log --pretty=format:"%ad" --date=short | head -1
git -C {repo_path} log --pretty=format:"%ad" --date=short | tail -1
git -C {repo_path} log --pretty=format:"%ad" --date=short | head -1
Merged PRs (if merge commit convention)
合并的PR(如果遵循合并提交约定)
git -C {repo_path} log --merges --oneline | wc -l
git -C {repo_path} log --merges --oneline | wc -l
Tags (releases)
标签(版本发布)
git -C {repo_path} tag --sort=version:refname
git -C {repo_path} tag --sort=version:refname
Velocity peak (busiest months)
速度峰值(最繁忙的月份)
git -C {repo_path} log --pretty=format:"%Y-%m" | sort | uniq -c | sort -rn | head -5
undefinedgit -C {repo_path} log --pretty=format:"%Y-%m" | sort | uniq -c | sort -rn | head -5
undefinedOutput Formats
输出格式
git-archaeology.md
git-archaeology.md
markdown
undefinedmarkdown
undefinedGit Archaeology — {slug}
Git考古 —— {slug}
Repo: {repo_path}
Period analyzed: {start date} → {end date}
Commands run: {list}
仓库: {repo_path}
分析时间段: {开始日期} → {结束日期}
执行的命令: {列表}
Global Metrics
全局指标
| Metric | Value | Source |
|---|---|---|
| Total commits | {n} | git log |
| Total merges/PRs | ~{n} | git log --merges |
| Total releases (tags) | {n} | git tag |
| Human contributors | {n} | git shortlog |
| Period covered | {n} months | first → last date |
| 指标 | 数值 | 来源 |
|---|---|---|
| 总提交数 | {n} | git log |
| 总合并/PR数 | ~{n} | git log --merges |
| 总发布数(标签) | {n} | git tag |
| 贡献者人数 | {n} | git shortlog |
| 覆盖时间段 | {n} 个月 | 首次→末次日期 |
Monthly Velocity
月度速度
| Month | Commits | Notes |
|---|---|---|
| {YYYY-MM} | {n} | {context if notable} |
| ... |
| 月份 | 提交数 | 备注 |
|---|---|---|
| {YYYY-MM} | {n} | {若值得关注则添加上下文} |
| ... |
Contributors
贡献者
| Rank | Name | Commits | % |
|---|---|---|---|
| 1 | {name} | {n} | {%} |
| ... |
Generated by talk-stage2-research — {date}
undefined| 排名 | 姓名 | 提交数 | 占比 |
|---|---|---|---|
| 1 | {name} | {n} | {%} |
| ... |
由talk-stage2-research生成 —— {日期}
undefinedchangelog-analysis.md
changelog-analysis.md
markdown
undefinedmarkdown
undefinedChangelog Analysis — {slug}
CHANGELOG分析 —— {slug}
Source: {CHANGELOG path}
Releases analyzed: {n} (v{first} → v{last})
来源: {CHANGELOG路径}
分析的版本发布: {n} 个(v{首个版本} → v{最后版本})
Features by release (summary)
各版本的功能(摘要)
| Release | Date | Key features | Metrics mentioned |
|---|---|---|---|
| {version} | {date} | {features} | {metrics} |
| ... |
| 版本 | 日期 | 核心功能 | 提及的指标 |
|---|---|---|---|
| {version} | {date} | {features} | {metrics} |
| ... |
Patterns identified
识别到的模式
Acceleration
加速阶段
{Periods of high velocity and what drove them}
{高速度的时间段及其驱动因素}
Inflection points
转折点
{Pivots, direction changes, major releases}
{转型、方向变更、重大版本发布}
Verifiable metrics in CHANGELOG
CHANGELOG中可验证的指标
{Exhaustive list of numbers mentioned in CHANGELOG with their release}
Generated by talk-stage2-research — {date}
undefined{CHANGELOG中提及的所有数值及其对应版本的完整列表}
由talk-stage2-research生成 —— {日期}
undefinedtimeline.md
timeline.md
markdown
undefinedmarkdown
undefinedFactual Timeline — {slug}
事实时间线 —— {slug}
Period: {start} → {end} ({n} months)
Cross-referenced sources: Summary × Git history × CHANGELOG
时间段: {开始} → {结束}({n} 个月)
交叉引用来源: 摘要 × Git历史 × CHANGELOG
Month-by-month timeline
月度时间线
| Month | Commits | Releases | Versions | Key features | Talk event |
|---|---|---|---|---|---|
| {YYYY-MM} | {n} | {n} | {versions} | {features} | {anecdote/event} |
| ... |
| 月份 | 提交数 | 发布数 | 版本 | 核心功能 | 演讲事件 |
|---|---|---|---|---|---|
| {YYYY-MM} | {n} | {n} | {versions} | {features} | {轶事/事件} |
| ... |
Cross-reference: Conflicts and inconsistencies
交叉引用:冲突与不一致
{If dates or metrics contradict between sources, note here}
Generated by talk-stage2-research — {date}
Sources: git log × {CHANGELOG path} × {summary path}
undefined{如果不同来源之间的日期或指标存在矛盾,在此处记录}
由talk-stage2-research生成 —— {日期}
来源: git log × {CHANGELOG路径} × {摘要路径}
undefinedKey Rules
核心规则
- Read-only only — no git commands that modify repo state
- Verify before asserting — a date not found in git = "unverified"
- Cross-reference — flag inconsistencies between sources, don't pick one arbitrarily
- Granularity — month by month minimum; week by week if the period is short (< 2 months)
- 仅使用只读命令 —— 不执行任何会修改仓库状态的Git命令
- 先验证再断言 —— 未在Git中找到的日期标记为“未验证”
- 交叉引用 —— 标记不同来源之间的不一致,不要随意选择其中一个
- 粒度 —— 至少按月份统计;如果时间段较短(<2个月),则按周统计
Anti-patterns
反模式
- Running git commands that modify the repository
- Estimating dates instead of verifying them in git
- Rounding metrics without flagging it
- Silently merging contradictory data from different sources
- Omitting quiet periods — plateaus tell a story too
- 执行会修改仓库的Git命令
- 估算日期而非在Git中验证
- 未标记就四舍五入指标
- 静默合并来自不同来源的矛盾数据
- 忽略平缓期——平台期也能说明问题
Validation Checklist
验证清单
- Only read-only git commands executed
- Timeline covers the full period from summary
- All metrics have an explicit source (git or CHANGELOG)
- Conflicts between sources flagged in dedicated section
- 3 files generated and saved
- 仅执行了只读Git命令
- 时间线覆盖了摘要中的完整时间段
- 所有指标都有明确的来源(Git或CHANGELOG)
- 来源之间的冲突已在专门章节中标记
- 已生成并保存3个文件
Tips
提示
- The timeline is what Stage 3 (Concepts) uses to enrich concept scores — a good timeline makes the concept catalogue stronger
- "Quiet periods" in git velocity often correspond to hardest engineering challenges — worth noting
- If the CHANGELOG has no version tags, fall back to date-based anchoring
- 时间线是第三阶段(概念)用于丰富概念评分的依据——优质的时间线能让概念目录更完善
- Git速度中的“平缓期”通常对应最具挑战性的工程难题——值得记录
- 如果CHANGELOG没有版本标签,退而求其次使用基于日期的锚定
Related
相关内容
- Stage 1: Extract — prerequisite
- Stage 3: Concepts — reads this timeline
- Orchestrator
- 第一阶段:提取 —— 前置条件
- 第三阶段:概念 —— 读取此时间线
- 编排器