pulse-survey-analysis
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChinesePulse Survey Analysis
脉搏调查分析
Generate artefacts matching Company Pulse Survey Report - YYYY-MM.pdf from a standard 20-question CSV.
根据标准20题CSV文件生成符合《Company Pulse Survey Report - YYYY-MM.pdf》格式的成果文件。
Inputs
输入项
| Input | Required | Default |
|---|---|---|
| CSV path | Yes | — |
| Team name | No | |
| Period | No | Ask once, else |
Expected columns (utf-8-sig OK): , , , then … . Manager aliases accepted by analysis logic: / . Scale 1–5.
EmpIDDepartmentManagerQ1_Manager_LeadershipQ20_Engagement_ReferralManagerPeople LeaderQuestion map and thresholds: references/survey-structure.md.
Section contract matching the PDF template: references/report-template.md.
Section contract matching the PDF template: references/report-template.md.
| 输入项 | 是否必填 | 默认值 |
|---|---|---|
| CSV路径 | 是 | — |
| 团队名称 | 否 | |
| 周期 | 否 | 询问一次,否则为 |
预期列(支持utf-8-sig编码):、、,随后是……。分析逻辑接受的经理别名: / 。评分范围为1–5。
EmpIDDepartmentManagerQ1_Manager_LeadershipQ20_Engagement_ReferralManagerPeople Leader问题映射与阈值:references/survey-structure.md。
匹配PDF模板的章节约定:references/report-template.md。
匹配PDF模板的章节约定:references/report-template.md。
Outputs (beside CSV, unless --out-dir
)
--out-dir输出文件(默认与CSV同目录,除非指定--out-dir
)
--out-dir- — 8-section team report
[Team] Pulse Survey Report - [YYYY-MM].pdf - — 7-panel composite
[Team] Pulse Survey Charts - [YYYY-MM].png - (+ chart PNG)
individual_reports/{Manager} - Pulse Survey Personal Report.pdf - — Python numbers for
[Team] Pulse Survey Metrics - [YYYY-MM].json(always written; override path withhtml-executive-deck-generation)--json-out
- — 8章节团队报告
[Team] Pulse Survey Report - [YYYY-MM].pdf - — 7面板复合图表
[Team] Pulse Survey Charts - [YYYY-MM].png - (附带图表PNG文件)
individual_reports/{Manager} - Pulse Survey Personal Report.pdf - — 供
[Team] Pulse Survey Metrics - [YYYY-MM].json使用的Python数值格式数据(始终生成;可通过html-executive-deck-generation覆盖路径)--json-out
Workflow
工作流程
Copy this checklist:
Progress:
- [ ] Confirm team name + period
- [ ] Ensure venv deps installed
- [ ] Run pulse_report_runner.py
- [ ] Reply with output paths + 3 one-line findings复制以下检查清单:
进度:
- [ ] 确认团队名称 + 周期
- [ ] 确保venv依赖已安装
- [ ] 运行pulse_report_runner.py
- [ ] 返回输出路径 + 3条单行结论1. Setup (once per machine)
1. 环境设置(每台机器仅需一次)
From this skill folder (repo checkout or ):
~/.cursor/skills/pulse-survey-analysisbash
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt进入本技能所在文件夹(仓库检出目录或):
~/.cursor/skills/pulse-survey-analysisbash
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt2. Generate report (preferred — matches PDF template)
2. 生成报告(推荐方式——匹配PDF模板)
bash
.venv/bin/python scripts/pulse_report_runner.py \
"/absolute/path/to/engagement_survey_raw_data.csv" \
--team "Company" \
--period "2026-05" \
--json-out "/absolute/path/to/out/metrics.json"Flags:
- — write outputs elsewhere
--out-dir DIR - — team PDF + charts only
--no-individual - — skip PDFs; still write PNG + JSON (faster deck path)
--no-pdf - — metrics JSON for the executive deck (default: beside other artefacts)
--json-out PATH
Path safety: if the CSV lives under , resolve the path via shell/ glob (curly apostrophe U+2019). Do not hand-type a straight in absolute paths.
Desktop - km’s MacBook Propathlib'bash
.venv/bin/python scripts/pulse_report_runner.py \
"/absolute/path/to/engagement_survey_raw_data.csv" \
--team "Company" \
--period "2026-05" \
--json-out "/absolute/path/to/out/metrics.json"参数说明:
- — 将输出文件写入指定目录
--out-dir DIR - — 仅生成团队PDF报告和图表
--no-individual - — 跳过PDF生成;仍会生成PNG和JSON文件(生成演示文稿的更快路径)
--no-pdf - — 指定供高管演示文稿使用的指标JSON文件路径(默认:与其他输出文件同目录)
--json-out PATH
路径注意事项: 如果CSV文件位于目录下,请通过shell或 glob解析路径(注意此处为弯引号U+2019)。请勿在绝对路径中手动输入直引号。
Desktop - km’s MacBook Propathlib'3. Reply to user
3. 回复用户
List generated file paths. Summarise in 3 bullets: n / response coverage, top Direct Leader, strongest systemic flag (usually Q14–Q17 or pressure composite).
列出生成的文件路径。用3个项目符号总结:回复覆盖率、排名第一的直属领导者、最突出的系统性问题(通常为Q14–Q17或压力综合指标)。
Hard rules
硬性规则
- Direct Leader score = mean Q1–Q10 only → rank managers by this.
- Overall average = mean of all Q columns → context only; never sole judgment of a manager.
- Ratings ≤ 2 are extreme — always surface counts.
- Q11–Q13 and Q14–Q17 are systemic — do not blame one manager.
- If manager n ≤ 5, label conclusions “directional only”.
- Prefer the bundled runner for PDF/PNG fidelity; do not freehand a divergent layout unless the user asks for a different format.
- When this skill is used to feed , the deck may cite only the JSON this runner writes. Do not re-average Q columns in the LLM.
html-executive-deck-generation
- 直属领导者得分 = 仅Q1–Q10的平均值 → 以此对经理进行排名。
- 总体平均分 = 所有问题列的平均值 → 仅作参考;绝不能单独以此评判经理。
- 评分**≤2**为极端评分 — 必须明确列出此类评分的数量。
- Q11–Q13和Q14–Q17为系统性问题 — 不得归咎于单个经理。
- 如果经理人数n ≤5,需标注结论为“仅作趋势参考”。
- 优先使用内置运行器以保证PDF/PNG的格式准确性;除非用户要求其他格式,否则不得自行设计不同布局。
- 当本技能用于为提供数据时,演示文稿只能引用本运行器生成的JSON数据。不得在LLM中重新计算问题列的平均值。
html-executive-deck-generation
Manual analysis fallback
手动分析备选方案
If Python/env cannot run: fix the venv and rerun. For a deck, do not substitute LLM math. Standalone report-only sessions may write Markdown covering sections I–VIII in references/report-template.md and must note that PDF/PNG/JSON were not produced.
如果Python环境无法运行:修复venv后重新运行。对于演示文稿,不得用LLM计算替代原有逻辑。仅生成报告的独立会话可编写覆盖references/report-template.md中I–VIII章节的Markdown内容,但必须注明未生成PDF/PNG/JSON文件。