pulse-survey-analysis

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Pulse 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

InputRequiredDefault
CSV pathYes
Team nameNo
Company
PeriodNoAsk once, else
YYYY-MM
Expected columns (utf-8-sig OK):
EmpID
,
Department
,
Manager
, then
Q1_Manager_Leadership
Q20_Engagement_Referral
. Manager aliases accepted by analysis logic:
Manager
/
People Leader
. Scale 1–5.
Question map and thresholds: references/survey-structure.md.
Section contract matching the PDF template: references/report-template.md.
输入项是否必填默认值
CSV路径
团队名称
Company
周期询问一次,否则为
YYYY-MM
预期列(支持utf-8-sig编码):
EmpID
Department
Manager
,随后是
Q1_Manager_Leadership
……
Q20_Engagement_Referral
。分析逻辑接受的经理别名:
Manager
/
People Leader
。评分范围为1–5
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

Outputs (beside CSV, unless
--out-dir
)

输出文件(默认与CSV同目录,除非指定
--out-dir

  1. [Team] Pulse Survey Report - [YYYY-MM].pdf
    — 8-section team report
  2. [Team] Pulse Survey Charts - [YYYY-MM].png
    — 7-panel composite
  3. individual_reports/{Manager} - Pulse Survey Personal Report.pdf
    (+ chart PNG)
  4. [Team] Pulse Survey Metrics - [YYYY-MM].json
    — Python numbers for
    html-executive-deck-generation
    (always written; override path with
    --json-out
    )
  1. [Team] Pulse Survey Report - [YYYY-MM].pdf
    — 8章节团队报告
  2. [Team] Pulse Survey Charts - [YYYY-MM].png
    — 7面板复合图表
  3. individual_reports/{Manager} - Pulse Survey Personal Report.pdf
    (附带图表PNG文件)
  4. [Team] Pulse Survey Metrics - [YYYY-MM].json
    — 供
    html-executive-deck-generation
    使用的Python数值格式数据(始终生成;可通过
    --json-out
    覆盖路径)

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-analysis
):
bash
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-analysis
):
bash
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

2. 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:
  • --out-dir DIR
    — write outputs elsewhere
  • --no-individual
    — team PDF + charts only
  • --no-pdf
    — skip PDFs; still write PNG + JSON (faster deck path)
  • --json-out PATH
    — metrics JSON for the executive deck (default: beside other artefacts)
Path safety: if the CSV lives under
Desktop - km’s MacBook Pro
, resolve the path via shell/
pathlib
glob (curly apostrophe U+2019). Do not hand-type a straight
'
in absolute paths.
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:
  • --out-dir DIR
    — 将输出文件写入指定目录
  • --no-individual
    — 仅生成团队PDF报告和图表
  • --no-pdf
    — 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)
  • --json-out PATH
    — 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)
路径注意事项: 如果CSV文件位于
Desktop - km’s MacBook Pro
目录下,请通过shell或
pathlib
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
'

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

  1. Direct Leader score = mean Q1–Q10 only → rank managers by this.
  2. Overall average = mean of all Q columns → context only; never sole judgment of a manager.
  3. Ratings ≤ 2 are extreme — always surface counts.
  4. Q11–Q13 and Q14–Q17 are systemic — do not blame one manager.
  5. If manager n ≤ 5, label conclusions “directional only”.
  6. Prefer the bundled runner for PDF/PNG fidelity; do not freehand a divergent layout unless the user asks for a different format.
  7. When this skill is used to feed
    html-executive-deck-generation
    , the deck may cite only the JSON this runner writes. Do not re-average Q columns in the LLM.
  1. 直属领导者得分 = 仅Q1–Q10的平均值 → 以此对经理进行排名。
  2. 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。
  3. 评分**≤2**为极端评分 — 必须明确列出此类评分的数量。
  4. Q11–Q13Q14–Q17为系统性问题 — 不得归咎于单个经理。
  5. 如果经理人数n ≤5,需标注结论为“仅作趋势参考”。
  6. 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。
  7. 当本技能用于为
    html-executive-deck-generation
    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。

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。