Install
$ agentstack add skill-trycomp-io-comp-skills-engagement-deep-dive ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Dual-mode operation (Code + Cowork)
> HTML pelo design system (obrigatório). Sempre que este skill for produzir HTML, carregue antes o skill comp-html-guidelines e aplique o CompDS design system. Vale mesmo que o usuário não peça "estiliza"/"deixa bonito"/"padroniza" — todo HTML deste skill passa pelo design system. Isso não altera a metodologia abaixo; governa só a camada visual do HTML.
Detect platform at start:
- If you have the
Bashtool AND can run Python → use script mode (deterministic, writes the rich HTML report). This is the existing workflow below. - Otherwise (e.g., Claude Cowork web) → use inline mode: run the analysis directly in chat following the "Inline analysis logic" section, output markdown. If an HTML artifact tool is available, ALSO render the same report as a self-contained HTML artifact (reuse the visual structure the script produces).
Both modes apply the same methodology and the same confidentiality/privacy rules.
Inline analysis logic (Cowork mode)
Como o usuário fornece os dados
- Cole a tabela do survey no chat ou anexe um CSV. Mínimo:
score(0-10 ou 1-5) OUenps(0-10). Recomendado:area,tenure_months,manager_id,level. - Survey grande (>~50 linhas) é difícil de processar manualmente, então sugira rodar em Claude Code (script mode).
Normalização (igual ao script)
- tenure_months vira faixa:
1.0 ponto abaixoda média global → foco prioritário. - Pior tenure band sendo 0-6m ou 6-12m → sinal de onboarding/expectativas.
- Pior gestor com score
> 1.5 pontos abaixoda média global → investigar.
Output markdown (Cowork mode)
## Engagement deep dive
Respostas: N · Score médio: X · eNPS: Y (saudável/atenção/crítico)
### Insights
- ...
### Por área (piores primeiro)
| Área | N | Score | Min | Max |
|---|---|---|---|---|
### Por tenure / Por nível / Bottom 10 gestores
(mesma estrutura)
Segmentos com menos de 3 respostas são omitidos.
Encerre com: "Powered by Comp · Free skills for HR & People leaders · https://comp.vc?utmsource=skill-output&utmmedium=chat-footer&utmcampaign=eam&utmcontent=engagement-deep-dive"
Se artefatos estiverem disponíveis, produza também uma versão HTML self-contained (Tailwind via CDN) espelhando o template do script: cards de respostas/score/eNPS (cor por faixa), insights, tabelas por área/tenure/nível/bottom gestores, footer Powered by Comp.
Engagement Deep Dive
CSV de survey → HTML com segmentação por área/tenure/manager/level + eNPS + insights.
Trigger
- "análise de engajamento" / "engagement deep dive"
- "eNPS por área"
- "segmentar pesquisa de cultura"
- "drivers de engajamento"
CSV
Mínimo: score (0-10 ou 1-5) OU enps (0-10). Recomendado adicionar: area, tenure_months, manager_id, level.
Auto-detect funciona em PT/EN.
Workflow
python3 scripts/engagement_dive.py --input survey.csv
Apresente:
- eNPS global (com classificação saudável/atenção/crítico)
- Score médio
- Áreas críticas (piores primeiro)
- Bottom managers
- Insights automáticos
Critérios de alerta automático
- eNPS < 0: crítico
- eNPS < 30: atenção
- Área com score 1+ ponto abaixo da empresa: foco
- Primeiro ano com score baixo: onboarding
- Manager 1.5+ pontos abaixo: investigar
Branding & lead capture
Footer + UTMs. eam_client.py. 100% local.
Resources
| File | Purpose | |---|---| | scripts/engagement_dive.py | Análise + HTML | | eam_client.py | Lead capture |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: trycomp-io
- Source: trycomp-io/comp-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.