skills.rest
DKSang
DKSangCOMMUNITY
Explore all skills by this author →
GitHub

des-project-evaluation

Evaluate data engineering project readiness and produce a Phase 22 closure report.

2|Updated May 20, 2026
Search Tags:#data engineering#risk assessment#evidence-based#release readiness#project evaluation#workflow closure#CI/CD validation
One-click install
npx skills add https://github.com/DKSang/DES-SKILL --skill des-project-evaluation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: des-project-evaluation
Source: https://github.com/DKSang/DES-SKILL/tree/main/skills/des-project-evaluation
Command: npx skills add https://github.com/DKSang/DES-SKILL --skill des-project-evaluation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents agents from ending a data engineering workflow without clear, evidence-based conclusions about business value, technical readiness, release readiness, adoption signals, risks, and next steps.

Core Features & Use Cases

  • Evidence-driven project closure: Evaluates goals, KPIs, delivered data products, and readiness across design, quality, security, CI/CD, operations, and adoption using upstream artifacts and documented results.
  • Readiness scorecard and risk transparency: Produces explicit ratings and an evidence availability map, marking missing evidence as Unknown rather than success.
  • Phase 22 support validation: Runs the Phase 22 support work (handoff review, completeness checks, checklist/done-gate, final closeout) to ensure the evaluation is honest, auditable, and actionable.

Quick Start

Use des-project-evaluation when Phase 21 handoff and evaluation evidence exist, to generate or update _des-output/planning-artifacts/22-project-evaluation-report.md and complete Phase 22 closeout based on evidence.

Frequently Asked Questions about des-project-evaluation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate data engineering project readiness before release?▼

Evaluating data engineering project readiness requires assessing technical design, data quality, CI/CD validation, security, and adoption signals against business KPIs to produce a defensible release readiness scorecard.

What is evidence-based project closure for data pipelines?▼

Evidence-based project closure means concluding a data engineering workflow by validating delivered data products and release readiness strictly through documented artifacts and done-gate checks rather than assumptions.

How do I generate a risk assessment scorecard for a data engineering workflow?▼

Generating a risk assessment scorecard involves mapping available evidence from upstream planning artifacts, explicitly marking any missing CI/CD validation or operational evidence as Unknown rather than success.

What do I need to complete a final project evaluation and closeout?▼

Completing a final project evaluation requires upstream planning artifacts, a Phase 21 handoff, and optional evidence packs to produce an evaluation report, support plan, and final closeout files.

Can I assess business value and adoption evidence after a data product handoff?▼

Yes, you can assess business value and adoption evidence after handoff by reviewing delivered data products against original goals and KPIs to capture lessons learned and route next-iteration decisions.

When should I not use an evidence-driven project evaluation approach?▼

You should not use evidence-driven project evaluation when upstream planning artifacts are missing, as the readiness scorecard depends on documented results to mark missing evidence as Unknown rather than guessing.

Related Skills

Explore More Product & Management Skills→
matt-rileymatt-riley
1

workflow-contracts

Generate v1 handoff artifacts with required frontmatter for planning, review, or execution.

Community
Advanced
SJTU-IPADSSJTU-IPADS
7

cto-advisor

Consolidate architecture decisions, tech debt, and team scaling plans for engineering leadership.

Official
Advanced
danmestasdanmestas
4

farley

Evaluate software CD readiness and generate a 14-marker improvement plan.

Community
Advanced
DTMC-marketplaceDTMC-marketplace

ml-project-lifecycle

Plan and execute Machine Learning projects using CRISP-DM, TDSP, and MLOps templates.

Official
Intermediate