Project Selection & Go/No-Go Gates

TL;DR: Evaluates project proposals against feasibility criteria to make informed go/no-go decisions. Assesses strategic fit, financial viability, technical feasibility, resource availability, and risk tolerance to determine whether a project should proceed, be modified, or be rejected.

Principio Rector

Decir "no" a un proyecto que no debería existir es tan valioso como decir "sí" al correcto. El costo de un proyecto fallido no es solo su presupuesto — es el costo de oportunidad de los recursos que pudieron haber creado valor en otro lugar. Selection gates protegen a la organización de comprometer recursos en iniciativas inviables.

Assumptions & Limits

• Assumes a project proposal or business case exists with enough detail for evaluation [PLAN]
• Assumes organizational strategy and risk appetite are documented for alignment scoring [SUPUESTO]
• Breaks when selection criteria are undefined — establish criteria before attempting selection
• Does not replace detailed feasibility studies; provides screening-level assessment
• Assumes scoring weights are agreed upon by governance stakeholders [STAKEHOLDER]
• Limited to individual project evaluation; for portfolio-level prioritization use strategic-alignment

Usage

# Full project selection assessment
/pm:project-selection $ARGUMENTS="--proposal project-proposal.md --criteria weighted"

# Quick go/no-go screening
/pm:project-selection --type screening --proposal brief.md

# Comparative selection across multiple proposals
/pm:project-selection --type comparative --proposals "prop-A.md,prop-B.md,prop-C.md"

Parameters:

Service Type Routing

{TIPO_PROYECTO}: All types pass through selection gates. Criteria weights vary: strategic projects weight alignment higher; innovation projects weight learning potential; compliance projects require mandatory assessment.

Before Selecting

1. Read the project proposal and business case to understand the investment request [PLAN]
2. Read organizational strategy or OKRs to validate strategic alignment claims [PLAN]
3. Glob **/resource_plan* to verify resource availability assertions [SCHEDULE]
4. Grep for similar completed projects in **/closure* or **/lessons* to inform feasibility judgment [INFERENCIA]

Entrada (Input Requirements)

• Project proposal or business case
• Portfolio prioritization results
• Resource availability
• Strategic plan and investment themes
• Risk appetite framework

Proceso (Protocol)

1. Screening criteria — Apply minimum threshold criteria (strategic fit, sponsor, budget)
2. Strategic alignment — Assess fit with organizational strategy and OKRs
3. Financial viability — Review business case (NPV, ROI, payback)
4. Technical feasibility — Assess technical capability and readiness
5. Resource availability — Verify resource capacity for the project
6. Risk assessment — Evaluate risk within organizational risk appetite
7. Dependency check — Assess cross-project dependencies and timing
8. Scoring — Apply weighted scoring model per criterion
9. Decision recommendation — Recommend GO, CONDITIONAL GO, NO-GO, or DEFER
10. Conditions documentation — If conditional, specify what must be resolved

Edge Cases

1. Strategic mandate overrides feasibility — Document the override with [STAKEHOLDER] tag. Proceed but flag all feasibility gaps as risks in the risk register. The selection record must show the mandate, not hide it [STAKEHOLDER].
2. All candidates score similarly — Apply sensitivity analysis by varying weights ±10%. If ranking remains stable, decision requires qualitative tiebreaker from governance. If unstable, the scoring model needs refinement [METRIC].
3. Proposal lacks data for scoring — Score what is available; mark data-gap dimensions as [SUPUESTO] with confidence=Low. Require data completion before final GO decision [SUPUESTO].
4. Project already started without selection gate — Conduct retroactive assessment. If NO-GO, escalate to sponsor with sunk-cost analysis and recommendation to continue, pivot, or terminate [STAKEHOLDER].

Example: Good vs Bad

Good example — Weighted selection assessment:

Bad example — Rubber-stamp approval: "Approved" with no scoring criteria, no strategic alignment check, no resource verification, and no risk assessment. Selection without criteria is not selection — it is hope. Every project that proceeds without evaluation competes for resources against projects that were properly vetted.

Salida (Deliverables)

• Project selection assessment report
• Scoring matrix with weighted results
• GO / CONDITIONAL GO / NO-GO / DEFER recommendation
• Conditions and prerequisites (if applicable)
• Portfolio impact analysis

Validation Gate

• ≥5 selection dimensions evaluated with weighted scores [METRIC]
• Every score justified with specific evidence, not subjective opinion [PLAN]
• Strategic alignment validated against ≥1 documented organizational objective [PLAN]
• Resource availability confirmed for project timeline [SCHEDULE]
• Risk assessment completed within organizational risk appetite framework [PLAN]
• Decision recommendation clearly stated as GO/CONDITIONAL/NO-GO/DEFER [PLAN]
• Conditions (if CONDITIONAL) are specific, measurable, and time-bound [PLAN]
• Evidence ratio: ≥70% [PLAN]/[METRIC], <30% [SUPUESTO]
• Scoring weights agreed by governance stakeholders before application [STAKEHOLDER]
• Portfolio impact of approval documented (resource, budget, timeline) [SCHEDULE]

Escalation Triggers

• Strategic mandate overrides feasibility concerns
• Multiple projects competing for same resources
• Conditional go with unresolvable conditions
• Selection criteria inadequate for project type

Additional Resources

Output Configuration

• Language: Spanish (Latin American, business register)
• Evidence: [PLAN], [SCHEDULE], [METRIC], [INFERENCIA], [SUPUESTO], [STAKEHOLDER]
• Branding: #2563EB royal blue, #F59E0B amber (NEVER green), #0F172A dark

Sub-Agents

Comparative Ranker

Comparative Ranker Agent

Core Responsibility

Ranks project proposals using consistent scoring, producing transparent comparative analysis. This agent operates autonomously within the project selection domain, applying systematic analysis and producing structured outputs that integrate with the broader project management framework.

Process

1. Gather Inputs. Collect all relevant data, documents, and stakeholder inputs needed for analysis. Validate data quality and completeness before proceeding.
2. Analyze Context. Assess the project context, methodology, phase, and constraints that influence the analysis approach and output requirements.
3. Apply Framework. Apply the appropriate analytical framework, methodology, or model specific to this domain area with calibrated rigor.
4. Generate Findings. Produce detailed findings with evidence tags, quantified impacts where possible, and clear categorization by severity or priority.
5. Validate Results. Cross-check findings against related project artifacts for consistency and flag any contradictions or gaps discovered.
6. Formulate Recommendations. Transform findings into actionable recommendations with owners, timelines, and success criteria.
7. Deliver Output. Produce the final structured output in the standard format with executive summary, detailed analysis, and action items.

Output Format

• Analysis Report — Structured findings with evidence tags, severity ratings, and cross-references.
• Recommendation Register — Actionable items with owners, deadlines, and success criteria.
• Executive Summary — 3-5 bullet point summary for stakeholder communication.

Go Nogo Recommender

Go Nogo Recommender Agent

Core Responsibility

Produces go/no-go recommendations with supporting evidence and conditions for approval. This agent operates autonomously within the project selection domain, applying systematic analysis and producing structured outputs that integrate with the broader project management framework.

Process

1. Gather Inputs. Collect all relevant data, documents, and stakeholder inputs needed for analysis. Validate data quality and completeness before proceeding.
2. Analyze Context. Assess the project context, methodology, phase, and constraints that influence the analysis approach and output requirements.
3. Apply Framework. Apply the appropriate analytical framework, methodology, or model specific to this domain area with calibrated rigor.
4. Generate Findings. Produce detailed findings with evidence tags, quantified impacts where possible, and clear categorization by severity or priority.
5. Validate Results. Cross-check findings against related project artifacts for consistency and flag any contradictions or gaps discovered.
6. Formulate Recommendations. Transform findings into actionable recommendations with owners, timelines, and success criteria.
7. Deliver Output. Produce the final structured output in the standard format with executive summary, detailed analysis, and action items.

Output Format

• Analysis Report — Structured findings with evidence tags, severity ratings, and cross-references.
• Recommendation Register — Actionable items with owners, deadlines, and success criteria.
• Executive Summary — 3-5 bullet point summary for stakeholder communication.

Scoring Model Builder

Scoring Model Builder Agent

Core Responsibility

Builds weighted scoring models with stakeholder-agreed weights and calibrated scales. This agent operates autonomously within the project selection domain, applying systematic analysis and producing structured outputs that integrate with the broader project management framework.

Process

1. Gather Inputs. Collect all relevant data, documents, and stakeholder inputs needed for analysis. Validate data quality and completeness before proceeding.
2. Analyze Context. Assess the project context, methodology, phase, and constraints that influence the analysis approach and output requirements.
3. Apply Framework. Apply the appropriate analytical framework, methodology, or model specific to this domain area with calibrated rigor.
4. Generate Findings. Produce detailed findings with evidence tags, quantified impacts where possible, and clear categorization by severity or priority.
5. Validate Results. Cross-check findings against related project artifacts for consistency and flag any contradictions or gaps discovered.
6. Formulate Recommendations. Transform findings into actionable recommendations with owners, timelines, and success criteria.
7. Deliver Output. Produce the final structured output in the standard format with executive summary, detailed analysis, and action items.

Output Format

• Analysis Report — Structured findings with evidence tags, severity ratings, and cross-references.
• Recommendation Register — Actionable items with owners, deadlines, and success criteria.
• Executive Summary — 3-5 bullet point summary for stakeholder communication.

Selection Criteria Designer

Selection Criteria Designer Agent

Core Responsibility

Designs project selection criteria: strategic fit, financial value, risk, feasibility, and resource availability. This agent operates autonomously within the project selection domain, applying systematic analysis and producing structured outputs that integrate with the broader project management framework.

Process

1. Gather Inputs. Collect all relevant data, documents, and stakeholder inputs needed for analysis. Validate data quality and completeness before proceeding.
2. Analyze Context. Assess the project context, methodology, phase, and constraints that influence the analysis approach and output requirements.
3. Apply Framework. Apply the appropriate analytical framework, methodology, or model specific to this domain area with calibrated rigor.
4. Generate Findings. Produce detailed findings with evidence tags, quantified impacts where possible, and clear categorization by severity or priority.
5. Validate Results. Cross-check findings against related project artifacts for consistency and flag any contradictions or gaps discovered.
6. Formulate Recommendations. Transform findings into actionable recommendations with owners, timelines, and success criteria.
7. Deliver Output. Produce the final structured output in the standard format with executive summary, detailed analysis, and action items.

Output Format

• Analysis Report — Structured findings with evidence tags, severity ratings, and cross-references.
• Recommendation Register — Actionable items with owners, deadlines, and success criteria.
• Executive Summary — 3-5 bullet point summary for stakeholder communication.