draft-project-charter
Acerca de
Esta habilidad de Claude redacta una carta de proyecto integral, definiendo el alcance, las partes interesadas, los criterios de éxito y un registro inicial de riesgos. Genera elementos clave como una declaración del problema, una matriz RACI y una planificación de hitos para metodologías tanto ágiles como clásicas. Úsala para iniciar formalmente un proyecto, alinear a las partes interesadas o hacer la transición desde la fase de descubrimiento al trabajo activo.
Instalación rápida
Claude Code
Recomendadonpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/draft-project-charterCopia y pega este comando en Claude Code para instalar esta habilidad
Documentación
Draft a Project Charter
Structured charter → project bounds + stakeholder agreement + success criteria before detailed planning. Doc: scope + RACI + milestones + initial risk register. Agile/classic/hybrid.
Use When
- New project kickoff
- Formalize scope after informal start
- Align stakeholders before detailed planning
- Reference doc for scope decisions during execution
- Transition from discovery/ideation → active work
In
- Required: Project name + brief desc
- Required: Primary stakeholder/sponsor
- Optional: Existing docs (proposals, briefs, emails)
- Optional: Known constraints (budget, deadline, team size)
- Optional: Methodology pref (agile, classic, hybrid)
Do
Step 1: Gather Context + Template
Read existing docs (proposals, emails, briefs) → understand background. ID core problem/opportunity. Create charter file w/ structured template → populate subsequent steps.
File: PROJECT-CHARTER-[PROJECT-NAME].md:
# Project Charter: [Project Name]
## Document ID: PC-[PROJECT]-[YYYY]-[NNN]
### 1. Problem Statement
[2-3 sentences describing the problem or opportunity this project addresses]
### 2. Project Purpose
[What the project will achieve and why it matters]
### 3. Scope
#### In Scope
- [Deliverable 1]
- [Deliverable 2]
#### Out of Scope
- [Exclusion 1]
- [Exclusion 2]
### 4. Deliverables
| # | Deliverable | Acceptance Criteria | Target Date |
|---|------------|---------------------|-------------|
| 1 | | | |
### 5. Stakeholders & RACI
| Stakeholder | Role | D1 | D2 | D3 |
|-------------|------|----|----|-----|
| | | | | |
*R=Responsible, A=Accountable, C=Consulted, I=Informed*
### 6. Success Criteria
| # | Criterion | Measure | Target |
|---|-----------|---------|--------|
| 1 | | | |
### 7. Milestones
| Milestone | Target Date | Dependencies |
|-----------|-------------|--------------|
| | | |
### 8. Risk Register
| ID | Risk | Likelihood | Impact | Severity | Mitigation | Owner |
|----|------|------------|--------|----------|------------|-------|
| R1 | | | | | | |
*Likelihood/Impact: Low, Medium, High*
*Severity = Likelihood × Impact*
### 9. Assumptions and Constraints
#### Assumptions
- [Key assumption 1]
#### Constraints
- [Key constraint 1]
### 10. Approval
| Role | Name | Date |
|------|------|------|
| Sponsor | | |
| Project Lead | | |
Fill doc ID → PC-[PROJECT]-[YYYY]-[NNN] (e.g., PC-WEBSITE-2026-001). Problem statement (2-3 sentences): current situation + gap + impact. Purpose (1 para): what will be achieved.
→ Charter file: doc ID + problem + purpose filled. Problem specific + measurable gap.
If err: context unclear → QUESTIONS section at top for sponsor. Existing docs conflict → OPEN ISSUES + flag for stakeholder resolution.
Step 2: Scope Boundaries
Explicit in-scope + out-of-scope. Write 3-5 in-scope deliverables + specific acceptance criteria each. Write 3-5 out-of-scope → prevent creep. Populate Deliverables table: deliverable + criteria + target date.
→ Scope balanced. Deliverables 3-5 w/ specific testable criteria. Dates realistic + sequenced.
If err: vague deliverables → break into sub-deliverables w/ concrete outputs. Criteria missing → ask "How would we demonstrate this is complete?". No dates → TBD, flag for milestone session.
Step 3: Stakeholders + RACI
List all affected/contributing/decision-authority individuals + org role. RACI matrix per stakeholder × deliverable:
- R (Responsible): does work
- A (Accountable): final decision authority (one A per deliverable)
- C (Consulted): input before decisions
- I (Informed): updated on progress
Each deliverable → exactly one A + ≥ one R.
→ Stakeholders 5-10 + roles. One A per deliverable column. No missing R / multiple As. Sponsor = A for final approval.
If err: list incomplete → cross-ref org chart + discovery meeting attendees. Multiple As → escalate to sponsor for clarification. No R → flag unassigned + resource allocation.
Step 4: Success Criteria + Milestones
3-5 measurable criteria SMART (Specific + Measurable + Achievable + Relevant + Time-bound). Each → quantifiable measure + target. 4-6 key milestones = major stages/completions + target dates + deps on prior milestones.
→ Criteria 3-5 w/ specific measures (e.g., "Uptime" = "% availability" target "99.5%"). Milestones logical + realistic. Deps clear.
If err: criteria vague ("improve quality") → rewrite as measurable outcomes + baseline + target. Dates unrealistic → work backward from final deadline w/ durations + buffers. Circular deps → restructure sequence or split conflicting.
Step 5: Initial Risk Register
5-10 risks. Per risk: likelihood (L/M/H) + impact (L/M/H) → severity. Specific mitigation + assigned owner. ≥1 per category: scope, schedule, resource, technical, external.
→ Register 5-10 across scope + schedule + resource + technical + external. Each w/ L + I + severity. Mitigations actionable + specific. Each has owner.
If err: incomplete → review scope + deps + stakeholders + assumptions for failure points. Generic mitigations ("monitor closely") → specify: what monitored, how often, what triggers action. No owner → assign project lead temp + escalate to sponsor.
Check
- Charter file created w/ doc ID
- Problem specific + measurable
- Scope has in + out-of-scope
- RACI covers all deliverables
- Criteria SMART
- ≥5 risks w/ mitigations
- Milestones w/ target dates
- Approval section included
Traps
- Scope w/o bounds: In-scope w/o out-of-scope → creep. Always define what NOT doing.
- Vague criteria: "Improve perf" unmeasurable. Tie each to number + baseline + target.
- Missing stakeholders: Overlooked ones surface late + derail. Cross-ref org charts + prior comms.
- Risk register as checkbox: Risks w/o actionable mitigations = false confidence. Each needs specific response.
- Over-detailed charter: Charter = compass, not map. 2-4 pages. Detailed planning later.
→
create-work-breakdown-structure— decompose deliverables → work packagesmanage-backlog— charter scope → prioritized backlogplan-sprint— first sprint from deliverablesgenerate-status-report— report vs milestonesconduct-retrospective— review assumptions after execution
Repositorio GitHub
Frequently asked questions
What is the draft-project-charter skill?
draft-project-charter is a Claude Skill by pjt222. Skills package instructions and resources that Claude loads on demand, so Claude can perform draft-project-charter-related tasks without extra prompting.
How do I install draft-project-charter?
Use the install commands on this page: add draft-project-charter to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does draft-project-charter belong to?
draft-project-charter is in the Design category, tagged ai and data.
Is draft-project-charter free to use?
Yes. draft-project-charter is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
Habilidades relacionadas
Utilice la habilidad executing-plans cuando tenga un plan de implementación completo para ejecutar en lotes controlados con puntos de revisión. Esta habilidad carga y revisa críticamente el plan, luego ejecuta tareas en pequeños lotes (por defecto 3 tareas) mientras reporta el progreso entre cada lote para la revisión del arquitecto. Esto asegura una implementación sistemática con puntos de control de calidad integrados.
Esta habilidad despacha un subagente revisor de código para analizar los cambios en el código frente a los requisitos antes de proceder. Debe usarse después de completar tareas, implementar funciones principales o antes de fusionar con la rama principal. La revisión ayuda a detectar problemas de forma temprana al comparar la implementación actual con el plan original.
Esta habilidad proporciona una guía integral para que los desarrolladores conecten servidores MCP a Claude Code mediante transportes HTTP, stdio o SSE. Cubre la instalación, configuración, autenticación y seguridad para integrar servicios externos como GitHub, Notion y APIs personalizadas. Úsala al configurar integraciones MCP, al configurar herramientas externas o al trabajar con el Protocolo de Contexto del Modelo de Claude.
Esta habilidad ayuda a los desarrolladores a elegir entre las interfaces web y CLI de Claude Code mediante el análisis de tareas, y luego permite la teletransportación fluida de sesiones entre estos entornos. Optimiza el flujo de trabajo gestionando el estado y el contexto de la sesión al cambiar entre web, CLI o móvil. Úsala para proyectos complejos que requieren diferentes herramientas en varias etapas.
