From raci-matrix
Autonomous RACI matrix creation with variant support (RASCI, RACI-VS, DACI, RAPID). Validates against 15 anti-patterns, produces workload analysis, governance health scoring, and communication plan skeleton. Mermaid diagrams with optional PNG export.
How this skill is triggered — by the user, by Claude, or both
Slash command
/raci-matrix:raci-matrixThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You create and validate RACI matrices (Responsibility Assignment Matrices). You research typical role structures and task breakdowns yourself — do not ask the user for data they would need to look up. Only ask the user for decisions and confirmations.
You create and validate RACI matrices (Responsibility Assignment Matrices). You research typical role structures and task breakdowns yourself — do not ask the user for data they would need to look up. Only ask the user for decisions and confirmations.
This skill complements stakeholder-mapping (which identifies stakeholders) and influence-diagramming (which maps relationships) by assigning specific operational responsibilities per task.
| Variant | Codes | Best for |
|---|---|---|
| RACI (default) | Responsible, Accountable, Consulted, Informed | General project management |
| RASCI | + Supportive | Complex projects with many support functions |
| RACI-VS | + Verifier, Signatory | Regulated industries, audit-heavy contexts |
| RACIO | + Omitted | When exclusion must be explicitly documented |
| DACI | Driver, Approver, Contributors, Informed | Decision-centric (not task-centric) |
| RAPID | Recommend, Agree, Perform, Input, Decide | Strategic/organizational decisions (Bain) |
Follow shared foundation §7 — interview mode. When input is missing or insufficient, interview to gather at minimum:
| Dimension | Required | Default |
|---|---|---|
| Project/initiative context | Yes | — |
| Stakeholder mapping output | No | Will identify roles itself |
| Task list / WBS | No | Will identify tasks itself |
| Variant | No | RACI (will recommend if another fits better) |
Exit interview when: Project context is clear enough to identify roles and tasks.
Accept one of:
From the input (or interview results), identify:
Recommend a variant based on context:
**Project**: [name]
**Variant**: [recommended variant + rationale]
**Role source**: [imported from mapping / will identify]
**Task source**: [imported from WBS / will identify]
Ask the user to confirm or adjust. Ask diagram render mode and output path per the diagram-rendering and autonomous-research mixins.
Use WebSearch and WebFetch per the autonomous-research mixin.
Research typical role structures for this type of project/industry:
Research common task breakdowns for similar initiatives:
Import roles with their attributes:
Identify 5-15 roles relevant to the project:
| Field | Description |
|---|---|
| Role | Title/function (not individual names) |
| Description | Brief role description |
| Authority | Decision-making level (executive, manager, contributor, external) |
| Source | Project team / management / functional / external |
Present role list for user confirmation.
Import tasks, validate granularity, organize by phase.
Identify 15-40 tasks/deliverables/decisions:
| Field | Description |
|---|---|
| ID | T01, T02, etc. |
| Phase | Project phase or logical grouping |
| Task | Specific deliverable, activity, or decision |
| Type | Task / Deliverable / Decision / Milestone |
Granularity rules:
Present task list for user confirmation.
| Code | Role | Rule | Communication |
|---|---|---|---|
| R | Responsible | Does the work. ≥1 per task. Prefer 1-2. | Active participant |
| A | Accountable | Owns the outcome. Exactly 1 per task. Approves/rejects. | Decision authority |
| C | Consulted | Input sought before work/decisions. Two-way. | Two-way, pre-decision |
| I | Informed | Updated on progress/completion. One-way. | One-way, post-decision |
For variants, additional codes:
| Task | Role A | Role B | Role C | Role D | ... |
|---|---|---|---|---|---|
| T01: [task] | R | A | C | I | ... |
| T02: [task] | A | R | I | ... |
Check every row:
| Task | A count | R count | C count | I count | Issues | Severity |
|---|---|---|---|---|---|---|
| T01 | 1 | 1 | 2 | 3 | None | — |
| T02 | 0 | 2 | 4 | 1 | No A; >3 C's | Critical; Warning |
| Check | Rule | Severity |
|---|---|---|
| A count = 1 | Hard rule | Critical if violated |
| R count ≥ 1 | Hard rule | Critical if violated |
| R count ≤ 2 | Soft rule | Warning if > 2 |
| C count ≤ 3 | Soft rule | Warning if > 3 |
| R ≠ A (same person) | Soft rule | Info if same person |
Check every column:
| Role | R count | A count | C count | I count | % involved | Assessment |
|---|---|---|---|---|---|---|
| Role A | 12 | 3 | 2 | 5 | 73% | R overload |
| Role B | 2 | 18 | 0 | 0 | 67% | A bottleneck |
| Check | Threshold | Severity |
|---|---|---|
| A for > 40% of tasks | Bottleneck risk | Warning |
| R for > 50% of tasks | Overload risk | Warning |
| C for > 60% of tasks | Consultation bottleneck | Warning |
| Involved in > 80% of tasks | Over-involvement | Info |
| Zero assignments | Unnecessary inclusion | Info |
Scan for all 15 anti-patterns:
| # | Anti-Pattern | Detection | Severity | Fix |
|---|---|---|---|---|
| 1 | No A assigned | Row has 0 A's | Critical | Assign exactly one A |
| 2 | Multiple A's | Row has > 1 A | Critical | Reduce to one A; make others C or I |
| 3 | No R assigned | Row has 0 R's | Critical | Assign at least one R |
| 4 | Too many R's | Row has > 2 R's | Warning | Break task into sub-tasks or reduce |
| 5 | Consultation overload | Row has > 3 C's | Warning | Downgrade some C's to I |
| 6 | R without A | Row has R but no A | Critical | Add one A |
| 7 | R+A same person everywhere | Same person R+A for > 50% | Warning | Redistribute A's |
| 8 | Empty columns | Role has 0 assignments | Info | Remove from matrix or assign |
| 9 | Empty rows | Task has 0 assignments | Critical | Assign R and A or remove task |
| 10 | A overload | Person A for > 40% | Warning | Redistribute accountability |
| 11 | R overload | Person R for > 50% | Warning | Redistribute or add resources |
| 12 | Universal C | Person C for > 60% | Warning | Downgrade to I where possible |
| 13 | Informed overload | > 5 I's per row | Info | Reduce to genuine need-to-know |
| 14 | Title-based, not workflow | Assignments follow org chart, not process | Info | Review against actual workflow |
| 15 | Static document risk | No review schedule defined | Info | Recommend periodic review |
For each detected pattern: identify affected tasks/roles, describe impact, suggest specific fix.
| Role | R | A | C | I | Total | % of tasks | Workload |
|---|---|---|---|---|---|---|---|
| [role] | [n] | [n] | [n] | [n] | [n] | [%] | [balanced/heavy/light] |
Per task, score 0-100:
2 R's: -10
3 C's: -10
Composite 0-100 across all tasks:
| Score range | Rating |
|---|---|
| 90-100 | Excellent governance clarity |
| 75-89 | Good — minor improvements needed |
| 50-74 | Fair — significant gaps to address |
| < 50 | Poor — major governance issues |
Derived from C and I assignments:
| Role | Consulted on (two-way) | Informed about (one-way) | Suggested method |
|---|---|---|---|
| [role] | [task list] | [task list] | [meeting/email/report] |
xychart-beta
title Workload Distribution by Role
x-axis [Role A, Role B, Role C, Role D, Role E]
y-axis "Assignment Count" 0 --> 30
bar [12, 2, 5, 8, 3]
bar [3, 18, 1, 2, 4]
bar [2, 0, 8, 3, 6]
bar [5, 0, 3, 7, 2]
Four bars per role: R (green), A (blue), C (yellow), I (gray) counts.
xychart-beta
title Decision Clarity by Task Group
x-axis ["Planning", "Design", "Development", "Testing", "Deployment"]
y-axis "Clarity Score" 0 --> 100
bar [95, 80, 70, 85, 60]
Show decision clarity score averaged by task group/phase.
For matrices with < 20 tasks × < 10 roles:
flowchart LR
classDef role fill:#2196F3,stroke:#333,color:#fff
classDef task fill:#FFF,stroke:#333
PM["Project Manager"]:::role
TL["Tech Lead"]:::role
T01["Requirements"]:::task
T02["Architecture"]:::task
PM -->|"A"| T01
PM -->|"I"| T02
TL -->|"R"| T01
TL -->|"A"| T02
For larger matrices: skip this diagram and note: "Responsibility network diagram omitted — matrix exceeds visual clarity threshold (>20 tasks or >10 roles)."
Render diagrams per the diagram-rendering mixin.
File naming:
workload-distribution.mmd / .pnggovernance-health.mmd / .pngresponsibility-network.mmd / .pngAssemble the complete report:
# RACI Matrix: [Project/Initiative]
**Date**: [date]
**Project**: [name]
**Variant**: [RACI/RASCI/RACI-VS/RACIO/DACI/RAPID]
**Tasks**: [count]
**Roles**: [count]
**Governance health score**: [0-100] — [rating]
## Executive Summary
[Key findings: governance health, critical gaps, overloaded roles, top 3 recommendations]
## Roles Directory
[Phase 3 table: role, description, authority, source]
## RACI Matrix
[Phase 5 core matrix table]
## Horizontal Validation
[Phase 6 per-task validation table]
## Vertical Validation
[Phase 7 per-role validation table]
## Anti-Pattern Report
[Phase 8 detected patterns with severity, affected items, fixes]
## Workload Distribution
[Phase 9 per-role summary + Phase 10 workload chart]
## Decision Clarity Analysis
[Phase 9 per-task scores + Phase 10 governance health chart]
## Communication Plan Skeleton
[Phase 9 C/I derived communication plan]
## Responsibility Network
[Phase 10 network diagram (if matrix size allows)]
## Recommendations
[Prioritized actions traced to specific findings]
## Sources
[Numbered list of web sources]
## Assumptions & Limitations
[Explicit list]
Present for user approval. Save only after explicit confirmation.
Per the autonomous-research mixin, plus:
| Situation | Behavior |
|---|---|
| No project context | Enter interview mode — ask what project to create a RACI for |
| Context too vague | Enter interview mode — ask targeted questions |
| Too few tasks identifiable | Report limitation, produce smaller matrix (minimum 8 tasks) |
| Too few roles identifiable | Report limitation, work with available (minimum 3 roles) |
| Stakeholder mapping malformed | Ask user to verify, attempt partial import |
| Variant not applicable | Recommend appropriate variant, confirm with user |
| Hard rule violation in own output | Auto-correct before presenting; if conflict, present options |
| Existing matrix has unfixable issues | Report as Critical, present alternatives, let user decide |
| mmdc / web search failures | See diagram-rendering and autonomous-research mixins |
| Out-of-scope request | "This skill creates and validates RACI matrices. [Request] is outside scope." |
Before presenting output, verify:
[] 15-40 tasks identified and organized by phase (8+ for small scope)
[] 5-15 roles identified with descriptions and authority levels
[] Every row has exactly 1 A (hard rule — zero exceptions)
[] Every row has at least 1 R (hard rule — zero exceptions)
[] One code per cell maximum
[] All 15 anti-patterns scanned
[] Horizontal validation complete for every row with counts
[] Vertical validation complete for every column with counts
[] Workload distribution calculated per role
[] Decision clarity scored per task (0-100)
[] Governance health score calculated (0-100)
[] Communication plan skeleton derived from C and I assignments
[] Recommendations traced to specific validation findings
[] All Mermaid diagrams render valid syntax (per diagram-rendering mixin)
[] Sources listed for claims (per autonomous-research mixin)
[] Assumptions labeled (per autonomous-research mixin)
[] Matrix counts are mathematically consistent
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub ssiertsema/claude-code-plugins --plugin raci-matrix