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.
What this skill does
# RACI Matrix
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.
## Supported Variants
| 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) |
## Phase 1 — Setup
### Input handling
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.
### 1. Collect input
Accept one of:
- A project or initiative description
- A file path to a stakeholder mapping report and/or task list
- Pasted content (business case, stakeholder register, WBS)
- No input or vague input → enter interview mode
### 2. Detect scope and recommend variant
From the input (or interview results), identify:
- **Project/initiative**: What is being planned or executed
- **Domain**: Industry, regulatory context
- **Stakeholder source**: Imported from mapping or to be identified
- **Task source**: Imported from WBS or to be identified
Recommend a variant based on context:
- Regulated industry (SOX, GDPR, FDA) → **RACI-VS** (audit trail)
- Complex support structures → **RASCI** (explicit support roles)
- Decision rights focus → **DACI** or **RAPID**
- Political sensitivity about exclusion → **RACIO**
- General → **RACI**
### 3. Confirm scope
```
**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.
## Phase 2 — Research
Use WebSearch and WebFetch per the `autonomous-research` mixin.
### 2a. Role structure research
Research typical role structures for this type of project/industry:
- Standard project roles and their authority levels
- Industry-specific roles (compliance, regulatory, audit)
- Governance patterns and decision-making structures
### 2b. Task breakdown research
Research common task breakdowns for similar initiatives:
- Standard project phases and deliverables
- Industry-specific tasks and milestones
- Governance checkpoints and approval gates
## Phase 3 — Role Identification (Columns)
### If stakeholder mapping is provided
Import roles with their attributes:
- Read the stakeholder mapping report
- Extract roles from the stakeholder register
- Map Power/Interest quadrant to likely RACI assignments:
- Manage Closely (high power, high interest) → likely A or R
- Keep Satisfied (high power, low interest) → likely A or I
- Keep Informed (low power, high interest) → likely C or I
- Monitor (low power, low interest) → likely I or blank
### If no stakeholder mapping
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.
## Phase 4 — Task/Deliverable Identification (Rows)
### If WBS/task list is provided
Import tasks, validate granularity, organize by phase.
### If no task list
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:**
- Specific enough for clear responsibility assignment
- Not micro-tasks (avoid "write line 42 of config")
- Not too high-level ("do the project")
- Each task should have a clear "done" state
Present task list for user confirmation.
## Phase 5 — RACI Assignment
### RACI code definitions
| 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:
- **S** (Supportive/RASCI): Assists R but doesn't own the task
- **V** (Verifier/RACI-VS): Checks deliverable meets acceptance criteria
- **Si** (Signatory/RACI-VS): Provides formal sign-off
- **O** (Omitted/RACIO): Explicitly excluded from involvement
- **D** (Driver/DACI): Leads the decision process (equivalent to R)
- **Ap** (Approver/DACI): Has final say (equivalent to A)
### Hard rules (must enforce)
1. Every row must have **exactly 1 A** — no exceptions
2. Every row must have **at least 1 R** — someone must do the work
3. One code per cell (or blank)
### Soft rules (best practices, report violations as Warning)
4. Prefer 1-2 R per row (avoid "too many cooks")
5. Max 2-3 C per row (avoid consultation bottleneck)
6. Separate R and A where possible (four-eyes principle)
7. No person A for > 40% of tasks (bottleneck risk)
### Assignment table
| Task | Role A | Role B | Role C | Role D | ... |
|---|---|---|---|---|---|
| T01: [task] | R | A | C | I | ... |
| T02: [task] | A | R | | I | ... |
## Phase 6 — Horizontal Validation (per task)
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 |
### Validation rules
| 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 |
## Phase 7 — Vertical Validation (per role)
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 |
### Validation rules
| 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** |
## Phase 8 — Anti-Pattern Detection
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 |Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.