Agent skill

Decision Support

by jmagly in jmagly/aiwg

Facilitate data-driven technical decisions using weighted decision matrices, trade-off analysis, and ADR generation

MITAuto-check passedDevelopment

Install Decision Support

skills CLI
$ npx skills add jmagly/aiwg --skill decision-support -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jmagly/aiwg decision-support --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jmagly/aiwg.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agentic/code/plugins/sdlc/skills/decision-support .claude/skills/decision-support && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
decision-support
GitHub stars
220
Used in
1 other repo
Token cost
~2.7k tokens
SKILL.md length
243 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Facilitate data-driven technical decisions using weighted decision matrices, trade-off analysis, and ADR generation

  • Works in 6 steps: Identifies decision context → Gathers alternatives → Defines evaluation criteria → …
  • Tasks that involve Architecture decision records
  • SKILL.md covers Triggers, Purpose, Behavior and Decision Types, plus 8 more sections
  • Calls aws

What it does

Decision Support is an agent skill from jmagly/aiwg. Facilitate data-driven technical decisions using weighted decision matrices, trade-off analysis, and ADR generation

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Architecture decision records. The repository describes itself as: Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and multi-platform deployment. Claude Code · Codex · Copilot · Cursor ·… The licence is MIT.

When your agent uses it

  • Tasks that involve Architecture decision records

Example prompts

  • “/decision-support”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Identifies decision context
  2. Gathers alternatives
  3. Defines evaluation criteria
  4. Builds decision matrix
  5. Analyzes trade-offs
  6. Generates recommendation

What it can do on your machine

Read from SKILL.md and the folder at commit dda238f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • aws

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use aws, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Decision Support loads about 2.7k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 243 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jmagly/aiwg at commit dda238f, republished under its MIT licence (© jmagly). 243 words, ~2,707 tokens.

Download SKILL.mdSave it as .claude/skills/decision-support/SKILL.md (or your agent's skills folder).
name
decision-support
description
Facilitate data-driven technical decisions using weighted decision matrices, trade-off analysis, and ADR generation
namespace
aiwg
platforms
all

decision-support

Facilitate data-driven technical decisions using embedded decision matrices and trade-off analysis.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

  • "ADR" in decision context → Architecture Decision Record
  • "ToT" / "tree of thought" → structured reasoning mode
  • "pros and cons" → trade-off analysis

Purpose

This skill facilitates structured decision-making for technical and architectural choices by:

  • Building weighted decision matrices
  • Analyzing trade-offs across multiple dimensions
  • Documenting decision rationale
  • Generating Architecture Decision Records (ADRs)
  • Tracking decision outcomes

Behavior

When triggered, this skill:

  1. Identifies decision context:

    • Parse the decision question
    • Identify stakeholders and constraints
    • Determine decision type (architectural, technical, process)
  2. Gathers alternatives:

    • List candidate options
    • Research each alternative
    • Document key characteristics
  3. Defines evaluation criteria:

    • Identify relevant factors
    • Assign weights based on priorities
    • Define scoring rubrics
  4. Builds decision matrix:

    • Score each option per criterion
    • Calculate weighted totals
    • Visualize comparisons
  5. Analyzes trade-offs:

    • Identify strengths/weaknesses
    • Document risks per option
    • Consider long-term implications
  6. Generates recommendation:

    • Provide data-backed recommendation
    • Document minority positions
    • Create ADR for record

Decision Types

Architectural Decisions
yaml
architectural:
  examples:
    - database_selection
    - api_design_pattern
    - microservices_vs_monolith
    - authentication_approach
    - caching_strategy

  typical_criteria:
    - scalability
    - maintainability
    - performance
    - security
    - team_expertise
    - cost
    - time_to_implement
Technical Decisions
yaml
technical:
  examples:
    - library_selection
    - framework_choice
    - language_selection
    - testing_approach
    - ci_cd_tooling

  typical_criteria:
    - maturity
    - community_support
    - documentation
    - learning_curve
    - integration_ease
    - license_compatibility
Process Decisions
yaml
process:
  examples:
    - branching_strategy
    - release_cadence
    - review_process
    - documentation_approach
    - communication_tools

  typical_criteria:
    - team_fit
    - efficiency
    - quality_impact
    - adoption_effort
    - tooling_support

Decision Matrix Template

markdown
# Decision Matrix: [Decision Title]

**Decision ID**: DEC-2025-001
**Date**: 2025-12-08
**Status**: Under Evaluation
**Decision Owner**: [Name]
**Stakeholders**: [List]

## Context

[Description of the problem or opportunity requiring a decision]

## Constraints

- [Constraint 1]
- [Constraint 2]
- [Constraint 3]

## Options Under Consideration

### Option A: [Name]
- **Description**: [Brief description]
- **Pros**: [Key advantages]
- **Cons**: [Key disadvantages]
- **Risk Level**: Low/Medium/High

### Option B: [Name]
- **Description**: [Brief description]
- **Pros**: [Key advantages]
- **Cons**: [Key disadvantages]
- **Risk Level**: Low/Medium/High

### Option C: [Name]
- **Description**: [Brief description]
- **Pros**: [Key advantages]
- **Cons**: [Key disadvantages]
- **Risk Level**: Low/Medium/High

## Evaluation Criteria

| Criterion | Weight | Description |
|-----------|--------|-------------|
| Scalability | 25% | Ability to handle growth |
| Maintainability | 20% | Ease of ongoing maintenance |
| Performance | 20% | Speed and efficiency |
| Security | 15% | Security posture |
| Team Expertise | 10% | Team familiarity |
| Cost | 10% | Total cost of ownership |

## Scoring Rubric

| Score | Meaning |
|-------|---------|
| 5 | Excellent - Exceeds requirements |
| 4 | Good - Meets all requirements |
| 3 | Adequate - Meets most requirements |
| 2 | Poor - Meets some requirements |
| 1 | Unacceptable - Does not meet requirements |

## Decision Matrix

| Criterion | Weight | Option A | Option B | Option C |
|-----------|--------|----------|----------|----------|
| Scalability | 25% | 4 (1.00) | 5 (1.25) | 3 (0.75) |
| Maintainability | 20% | 5 (1.00) | 3 (0.60) | 4 (0.80) |
| Performance | 20% | 4 (0.80) | 5 (1.00) | 3 (0.60) |
| Security | 15% | 4 (0.60) | 4 (0.60) | 5 (0.75) |
| Team Expertise | 10% | 5 (0.50) | 2 (0.20) | 4 (0.40) |
| Cost | 10% | 3 (0.30) | 4 (0.40) | 3 (0.30) |
| **Total** | 100% | **4.20** | **4.05** | **3.60** |

## Trade-off Analysis

### Option A vs Option B
- **A wins on**: Maintainability (+2), Team Expertise (+3)
- **B wins on**: Scalability (+1), Performance (+1), Cost (+1)
- **Key trade-off**: Immediate productivity vs long-term scale

### Option A vs Option C
- **A wins on**: Scalability (+1), Maintainability (+1), Performance (+1)
- **C wins on**: Security (+1)
- **Key trade-off**: Overall capability vs security focus

## Risk Assessment

| Option | Key Risks | Mitigation |
|--------|-----------|------------|
| A | May hit scale limits in 2 years | Plan migration path |
| B | Learning curve may slow initial dev | Training budget |
| C | Performance concerns at scale | Performance testing |

## Recommendation

**Recommended Option**: Option A

**Rationale**:
1. Highest weighted score (4.20)
2. Strong team expertise reduces implementation risk
3. Best maintainability for long-term ownership
4. Acceptable scalability with documented migration path

**Dissenting Views**:
- [Stakeholder X] prefers Option B for scalability headroom
- Noted for future re-evaluation if growth exceeds projections

## Decision Record

**Decision**: Adopt Option A
**Decided By**: [Decision Owner]
**Date**: 2025-12-08
**Review Date**: 2026-06-08 (6 months)

## Action Items

- [ ] Document implementation approach
- [ ] Create ADR
- [ ] Communicate decision to team
- [ ] Set up review milestone

ADR Generation

When a decision is finalized, generate an ADR:

markdown
# ADR-XXX: [Decision Title]

## Status

Accepted

## Context

[Background and problem statement]

## Decision

We will use [Option A] because [rationale summary].

## Consequences

### Positive
- [Benefit 1]
- [Benefit 2]

### Negative
- [Trade-off 1]
- [Trade-off 2]

### Neutral
- [Observation 1]

## Alternatives Considered

### Option B: [Name]
Rejected because: [reason]

### Option C: [Name]
Rejected because: [reason]

## References

- Decision Matrix: .aiwg/decisions/DEC-2025-001.md
- Related ADRs: ADR-XXX

Usage Examples

Full Decision Analysis
User: "Help me decide between PostgreSQL and MongoDB for our user service"

Skill executes:
1. Identify decision: Database selection for user service
2. Gather alternatives: PostgreSQL, MongoDB, (suggests DynamoDB)
3. Define criteria based on user service requirements
4. Build comparison matrix
5. Analyze trade-offs
6. Generate recommendation

Output:
"Decision Analysis: User Service Database

Options Evaluated:
1. PostgreSQL (Score: 4.35)
2. MongoDB (Score: 3.90)
3. DynamoDB (Score: 3.65)

Recommendation: PostgreSQL

Key Factors:
- Strong ACID compliance for user data
- Team has SQL expertise
- Proven scalability with proper indexing
- Better for relational user data patterns

Trade-off Accepted:
- Less flexibility for schema changes
- Mitigation: Use JSONB for extensible fields

Decision Matrix: .aiwg/decisions/database-selection.md
ADR: .aiwg/architecture/adr-015-user-db.md"
Quick Comparison
User: "Compare options for API gateway"

Skill generates:
- Kong vs AWS API Gateway vs Nginx
- Weighted criteria comparison
- Quick recommendation

Output:
"API Gateway Comparison:

| Criteria | Kong | AWS GW | Nginx |
|----------|------|--------|-------|
| Features | 5 | 4 | 3 |
| Cost | 3 | 4 | 5 |
| Ops Effort | 3 | 5 | 2 |
| Flexibility | 5 | 3 | 5 |
| Weighted | 4.1 | 4.0 | 3.8 |

Recommendation: Kong (slight edge)
Key: Best feature set with acceptable ops overhead

Want full analysis? Say 'full decision matrix'"
Trade-off Focus
User: "What are the trade-offs between microservices and monolith?"

Skill analyzes:
- Key dimensions
- Specific trade-offs
- When each is preferred

Output:
"Microservices vs Monolith Trade-offs:

Microservices Wins:
✓ Independent scaling
✓ Technology flexibility
✓ Team autonomy
✓ Fault isolation

Monolith Wins:
✓ Simpler operations
✓ Easier debugging
✓ Lower latency (no network)
✓ Faster initial development

Decision Factors:
- Team size: <10 devs → monolith
- Scale needs: 10x+ growth → microservices
- Domain complexity: Clear boundaries → microservices

Want me to build a decision matrix for your specific context?"

Integration

This skill uses:

  • project-awareness: Context for decision constraints
  • artifact-metadata: Track decision lifecycle
  • template-engine: Load ADR templates

Agent Orchestration

yaml
agents:
  research:
    agent: technical-researcher
    focus: Gather data on alternatives

  architecture:
    agent: architecture-designer
    focus: Architectural implications

  security:
    agent: security-architect
    focus: Security trade-offs
    condition: security_relevant == true

  cost:
    agent: business-process-analyst
    focus: Cost and resource implications

Configuration

Default Criteria Sets
yaml
criteria_sets:
  architectural:
    - {name: scalability, weight: 20, default: true}
    - {name: maintainability, weight: 20, default: true}
    - {name: performance, weight: 15, default: true}
    - {name: security, weight: 15, default: true}
    - {name: team_expertise, weight: 10, default: true}
    - {name: cost, weight: 10, default: true}
    - {name: time_to_implement, weight: 10, default: true}

  library_selection:
    - {name: maturity, weight: 20}
    - {name: community_support, weight: 20}
    - {name: documentation, weight: 15}
    - {name: learning_curve, weight: 15}
    - {name: license, weight: 15}
    - {name: performance, weight: 15}
Decision Thresholds
yaml
thresholds:
  clear_winner: 0.5  # Score gap for clear recommendation
  close_call: 0.2    # Gap requiring stakeholder input
  tie: 0.1           # Effectively equal, other factors decide

Output Locations

  • Decision matrices: .aiwg/decisions/
  • ADRs: .aiwg/architecture/adr-*.md
  • Decision log: .aiwg/decisions/decision-log.md

References

  • ADR template: templates/analysis-design/adr-template.md
  • Decision matrix template: templates/management/decision-matrix.md
  • Trade-off catalog: docs/common-tradeoffs.md

© jmagly, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agentic/code/plugins/sdlc/skills/decision-support of jmagly/aiwg.

Open the folder on GitHubat commit dda238f

Used in 1 other repository

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in jmagly/aiwg, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Decision Support next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Decision Support compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Decision Support this skilljmagly/aiwg2201 repos~2.7kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT
Cto AdvisorIbrahim-3d/orchestrator-supaconductor3804 repos~2.4kAutomated safety check: PassMIT
Improve Codebase Architectureywwynm/EverythingDone14415 repos~1.3kAutomated safety check: PassGPL-3.0
Domain Modelingbrim-borium/spotify_sdk1665 repos~806Automated safety check: PassApache-2.0
Design Doc MermaidSpillwaveSolutions/design-doc-mermaid1751 repos~5.6kAutomated safety check: PassNone

Similar skills

  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Cto Advisor

    Ibrahim-3d/orchestrator-supaconductor

    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

    380 GitHub starsUsed in 4 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Improve Codebase Architecture

    ywwynm/EverythingDone

    Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.

    144 GitHub starsUsed in 15 repos~1.3k tokens
    DevelopmentAuto-check passed
  • Domain Modeling

    brim-borium/spotify_sdk

    Build and sharpen a project's domain model. An agent skill from brim-borium/spotify_sdk.

    166 GitHub starsUsed in 5 repos~806 tokens
    DevelopmentAuto-check passed
  • Design Doc Mermaid

    SpillwaveSolutions/design-doc-mermaid

    Create Mermaid diagrams (flowchart, sequence, class, ER, state, C4, architecture) from text or source code.

    175 GitHub starsUsed in 1 repo~5.6k tokens
    DevelopmentAuto-check passed
  • Learning Opportunities

    DrCatHicks/learning-opportunities

    Facilitates deliberate skill development during AI-assisted coding.

    2.5k GitHub stars~2.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from jmagly/aiwg

All 12 skills in this repo
  • Review editorial phrase patterns and suggest contextual alternatives; legacy name does not imply authorship detection.

    220 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Voice Apply

    jmagly/aiwg

    Apply a voice profile to transform content. An agent skill from jmagly/aiwg.

    220 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Mutation Test

    jmagly/aiwg

    Run mutation testing to validate test quality beyond code coverage.

    220 GitHub stars~3.2k tokensUpdated 2 days ago
    Auto-check passed
  • TDD Enforce

    jmagly/aiwg

    Configure TDD enforcement via pre-commit hooks and CI coverage gates.

    220 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed
  • LLMs Txt Support

    jmagly/aiwg

    Detect and use llms.txt files for LLM-optimized documentation.

    220 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions

    220 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Decision Support

What does Decision Support do?

Facilitate data-driven technical decisions using weighted decision matrices, trade-off analysis, and ADR generation. Decision Support is an agent skill from jmagly/aiwg.

When should I use Decision Support?

Decision Support fits situations like: tasks that involve Architecture decision records.

How do I install Decision Support in Claude Code?

Run `npx skills add jmagly/aiwg --skill decision-support -a claude-code`. Or copy the skill folder (agentic/code/plugins/sdlc/skills/decision-support in jmagly/aiwg) into .claude/skills/decision-support in your project. Claude Code loads it when a task matches its description.

How do I install Decision Support in Codex?

Run `npx skills add jmagly/aiwg --skill decision-support -a codex`. Or copy the skill folder (agentic/code/plugins/sdlc/skills/decision-support in jmagly/aiwg) into .agents/skills/decision-support in your project. Codex loads it when a task matches its description.

Can I use Decision Support in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jmagly/aiwg --skill decision-support -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/decision-support, .gemini/skills/decision-support, .github/skills/decision-support and .opencode/skills/decision-support in your project.

What does Decision Support need to run?

Going by SKILL.md and its folder, Decision Support needs the command-line tools its instructions call (aws).

Does Decision Support access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Decision Support safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Decision Support use?

Decision Support is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Decision Support use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Decision Support?

Skills that share tags, products or a category with Decision Support: PR Design Doc (OpenHands/OpenHands, 90k stars), Cto Advisor (Ibrahim-3d/orchestrator-supaconductor, 380 stars), Improve Codebase Architecture (ywwynm/EverythingDone, 144 stars) and Domain Modeling (brim-borium/spotify_sdk, 166 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Decision Support?

jmagly (a GitHub user) maintains it in jmagly/aiwg, which has 220 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 5, 2026.

Source: jmagly/aiwg on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.