Back to Skills

decision-eval

avelikiy
Updated 2 days ago
9 views
30
6
30
View on GitHub
Documentationgeneral

About

The decision-eval skill automatically scores architectural alternatives by spawning a decision-scorer agent when an ADR contains two or more proposed variants. It generates a weighted scoring table and a recommended choice, saving the output to the docs/decisions/ directory. Use this skill to obtain an objective tie-breaker before finalizing a multi-variant decision, typically prior to gate:arch approval.

Quick Install

Claude Code

Recommended
Primary
npx skills add avelikiy/great_cto -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/avelikiy/great_cto
Git CloneAlternative
git clone https://github.com/avelikiy/great_cto.git ~/.claude/skills/decision-eval

Copy and paste this command in Claude Code to install this skill

Documentation

Decision Eval — automated scoring for architectural alternatives

Invoke after architect proposes 2+ variants, before creating gate:arch.

When to invoke

Invoke this skill when ALL of these are true:

  1. An ADR (docs/decisions/ADR-*.md) or ARCH doc (docs/architecture/ARCH-*.md) contains a section with 2 or more named alternatives (look for ## Alternatives Considered, ## Options, or bold-prefixed options like **Option A:**)
  2. The architect has not yet created gate:arch
  3. The user has not said "skip scoring", "no scoring", or "skip decision-eval"
  4. project_size in PROJECT.md is NOT nano

Skip silently (do not even mention) if any condition fails.

How to invoke

Read the most recent ADR or ARCH doc to confirm 2+ variants exist, then spawn the decision-scorer agent with the file path as context:

# Identify target document
TARGET=$(ls -t docs/decisions/ADR-*.md 2>/dev/null | head -1)
[ -z "$TARGET" ] && TARGET=$(ls -t docs/architecture/ARCH-*.md 2>/dev/null | head -1)

# Confirm 2+ variants
VARIANT_COUNT=$(grep -cE "^\*\*[A-Za-z]|^### [A-Za-z]|^- \*\*[A-Za-z]" "$TARGET" 2>/dev/null || echo 0)

If VARIANT_COUNT >= 2, dispatch the agent:

Agent: decision-scorer
Context: <TARGET file path>
Task: Score the architectural variants in <TARGET> against .great_cto/PROJECT.md criteria.
      Save output to docs/decisions/.

Output location

The decision-scorer agent saves results to:

docs/decisions/DECISION-<slug>-<YYYYMMDD>.md

After the agent completes, read the output file and surface the recommendation to the architect:

Decision scoring complete:
  Recommended: <variant name> (<score>/5.00)
  Runner-up:   <variant name> (<score>/5.00)
  Full report: docs/decisions/DECISION-<slug>-<YYYYMMDD>.md

Architect: review the scoring rationale before accepting or overriding the recommendation.

Skip conditions

Output nothing and proceed to the next step if:

  • project_size: nano in PROJECT.md
  • Fewer than 2 variants found in the ADR/ARCH doc
  • User message contains "skip scoring" or "skip decision-eval" or "no scoring"
  • The target document is a bug-fix or docs-only ADR (check title for "fix:", "docs:", "chore:")

Integration with architect workflow

This skill sits between Step 4 (Write ADR) and Step 5 (Create gate:arch) in agents/architect.md. Architect invokes it by name:

Invoke skill: decision-eval

After scoring completes, architect may:

  • Accept the recommendation → proceed to gate:arch with the recommended option
  • Override the recommendation → document rationale in the ADR under a new ## Scoring Override section before creating gate:arch

GitHub Repository

avelikiy/great_cto
Path: skills/decision-eval
0
agentic-codingclaude-code-pluginclaude-code-skillsclaude-code-subagentscode-reviewcto

Related Skills

railway-docs

Documentation

This skill fetches current Railway documentation to answer questions about features, functionality, or specific docs URLs. It ensures developers receive accurate, up-to-date information directly from Railway's official sources. Use it when users ask how Railway works or reference Railway documentation.

View skill

n8n-code-python

Documentation

This Claude Skill provides expert guidance for writing Python code in n8n's Code nodes, specifically for using Python's standard library and working with n8n's special syntax like `_input`, `_json`, and `_node`. It helps developers understand Python's limitations within n8n and recommends using JavaScript for most workflows while offering Python solutions for specific data transformation needs.

View skill

archon

Documentation

The Archon skill provides RAG-powered semantic search and project management through a REST API. Use it for querying documentation, managing hierarchical projects/tasks, and performing knowledge retrieval with document upload capabilities. Always prioritize Archon first when searching external documentation before using other sources.

View skill

n8n-code-javascript

Documentation

This Claude Skill provides expert guidance for writing JavaScript code in n8n's Code nodes. It covers essential n8n-specific syntax like `$input`/`$json` variables, HTTP helpers, and DateTime handling, while troubleshooting common errors. Use it when developing n8n workflows that require custom JavaScript processing in Code nodes.

View skill