decision-eval
π―SkillInstallation
npx skills add avelikiy/great_cto --skill decision-evalRun it in a terminal; it asks which AI coding tools to install it for (Claude Code, Codex, Cursor and more).
Uses skills.sh Β· Node.js 22.20+
After installing
Ask for related work and the agent uses it on its own, or call it yourself.
/decision-evalInstall by hand
Copy the whole skill folder from GitHub to the place below. Copying only SKILL.md can leave out files the skill uses.
Open the skill folder β- This project
.claude/skills/decision-eval/ - All projects
~/.claude/skills/decision-eval/
These paths are for Claude Code. For other tools, the command above puts it in the right place.
SKILL.md
View on GitHub βSpawns the decision-scorer agent after architect proposes 2+ variants in an ADR. Produces a weighted scoring table and recommended choice saved to docs/decisions/.
Decision Eval β 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:
- An ADR (
docs/adr/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:**) - The architect has not yet created
gate:arch - The user has not said "skip scoring", "no scoring", or "skip decision-eval"
project_sizein PROJECT.md is NOTnano
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=$(ls -t docs/adr/ADR-*.md 2>/dev/null | head -1)
[ -z "$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: nanoin 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 β proceed to gate:arch with the recommended option
- Override the recommendation β document rationale in the ADR under a new
## Scoring Overridesection before creating gate:arch
More from this repository6
An open-source engineering OS for Claude Code that orchestrates 51 specialist agents including architect, PM, senior-dev, code-reviewer, QA, security, and DevOps roles. Covers 16 domain packs (voice-AI, clinical, HR-AI, fintech, and more) as a local-first alternative to Devin for solo CTOs.
Skill
Skill
Skill
Skill
A tool that runs Claude Code work in clear stages with reviews and checks, and can try the same with Codex. A local board shows your tasks, what ran, project documents and usage in one place.