Decision Eval

What it does

When your agent uses it

• Tasks that involve Architecture decision records

Example prompts

• “Use the decision-eval skill to spawn the decision-scorer agent after architect proposes 2+ variants in an ADR”
• “/decision-eval”

Requirements

• Pre-approved tools (allowed-tools): Read, Glob, Bash, Agent

Workflow steps

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

1. 1An ADR (docs/adr/ADR-*.md) or ARCH doc (docs/architecture/ARCH-*.md)
2. 2The architect has not yet created gate:arch
3. 3The user has not said "skip scoring", "no scoring", or "skip decision-eval"
4. 4project_size in PROJECT.md is NOT nano

What it can do on your machine

Read from SKILL.md and the folder at commit 5d6e760. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Bash
  • Agent

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

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

• Network

  No URLs in SKILL.md.

  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 Eval loads about 884 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 256 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~44

When it runs · the whole SKILL.md, loaded when a task matches

~884

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Glob, Bash, Agent

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 avelikiy/great_cto at commit 5d6e760, republished under its MIT licence (© avelikiy). 256 words, ~884 tokens.

name

decision-eval

description

Spawns the decision-scorer agent after architect proposes 2+ variants in an ADR. Produces a weighted scoring table and recommended choice saved to docs/decisions/.

allowed-tools

Read, Glob, Bash, Agent

when_to_use

Apply when: - architect has written an ADR with 2+ alternatives under ## Alternatives Considered or ## Options - architect is about to finalize a…

effort

medium

paths

docs/decisions/**, docs/architecture/**, .great_cto/PROJECT.md

# 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)

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/.

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

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.

Invoke skill: decision-eval

© avelikiy, 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 skills/decision-eval of avelikiy/great_cto.

Open the folder on GitHubat commit 5d6e760