Name: Evaluation Coverage Audit
Author: Skills Guide Bot

Automated summary

Performs a retroactive evaluation-coverage audit of an already executed AI phase, checking the actual implementation against the evaluation strategy defined in AI-SPEC.md.

Strengths

Scores each evaluation dimension as COVERED/PARTIAL/MISSING, making gaps immediately legible
Produces a structured EVAL-REVIEW.md deliverable with a verdict, gaps and an actionable remediation plan
Relies on dedicated workflows and references (ai-evals.md) instead of ad-hoc inspection
Can target a specific phase number or default to the last completed phase

Limitations

Assumes an AI-SPEC.md containing an evaluation strategy already exists; without it the audit has no baseline
The analysis is retroactive only: it reports missing evals but does not implement them
Verdict quality depends on how well the actual evaluation artifacts can be located

When to use it

Use it after an AI phase has been delivered, to objectively confirm the planned evaluation strategy was really implemented before moving on.

When not to use it

Avoid it before a phase has run or on projects with no evaluation spec, since there is no baseline to audit against.

Security analysis

Safe

Quality score80/100

The skill defines an audit workflow that reads and writes files, uses glob/grep to inspect project contents, and may run Bash for inspection purposes. No destructive commands, data exfiltration, obfuscation, or secret handling are specified. The allowed tools are used for legitimate evaluation review tasks.

No concerns found

How this analysis is made

Examples

Audit a specific phase

/gsd:eval-review 3

Audit the latest completed phase

Run an eval coverage review of the last completed phase and write EVAL-REVIEW.md with the remediation plan.

Check missing evals before shipping

Before we ship this phase, audit whether the evaluation strategy from AI-SPEC.md was actually implemented and list what's COVERED, PARTIAL, or MISSING.

name: gsd:eval-review description: Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan argument-hint: "[phase number]" allowed-tools:

Read
Write
Bash
Glob
Grep
Task
AskUserQuestion

<objective> Conduct a retroactive evaluation coverage audit of a completed AI phase. Checks whether the evaluation strategy from AI-SPEC.md was implemented. Produces EVAL-REVIEW.md with score, verdict, gaps, and remediation plan. </objective>

<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/eval-review.md @${CLAUDE_PLUGIN_ROOT}/references/ai-evals.md </execution_context>

<context> Phase: $ARGUMENTS — optional, defaults to last completed phase. </context> <process> Execute @${CLAUDE_PLUGIN_ROOT}/workflows/eval-review.md end-to-end. Preserve all workflow gates. </process>

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/evaluation-coverage-audit-msba3mnj/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/evaluation-coverage-audit-msba3mnj' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/evaluation-coverage-audit-msba3mnj/download' --output '.skill-downloads/evaluation-coverage-audit-msba3mnj/SKILL.md.part' && mv '.skill-downloads/evaluation-coverage-audit-msba3mnj/SKILL.md.part' '.skill-downloads/evaluation-coverage-audit-msba3mnj/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/evaluation-coverage-audit-msba3mnj/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.