Evals

Use to evaluate how faithfully the implementation matches the spec — runs the eval that checks whether each AC-N is covered by a task and referenced in a test, counts SPEC_DEVIATION and reports a score per feature. Trigger with /evals.

100 stars 27 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add adriannoes/awesome-agentic-ai --skill evals
Manual install
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai.git /tmp/awesome-agentic-ai
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-agentic-ai/cursor-claude-codex/skills/igoruehara-spec-driven/skills/evals ~/.claude/skills/evals

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

> **Translation note:** Originally authored in Portuguese (pt-BR) by Igor Uehara ([igoruehara/spec-driven](https://github.com/igoruehara/spec-driven), MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source.

# Skill: Spec→code fidelity evals

Measures whether **what was built reflects the spec** — the quality metric of the agent's output.
Two layers: deterministic (script) and judgment.

## 1. Deterministic layer
```
node scripts/eval-spec-fidelity.mjs .
```
Reports, per feature: total ACs, **covered by a task**, **referenced in test/code**, and
open **SPEC_DEVIATION**. Fails (exit 1) if any AC has no task — broken traceability.
Reference in test is a warning until the feature is implemented.

## 2. Judgment layer (the script does not catch this)
- Does the test for each `AC-N` actually exercise the **Given/When/Then** — or does it just cite the ID in an empty test?
- Does the implementation cover the **edge cases** and respect the spec's **"Out of scope"**?
- Do the open `SPEC_DEVIATION` items have a resolution (fix the code **or** update the spec/ADR)?

## Output
Score per feature + the gaps. It complements `/validar` (UAT for a single feature) with a
**portfolio fidelity** view. The same eval runs in CI (`esteira.yml`) — here it is the judgment counterpart.
Read the full skill on GitHub

Details

Skill name
evals
Path
cursor-claude-codex/skills/igoruehara-spec-driven/skills/evals/SKILL.md
License
MIT
Repo updated
2 November 2026

FAQ

What does the Evals skill do?

Use to evaluate how faithfully the implementation matches the spec — runs the eval that checks whether each AC-N is covered by a task and referenced in a test, counts SPEC_DEVIATION and reports a score per feature. Trigger with /evals.

How do I install the Evals skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add adriannoes/awesome-agentic-ai --skill evals. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Evals popular?

It lives in adriannoes/awesome-agentic-ai, which has 100 GitHub stars and 27 forks, and is included in 2 curated skill lists.

Related skills

Browserstack

100

adriannoes/awesome-agentic-ai

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

Testing & QAIn 2 lists27

Coverage

100

adriannoes/awesome-agentic-ai

Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".

Testing & QAIn 2 lists27

Fix

100

adriannoes/awesome-agentic-ai

Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".

Testing & QAIn 2 lists27

Extracting Config From Agent Tesla Rat

100

adriannoes/awesome-agentic-ai

Extract embedded configuration from Agent Tesla RAT samples including SMTP/FTP/Telegram exfiltration credentials, keylogger settings, and C2 endpoints using .NET decompilation and memory analysis.

AI, LLMs & AgentsIn 2 lists27

Effective Agent Skills

100

adriannoes/awesome-agentic-ai

How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.

AI, LLMs & AgentsIn 2 lists27

Fable Safe Prompt

100

adriannoes/awesome-agentic-ai

Rewrite a user's prompt to reduce the chance it trips Claude Fable 5's server-side safety classifiers (cyber/bio guardrails that force-route to Opus 4.8 or return stop_reason "refusal"). Use when the user hands you a prompt that touches cybersecurity, auth, exploits, malware, pentesting, or other dual-use topics and asks to make it "Fable-safe", "guardrail-safe", "won't get flagged/refused/downgraded", or to rewrite it so Fable 5 won't block it.

AI, LLMs & AgentsIn 2 lists27

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.