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.
Install
npx skills add adriannoes/awesome-agentic-ai --skill evalsgit 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/evalsPersonal 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.
Details
- Skill name
evals- Repository
- adriannoes/awesome-agentic-ai
- 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
100adriannoes/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".
Coverage
100adriannoes/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".
Fix
100adriannoes/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".
Extracting Config From Agent Tesla Rat
100adriannoes/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.
Effective Agent Skills
100adriannoes/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.
Fable Safe Prompt
100adriannoes/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.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.