Eval
- 1.4k installs
- 23.5k repo stars
- Updated July 17, 2026
- alirezarezvani/claude-skills
eval is an agent skill that Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
About
Evaluate and rank agent results by metric or LLM judge for an AgentHub session. --- name: "eval" description: "Evaluate and rank agent results by metric or LLM judge for an AgentHub session." command: /hub:eval --- # /hub:eval - Evaluate Agent Results Rank all agent results for a session. Supports metric-based evaluation (run a command), LLM judge (compare diffs), or hybrid. ## Usage ``` /hub:eval # Eval latest session using configured criteria /hub:eval 20260317-143022 # Eval specific session /hub:eval --judge # Force LLM judge mode (ignore metric config) ``` ## What It Does ### Metric Mode (eval command configured) Run the evaluation command in each agent's worktree: ```bash python {skill_path}/scripts/result_ranker.py \ --session {session-id} \ --eval-cmd "{eval_cmd}" \ --metric {metric} --direction {direction} ``` Output: ``` RANK AGENT METRIC DELTA FILES 1 agent-2 142ms -38ms 2 2 agent-1 165ms -15ms 3 3 agent-3 190ms +10ms 1 Winner: agent-2 (142ms) ``` ### LLM Judge Mode (no eval command, or --judge flag) For each agent: 1.
- /hub:eval - Evaluate Agent Results
- Get the diff: `git diff {base_branch}...{agent_branch}`
- Read the agent's result post from `.agenthub/board/results/agent-{i}-result.md`
- Compare all diffs and rank by:
- **Correctness** - Does it solve the task?
Eval by the numbers
- 1,401 all-time installs (skills.sh)
- +2 installs in the week ending Jul 29, 2026 (Skillselion tracking)
- Ranked #492 of 2,159 Testing & QA skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 31, 2026 (Skillselion catalog sync)
eval capabilities & compatibility
- Capabilities
- /hub:eval — evaluate agent results · get the diff: `git diff {base_branch}...{agent_b · read the agent's result post from `.agenthub/boa · compare all diffs and rank by: · **correctness** — does it solve the task?
- Use cases
- documentation
What eval says it does
Supports metric-based evaluation (run a command), LLM judge (compare diffs), or hybrid.
Get the diff: `git diff {base_branch}...{agent_branch}` 2.
Read the agent's result post from `.agenthub/board/results/agent-{i}-result.md` 3.
Compare all diffs and rank by: - **Correctness** — Does it solve the task?
npx skills add https://github.com/alirezarezvani/claude-skills --skill evalAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1.4k |
|---|---|
| repo stars | ★ 23.5k |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 17, 2026 |
| Repository | alirezarezvani/claude-skills ↗ |
What problem does eval solve for developers using this skill?
Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
Who is it for?
Developers who need eval patterns described in the cached skill documentation.
Skip if: Skip when docs are empty or the task is outside the skill's documented scope.
When should I use this skill?
Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
What you get
Actionable workflows and conventions from SKILL.md for eval.
- ranked agent results
- evaluation scores
Files
../../../engineering/agenthub/skills/eval/SKILL.md
Related skills
TddFollow test-driven development with a strict red-green-refactor loop when creating reliable features or fixing bugs.510k185k
Test Driven DevelopmentEnforce writing failing tests before any production implementation code.176k260kQaRun conversational QA sessions that turn user-reported bugs into well-written, domain-aware GitHub issues without manual ticket writing.164k185kMigrate To ShoehornAutomatically update TypeScript test files that rely on unsafe `as` type assertions by replacing them with type-safe partial objects from @total-typescript/shoehorn.151k185k
Webapp TestingVerify frontend behavior, debug UI issues, capture screenshots, and inspect logs of a running local web application using Playwright.121k164k
Playwright CliRun browser automation, generate element snapshots, inspect DOM attributes, and execute Playwright tests from the terminal.96.3k12.2kHow it compares
Use eval within AgentHub parallel sessions; use standalone LLM eval frameworks for production model benchmarking outside git worktrees.
FAQ
What does eval do?
Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
When should I use eval?
Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
Is eval safe to install?
Review the Security Audits panel on this page before installing in production.