batch
Evaluate multiple artifacts with comparative analysis and parallel processing
Skill by Ankh-Studio
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ankh-studio-batch
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/batch
What's inside
- Skill name
batch- Description
- Evaluate multiple artifacts with comparative analysis and parallel processing
- License
- MIT
- Instructions
- 80 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Batch Evaluate multiple Copilot artifacts efficiently with parallel processing, comparative analysis, and executive reporting. ## Core Process 1. **Discovery**: Scan directories and identify target artifacts 2. **Parallel Evaluation**: Apply appropriate rubrics simultaneously 3. **Comparative Analysis**: Identify patterns, outliers, and trends 4. **Executive Reporting**: Generate summaries and detailed results ## Usage Examples ### Directory Scanning ````bash /batch .github/prompts/ --type prompt /batch .github/skills/ --type skill /batch .github/ --all --recursive ```bash ### Custom Artifact Selection ```bash /batch artifact1.md artifact2.md artifact3.md /batch --glob "*.prompt.md" --exclude "test_*" ```bash ### Comparative Analysis ```bash /batch .github/prompts/ --compare --baseline v1.0 /batch .github/ --trend --timeframe "last-30-days" /batch .github/ --baseline v1.0 --target v2.0 --delta ```bash ### Performance Options ```bash /batch .github/ --parallel --workers 8 /batch .github/ --cache --incremental /batch .github/ --timeout 300 --retry-failed ```bash ## Output Formats ### Executive Dashboard - Quality metrics and KPIs - Trend analysis and comparisons - Risk assessment and priorities - Resource utilization reports ### Detailed Results - Individual artifact evaluations - Comparative insights and patterns - Improvement recommendations - Compliance status tracking ### Export Options ```bash /batch .github/ --export json --file results.json /batch .github/ --export csv --file metrics.csv /batch .github/ --export pdf --report executive-summary ```bash ## Performance Features - **Parallel Processing**: Evaluate multiple artifacts simultaneously - **Smart Caching**: Avoid redundant evaluations - **Incremental Updates**: Process only changed artifacts - **Resource Management**: Optimize memory and CPU usage Enables enterprise-scale quality assurance with efficient batch processing and comprehensive reporting. ````
From Ankh-Studio/copilot-enterprise-eval-plugin, MIT.
More from Ankh-Studio/copilot-enterprise-eval-plugin
- 0.407score
ai-enablement-intelligence
matthewvandusen
Repository intelligence and AI enablement toolkit that analyzes team context, discovers constraints, and provides research-backed AI adoption guidance for…
SkillDFreshness: DClaude Code +9 - 0.404score
artifact-evaluation
Ankh-Studio
Evaluate any Copilot artifact against its structured rubric with Chain-of-Verification methodology
SkillDFreshness: DClaude Code +9 - 0.404score
batch-evaluation
Ankh-Studio
Process multiple artifacts efficiently with comparative analysis and trend reporting
SkillDFreshness: DClaude Code +9 - 0.404score
adversarial
Ankh-Studio
Run comprehensive adversarial evaluation suite with attack patterns and stress testing
SkillDFreshness: DClaude Code +9 - 0.404score
validate-rubrics
Ankh-Studio
Apply adversarial stress-testing to identify and fix vulnerabilities in evaluation rubrics
SkillDFreshness: DClaude Code +9 - 0.404score
prompt-evaluation
Ankh-Studio
Specialized evaluation of prompt quality, clarity, and effectiveness
SkillDFreshness: DClaude Code +9 - 0.404score
architecture-debate
Ankh-Studio
Multi-perspective design decisions using structured debate methodology
SkillDFreshness: DClaude Code +9 - 0.401score
artifact
Ankh-Studio
Evaluate any Copilot artifact against its rubric
SkillDFreshness: DClaude Code +9 - 0.400score
enterprise-onboarding-orchestrator
Ankh-Studio
Enterprise-grade team member onboarding automation with comprehensive learning paths and knowledge transfer
SkillDFreshness: DClaude Code +9 - 0.400score
enterprise-architecture-generator
Ankh-Studio
Enterprise-grade architecture documentation generation with comprehensive system design and maintenance
SkillDFreshness: DClaude Code +9 - 0.400score
enterprise-change-handoff-orchestrator
Ankh-Studio
Enterprise-grade change handoff automation with comprehensive knowledge transfer and continuity management
SkillDFreshness: DClaude Code +9 - 0.400score
pack-context-analyzer
Ankh-Studio
Specialized evaluation of pack context and instructions for team enablement and pack ecosystem alignment
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 13, 2026 (7 months ago)
- Last release
- Mar 14, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Ankh-Studio
- 0.404score
architecture-debate
Ankh-Studio
Multi-perspective design decisions using structured debate methodology
SkillDFreshness: DClaude Code +9 - 0.404score
artifact-evaluation
Ankh-Studio
Evaluate any Copilot artifact against its structured rubric with Chain-of-Verification methodology
SkillDFreshness: DClaude Code +9 - 0.404score
batch-evaluation
Ankh-Studio
Process multiple artifacts efficiently with comparative analysis and trend reporting
SkillDFreshness: DClaude Code +9 - 0.404score
prompt-evaluation
Ankh-Studio
Specialized evaluation of prompt quality, clarity, and effectiveness
SkillDFreshness: DClaude Code +9 - 0.404score
validate-rubrics
Ankh-Studio
Apply adversarial stress-testing to identify and fix vulnerabilities in evaluation rubrics
SkillDFreshness: DClaude Code +9 - 0.404score
adversarial
Ankh-Studio
Run comprehensive adversarial evaluation suite with attack patterns and stress testing
SkillDFreshness: DClaude Code +9
Cite this page
batch skill. Agent Mart. https://agentmart.dev/skills/ankh-studio-batch (last updated 2026-10-24)