Agent Skill
Agentic Eval skill
agentic-evalgithub/awesome-copilotskills/agentic-eval/SKILL.md
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
always on
85 tokname + description
once used
1,247 tokSKILL.md body
bundled files
0
repo stars
40kGitHub
Install the Agentic Eval skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/github/awesome-copilot --skill agentic-eval
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/github/awesome-copilot.git /tmp/awesome-copilot mkdir -p ~/.claude/skills cp -R /tmp/awesome-copilot/skills/agentic-eval ~/.claude/skills/agentic-eval
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 85 tok |
| When the agent uses it | The SKILL.md instructions | 1,247 tok |
| Only if opened | No bundled files | — |
Until it is used, agentic-eval costs about 16× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 150 skills from github/awesome-copilot would load 9,863 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Agentic Evaluation Patterns
- Overview
- When to Use
- Pattern 1: Basic Reflection
- Pattern 2: Evaluator-Optimizer
- Pattern 3: Code-Specific Reflection
- Evaluation Strategies
- Outcome-Based
- LLM-as-Judge
- Rubric-Based
- Best Practices
- Quick Start Checklist
More skills from github/awesome-copilot
- acquire-codebase-knowledgegithub/awesome-copilot
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
40k182 tok idle · 1,945 in use - acreadiness-assessgithub/awesome-copilot
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.
40k82 tok idle · 678 in use - acreadiness-generate-instructionsgithub/awesome-copilot
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
40k77 tok idle · 1,995 in use - acreadiness-policygithub/awesome-copilot
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.
40k73 tok idle · 879 in use - ad-campaign-analyzergithub/awesome-copilot
Use this skill when the user shares ad campaign performance data and asks what to cut, scale, or test. Trigger for prompts like "analyze my ad campaigns", "where am I wasting ad spend", "reallocate my ad budget", "which ads are actually working", or "ROAS analysis". Do not trigger for campaign planning or creative generation without performance data.
40k80 tok idle · 3,472 in use - add-educational-commentsgithub/awesome-copilot
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.
40k27 tok idle · 1,301 in use - adobe-illustrator-scriptinggithub/awesome-copilot
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.
40k80 tok idle · 8,741 in use - agent-architecturegithub/awesome-copilot
Design AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only; excludes implementation and general code review.
40k32 tok idle · 1,816 in use