agentic-eval SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

agentic-eval from practicalswan/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add practicalswan/agent-skills/agentic-eval@v2.0

Pins v2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
practicalswan/agent-skills
Path
agentic-eval/SKILL.md
Versions recorded
5
Latest version
v2.0, committed Sep 7, 2026
First version recorded
Aug 24, 2026
Size
8,486 bytes
Repository stars
24
License
MIT

Evaluate and improve AI-generated output with explicit rubrics, reflection loops, and stop conditions. Use when building self-critique workflows, evaluator-optimizer pipelines, or acceptance gates for code, docs, analysis, or plans.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agentic Evaluation Patterns

Patterns for self-improvement through iterative evaluation and refinement.

## Overview

Evaluation patterns enable agents to assess and improve their own outputs, moving beyond single-shot generation to iterative refinement loops.

```
Generate → Evaluate → Critique → Refine → Output
    ↑                              │
    └──────────────────────────────┘
```

## When to Use

- **Quality-critical generation**: Code, reports, analysis requiring high accuracy
- **Tasks with clear evaluation criteria**: Defined success metrics exist
- **Content requiring specific standards**: Style guides, compliance, formatting

---

## Pattern 1: Basic Reflection

Agent evaluates and improves its own output through self-critique.

```python
def reflect_and_refine(task: str, criteria: list[str], max_iterations: int = 3) -> str:
    """Generate with reflection loop."""
    output = llm(f"Complete this task:\n{task}")

    for i in range(max_iterations):
        # Self-critique
        critique = llm(f"""
        Evaluate this output against criteria: {criteria}
        Output: {output}
        Rate each: PASS/FAIL with feedback as JSON.
        """)
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ucokokm6iqpjq5hn/2255d2a78263550edec192887e96b934f772c86196620922963cbe44d9a8c018.json

Then /plugin install agentic-eval@markdownregistry-ucokokm6iqpjq5hn in Claude Code. It installs v2.0, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add practicalswan/agent-skills/agentic-eval@sha256:2255d2a78263550e

The line at the top of this page pins the label v2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ucokokm6iqpjq5hn.svg)](https://markdownregistry.com/a/art_ucokokm6iqpjq5hn)

3 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in practicalswan/agent-skills/agentic-eval since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of agentic-eval from somewhere else? Ask it: where did my agentic-eval come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Aug 24, 2026 and Sep 7, 2026, about one every 4 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
v2.0 latest2026-09-07 afbb609 8,486 BA view · diff
v2.02026-09-05 da1f686 6,947 BA view · diff
v2.02026-08-31 4069d99 6,947 BA view · diff
v2.02026-08-29 f108298 6,947 BA view · diff
v2.02026-08-24 4d12f29 6,947 BA view

Copies

Copies in other repositories

1 file in 1 other repository holds the exact bytes of one of this file's versions, each committed after this file had them: it holds the newest version.

A copy does not update when this file does. Whoever holds one can learn which version it is with the Check your copy box below, or by asking their agent. Matched on exact bytes and commit dates only.

Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8486 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

practicalswan/agent-skills · 24 stars · license MIT · pushed 2026-11-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ucokokm6iqpjq5hn
GET https://markdownregistry.com/api/v1/resolve?ref=practicalswan/agent-skills/agentic-eval
GET https://markdownregistry.com/api/v1/blob/2255d2a78263550edec192887e96b934f772c86196620922963cbe44d9a8c018

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from practicalswan/agent-skills

AGENTS.md AGENTS.md file
practicalswan/agent-skills · AGENTS.md
git:20261116.1d800c8 · audit A · 24 stars
CLAUDE.md CLAUDE.md file
practicalswan/agent-skills · CLAUDE.md
git:20261116.1d800c8 · audit A · 24 stars
accelerated-computing-cudf SKILL.md skill
practicalswan/agent-skills · accelerated-computing-cudf/SKILL.md · Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby…
v2.0 · audit A · 24 stars
accessibility SKILL.md skill
practicalswan/agent-skills · accessibility/SKILL.md · Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y…
v2.0 · audit A · 24 stars
agent-skillguard SKILL.md skill
practicalswan/agent-skills · agent-skillguard/SKILL.md · Use before installing an agent skill or plugin. Scan local files for risky instructions, broad permissions, suspicious…
v2.0 · audit A · 24 stars
agent-task-mapping SKILL.md skill
practicalswan/agent-skills · agent-task-mapping/SKILL.md · Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to…
v2.0 · audit A · 24 stars
ai-writing-detector SKILL.md skill
practicalswan/agent-skills · ai-writing-detector/SKILL.md · Use when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including…
v2.0 · audit A · 24 stars
avoid-ai-writing-router SKILL.md skill
practicalswan/agent-skills · avoid-ai-writing-router/SKILL.md · Use when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation…
v2.0 · audit A · 24 stars
avoid-ai-writing SKILL.md skill
practicalswan/agent-skills · avoid-ai-writing/SKILL.md · Audit and rewrite content to remove AI writing patterns ("AI-isms"). Supports detect-only audits, edit-in-place file…
v2.0 · audit A · 24 stars
azure-integrations SKILL.md skill
practicalswan/agent-skills · azure-integrations/SKILL.md · Azure deployment for web apps — Static Web Apps, App Service, Blob Storage, Bicep/ARM, GitHub Actions CI/CD. Use when…
v2.0 · audit A · 24 stars
best-practices SKILL.md skill
practicalswan/agent-skills · best-practices/SKILL.md · Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply…
v2.0 · audit B · 24 stars
brainstorming SKILL.md skill
practicalswan/agent-skills · brainstorming/SKILL.md · Interactive idea refinement using Socratic method to develop fully-formed designs
v2.0 · audit A · 24 stars

Every file in practicalswan/agent-skills

Other files named agentic-eval

agentic-eval SKILL.md skill
github/awesome-copilot · skills/agentic-eval/SKILL.md · Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing…
git:20260119.3d00ec4 · audit A · 41,309 stars
agentic-eval SKILL.md skill
sandbaseai/sandbase-skills · marketing/agentic-eval/SKILL.md · Plan, implement, or review agentic eval work in an existing codebase with compatibility, security, and verification…
git:20260908.a887321 · audit A · 212 stars
agentic-eval SKILL.md skill
skillmds/skillmd · plugins/build-multi-agent-system-with-crewai/skills/agentic-eval/SKILL.md · Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing…
git:20260919.fecc0d5 · audit A · 144 stars
agentic-eval SKILL.md skill
jpeetz/agent-skills · skills/ai-agent-engineering/agentic-eval/SKILL.md · Use this skill when setting up or improving evaluation for AI agents and LLM outputs. Activates on "agent eval", "LLM…
v1.0.0 · audit A · 17 stars
agentic-eval SKILL.md skill
bg-szy/top-skills · skills/agent-skills/agentic-eval/SKILL.md · Evaluate and improve AI-generated output with explicit rubrics, reflection loops, and stop conditions. Use when…
v2.0 · audit A · 6 stars
agentic-eval SKILL.md skill
fabioc-aloha/alex_skill_mall · plugins/ai-agents/agentic-eval/skills/agentic-eval/SKILL.md · Patterns for agent self-improvement through iterative evaluation and refinement -- generate, evaluate, critique, refine…
git:20260728.80a7ab6 · audit A · 5 stars
agentic-eval SKILL.md skill
pr-e/openclaw-master-skills · skills/agentic-eval/SKILL.md · Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing…
git:20260302.9834b38 · audit A · 4 stars
agentic-eval SKILL.md skill
marielynneblock/arcanum-artifex · skills/agentic/agentic-eval/SKILL.md · Use when designing and implementing evaluation loops for AI agents, including reflection, evaluator-optimiser patterns…
git:20260624.0a2f9fa · audit A · 4 stars

Browse by kind, by grade A, or by owner.