CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-skills

Learn about Agent Skills - how AI agents use skills, create new skills, and understand skill discovery in real-time. Use when user asks about skills, wants to create a skill, or wants to understand how Claude uses skills.

65

1.44x
Quality

47%

Does it follow best practices?

Impact

100%

1.44x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/agent-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

48%

Automate the Nightly Production Deploy Checklist

Workflow skill creation with correct structure

Criteria
Without context
With context

Valid skill name

20%

100%

Name-directory match

0%

100%

Required frontmatter: name

0%

100%

Required frontmatter: description

100%

100%

Description formula

70%

100%

Project-local placement

20%

100%

Explicit bash commands

100%

100%

Verification section

100%

100%

Rollback section

41%

100%

Prerequisites section

0%

100%

SKILL.md under 500 lines

100%

100%

100%

23%

Set Up a Guided Local Development Environment Skill

Interactive skill with Ask/Say patterns

Criteria
Without context
With context

Valid skill name

100%

100%

Name-directory match

50%

100%

Required frontmatter fields

100%

100%

Description formula

87%

100%

Ask: prefix for prompts

66%

100%

Say: prefix for explanations

16%

100%

Wait for response

90%

100%

Branching logic

100%

100%

Success wrap-up

70%

100%

Troubleshooting section

100%

100%

Project-local placement

100%

100%

100%

22%

Fix a Skill That Claude Can No Longer Discover

Audit and fix a poorly-structured skill

Criteria
Without context
With context

Fixed name format

100%

100%

No invalid name characters

100%

100%

Name-directory match

100%

100%

Improved description

100%

100%

Bulk content in references/

0%

100%

Fixed SKILL.md under 500 lines

100%

100%

Relative reference paths

0%

100%

Required frontmatter present

100%

100%

Correct skill placement

100%

100%

Audit report identifies name issue

100%

100%

Repository
runpod/lazy-agent
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.