CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creation-walkthrough

Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not triggering or not loading the right context, when you are auditing a skill that is underperforming, or when you want to publish a skill for others. Also triggers when someone asks "how do I make a skill" or "what makes a good skill". Useful for individuals, teams, and anyone publishing skills publicly.

86

1.24x
Quality

Does it follow best practices?

Impact

98%

1.24x

Average score across 2 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

96%

33%

Package a Recurring Report Workflow as a Claude Skill

Skill creation with 6-artifact output and 4-part description formula

Criteria
Without context
With context

Trigger analysis delivered

42%

85%

Description draft delivered

85%

100%

SKILL.md body delivered

100%

100%

Reference plan delivered

71%

85%

Reference file written end-to-end

100%

100%

Test plan with trigger prompts

100%

100%

Test plan with non-trigger prompts

0%

100%

4-part description: verb-led action

100%

100%

4-part description: trigger phrases

0%

100%

4-part description: Also triggers when

0%

100%

4-part description: Useful for

0%

100%

Standard SKILL.md structure

100%

100%

When NOT to use cross-references

0%

60%

Reference files listed in SKILL.md

80%

100%

Reference file is standalone

100%

100%

Reference file naming convention

75%

100%

SKILL.md under 250 lines

100%

100%

Methodology-pure content

100%

100%

100%

4%

Diagnose and Fix a Skill That Isn't Triggering

Skill description diagnosis and fix

Criteria
Without context
With context

Verb-led first sentence

60%

100%

Primary triggers present

100%

100%

User vocabulary in triggers

100%

100%

Also triggers when clause

100%

100%

Useful for clause

100%

100%

Multi-sentence description

100%

100%

Diagnosis identifies vagueness

100%

100%

Test plan trigger prompts

100%

100%

Test plan non-trigger prompts

100%

100%

Output to correct file

100%

100%

Repository
rampstackco/claude-skills
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.