CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-template

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.

Install with Tessl CLI

npx tessl i github:muratcankoylan/Agent-Skills-for-Context-Engineering --skill skill-template
What are skills?

63

1.35x

Quality

47%

Does it follow best practices?

Impact

91%

1.35x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./template/SKILL.md
SKILL.md
Review
Evals

Evaluation results

83%

55%

New Skill: Git Workflow Management

Skill file structure and metadata

Criteria
Without context
With context

SKILL.md line count

100%

100%

Third-person activation

0%

100%

Direct triggers present

0%

100%

Indirect signals present

0%

50%

References subfolder used

100%

100%

Integration as plain text

0%

100%

Metadata section complete

0%

100%

Guidelines verifiable

53%

100%

Examples use input/output

0%

0%

Without context: $0.3356 · 1m 24s · 16 turns · 555 in / 4,423 out tokens

With context: $0.3086 · 1m 30s · 13 turns · 269 in / 4,415 out tokens

100%

Refactor Bloated Skill Documentation

Content economy and token efficiency

Criteria
Without context
With context

Third-person activation

100%

100%

Trivial HTTP content removed

100%

100%

JSON basics removed

100%

100%

Content moved to references

100%

100%

Freedom levels in guidance

100%

100%

Strict rules clearly marked

100%

100%

Guidelines verifiable

100%

100%

Removal rationale documented

100%

100%

Without context: $0.3246 · 1m 31s · 13 turns · 14 in / 4,740 out tokens

With context: $0.5077 · 1m 58s · 23 turns · 71 in / 6,033 out tokens

90%

17%

New Skill: Database Migration Workflow

Practical guidance specificity and examples

Criteria
Without context
With context

Third-person activation

30%

60%

Direct triggers present

37%

100%

Indirect signals present

0%

50%

Freedom levels used

66%

100%

Low-freedom rules distinct

100%

100%

Examples input/output format

83%

83%

Integration plain text

100%

100%

References subfolder linked

100%

100%

Guidelines specific

100%

100%

Without context: $0.3813 · 1m 56s · 14 turns · 503 in / 5,909 out tokens

With context: $0.3530 · 2m 3s · 14 turns · 13 in / 6,112 out tokens

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.