CtrlK
BlogDocsLog inGet started
Tessl Logo

load-skill

Load, activate, and optionally install an AI skill from a .skill file. Use this skill when the user wants to load, activate, or use a skill file. The user can invoke this skill with slash command `/load-skill [ --install | -i ] SKILLFILE`, where SKILLFILE is the path to a .skill file.

Install with Tessl CLI

npx tessl i github:fpl9000/ai-skills --skill load-skill
What are skills?

89

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

80%

Text Summarization with a Packaged Skill

Skill extraction and activation workflow

Criteria
Without context
With context

Uses unzip to extract

100%

100%

Extracts to temp directory

100%

100%

Uses -o flag with unzip

100%

100%

Locates SKILL.md

100%

100%

Reads entire SKILL.md

100%

100%

Activates the skill

100%

100%

Validates .skill extension

0%

0%

Temp directory cleanup

0%

0%

Correct skill identified

100%

100%

Without context: $0.2908 · 1m 5s · 21 turns · 89 in / 3,785 out tokens

With context: $0.3190 · 1m 24s · 19 turns · 134 in / 4,263 out tokens

92%

17%

Onboarding a New AI Skill for Permanent Use

Permanent skill installation without prompting

Criteria
Without context
With context

Recognizes install flag

0%

70%

No user prompts during install

100%

100%

Copies to skills folder

100%

100%

Uses unzip for extraction

100%

100%

Extracts with -o flag

100%

100%

Locates and reads SKILL.md

100%

100%

Activates the skill

100%

100%

Validates .skill extension

0%

0%

Cleanup of temp directory

0%

100%

Without context: $0.3286 · 1m 36s · 24 turns · 24 in / 5,364 out tokens

With context: $0.3877 · 1m 41s · 24 turns · 28 in / 4,907 out tokens

87%

20%

Analyzing Sales Data with a Packaged Analytics Skill

Scripts and references directory handling

Criteria
Without context
With context

Uses unzip for extraction

0%

100%

Extracts to temp directory with -o

0%

100%

Locates SKILL.md

100%

100%

Reads references/ files

100%

100%

Uses scripts/ contents

100%

100%

Output matches reference format

100%

100%

csv-report.txt produced

100%

100%

Activates skill correctly

83%

100%

Temp directory cleanup

0%

0%

Validates .skill file

0%

28%

Without context: $0.3699 · 1m 59s · 22 turns · 27 in / 5,218 out tokens

With context: $0.5472 · 2m 21s · 30 turns · 811 in / 6,559 out tokens

Evaluated
Agent
Claude Code

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.