CtrlK
BlogDocsLog inGet started
Tessl Logo

fusion-skill-authoring

Creates or modernizes repository skills with clear activation cues, purposeful support files, and practical review loops. USE FOR: creating a new skill, tightening an existing skill, improving discovery wording, and structuring references/assets/optional helper agents when they genuinely add value. DO NOT USE FOR: product-code changes, routine copy edits outside skills/, or documentation that should not become an installable skill.

78

1.25x
Quality

81%

Does it follow best practices?

Impact

59%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Evaluation results

70%

14%

Add Hotfix Release Support to the Release Notes Skill

APM-installed skill provenance check

Criteria
Without this skill
With this skill

Inspects apm.yml

100%

100%

Inspects apm.lock.yaml

100%

100%

Names external source

100%

100%

SKILL.md left unchanged

0%

0%

States edit was not made

0%

0%

Offers upstream alternative

40%

100%

Explains overwrite risk

12%

100%

No invented validation

100%

100%

100%

63%

PR Description Automation Skill

New skill authoring with naming convention and authoring report

Criteria
Without this skill
With this skill

custom- prefix naming

0%

100%

Name matches folder

100%

100%

Valid name format

100%

100%

Description USE FOR / DO NOT USE FOR

0%

100%

Version 0.0.0

0%

100%

Tags lowercase kebab-case

0%

100%

All required sections present

0%

100%

Concrete example included

12%

100%

SKILL.md under 300 lines

100%

100%

Three representative requests documented

60%

100%

Skill classification stated

62%

100%

Minimum folder structure

0%

100%

Authoring report is explicit contract

100%

100%

8%

-40%

Skill Quality Audit: Data Pipeline Debugger

Validate and fix a poorly authored skill draft

Criteria
Without this skill
With this skill

Name field corrected

100%

0%

USE FOR cue present

0%

0%

DO NOT USE FOR cue present

0%

0%

Expected output section added

0%

0%

Safety & constraints section added

0%

0%

Fixed SKILL.md under 300 lines

0%

0%

Overflow moved to references/

75%

0%

Concrete example present

25%

100%

References one level deep

100%

0%

findings.md severity ordering

100%

0%

findings.md validation evidence

100%

0%

Repository
equinor/fusion-framework
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.