CtrlK
BlogDocsLog inGet started
Tessl Logo

mcollina/skill-optimizer

Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark and release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.

87

1.14x
Quality

87%

Does it follow best practices?

Impact

87%

1.14x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-1/

Improve a Poorly-Activating Database Migration Skill

Problem/Feature Description

Your platform team has written a skill called db-migrations to help engineers safely write and apply database schema migrations. After running evals, you've discovered that models frequently ignore key safety rules from the skill: they omit the required rollback section in migration scripts, they miss backward-compatibility checks, and on noisy tasks (where there's a lot of context already in the prompt), the skill's guidance stops applying at all.

A junior engineer on the team wrote the original skill file in a hurry. Looking at it, it's hard to tell at a glance what's mandatory vs optional, critical rules are buried deep in a long document, and the only example in the file is a trivial toy that doesn't reflect the kind of migrations engineers actually write. Your job is to rewrite the skill so it activates reliably and gets followed.

Output Specification

Produce a rewritten skill file called SKILL-improved.md. You should also write a short file improvement-notes.md that explains the specific structural and content changes you made and why.

Input Files

The following files are provided as inputs. Extract them before beginning.

=============== FILE: inputs/SKILL-original.md ===============

name: db-migrations description: Guides safe database schema migration authoring and application.

Database Migration Guide

Database migrations are important and need to be done carefully. When you're working with database schema changes you should think about backwards compatibility. It's also good to include rollback steps, though sometimes that's not always needed.

Writing migrations

When writing a migration you may want to use the project's migration framework (Alembic for Python projects, Flyway for Java).

Consider adding a -- rollback section at the bottom of your SQL file.

Safety checks

Before applying a migration you might want to check:

  • Does the migration break existing queries?
  • Are there any long-running locks?
  • Does the application still work with both old and new schema?

Example

ALTER TABLE users ADD COLUMN email_verified BOOLEAN;

Deployment

Apply migrations during low-traffic windows. It's generally a good idea to test first.

evals

scenario-1

criteria.json

task.md

SKILL.md

tile.json