sg-technical

Use one explicit technical mode for code risk, dependencies, performance, or a breaking migration.

A unified technical entrypoint with four bounded modes and evidence limits that match the work.

Problem

What problem this solves

Code, dependency, performance, and migration work is related, but each needs different evidence and mutation safeguards.

Outcome

What changes when it works

You choose one explicit mode and receive a specialist audit or migration plan without silently running unrelated technical lanes.

Why It Matters

What this changes for a solo founder

One entrypoint reduces command noise while keeping security, supply-chain, measurement, and rollback discipline visible.

When to use it

Use audit for code correctness, architecture, security, reliability, or test posture
Use deps for vulnerabilities, supply chain, licenses, drift, lockfiles, or package configuration
Use performance for bundles, rendering, loading, fetching, caching, or database efficiency
Use migrate for a researched breaking framework or package upgrade

What you give it

One explicit mode: audit, deps, performance, or migrate
A file, project, global scope, or package target as accepted by that mode

What you get back

Severity-ranked technical findings with named evidence limits
A dependency or performance posture that distinguishes checked facts from unknowns
A migration matrix and safe apply plan before any approved mutation

Typical examples

/010-sg-technical audit src/lib/auth.ts
/010-sg-technical deps global
/010-sg-technical performance src/pages/index.astro
/010-sg-technical migrate astro@6

Limits

Audit, deps, and performance are read-only by default; findings do not authorize fixes
Static or partial evidence is not a security sign-off, measured bottleneck, or production proof
Migration requires current official guidance, distinct apply approval, safe dirty-state handling, rollback, and checks
Broad audits, proportional checks, production truth, SEO, and translation remain separate owner skills

Related Skills

See the rest of the loop around this move.

Audit & Improve

sg-audit

Run a broad project audit when you need a high-level map of what is weak before you decide what to fix.

The top-level audit skill scans across multiple quality domains so you can see where the real risk or drift sits.

Open skill page

Operate & Ship

sg-check

Run the standard technical checks and fix the obvious issues before you pretend the work is done.

A practical quality gate for typecheck, lint, build, and related technical validation in the current project.

Open skill page

Operate & Ship

sg-prod

Check whether production is actually healthy after a push instead of assuming the deploy tells the truth.

A production verification skill for deployment status, logs, and live health checks after release.

Open skill page

Audit & Improve

sg-seo

Check whether the site is set up to earn search visibility in the current AI and SEO environment.

A technical and on-page SEO audit for discoverability, crawlability, content structure, and AI-era visibility signals.

Open skill page

Audit & Improve

sg-audit-translate

Review whether translations are complete, consistent, and trustworthy, then sync missing localized content when the mapping is clear.

A translation audit and controlled i18n sync skill for completeness, tone consistency, cross-language coherence, and missing localized entries.

Open skill page

Go Deeper

This public page explains the move. The repository explains the execution contract.

Use the public catalog for education and workflow selection. Move to the docs and GitHub when you want the operator-grade execution details behind the skill system.

Documentation Overview Open skills on GitHub Return to the skills hub