Agent Skills by makyua-san
Showing 36 vetted skills indexed across 1 GitHub repositories.
benchmark
Compare current web page metrics against baselines to detect performance regressions.
design-html
Generate production-ready HTML and CSS from approved design documents.
design-shotgun
Generate multiple AI design variants for UI, branding, and layout concepts.
plan-design-review
Identify and fill missing design decisions in a PLAN before execution.
autoplan
Automates review of project plans by sequencing four expert AI personas.
design-consultation
Generate DESIGN.md with typography, color, spacing, and motion tokens.
crawl4ai
Crawl websites to extract structured data and generate Markdown or JSON outputs.
learn
Query and manage team learnings from a centralized JSONL store.
freeze
Restrict Edit and Write operations to a specified directory for a session.
checkpoint
Capture git state, decisions, and remaining tasks for session resume.
careful
Warns before destructive Bash commands and requires explicit user override.
cso
Audit infrastructure security posture and generate a Security Posture Report with severity ratings.
canary
Monitor production deployments for console errors, performance regressions, and page failures.
open-gstack-browser
Launch a headed Chromium browser with a live activity feed and sidebar chat.
investigate
Identifies and documents root causes of bugs from error reports and stack traces.
document-release
Synchronize and polish project documentation after code shipments.
health
Aggregate type-check, lint, test, dead code, and shell outputs into a 0-10 health score.
gstack-upgrade
Upgrade gstack installations with migrations and vendored copy sync.
land-and-deploy
Automates Git-based PR merge, CI wait, production deploy, and canary health checks.
codex
Evaluate Codex CLI outputs for safety and effectiveness.
qa
Run tiered QA tests on web applications and commit atomic fixes.
qa-only
Execute automated checks and manual validation on web apps to generate structured QA reports.
setup-browser-cookies
Import Chromium browser cookies into a Playwright session.
review
Analyze code diffs for SQL safety and LLM trust boundary issues.