agent-skills

Create or update privacy policy drafts and privacy pages for SaaS products, websites, mobile apps, APIs, platforms, and digital products by inspecting installed packages, SDKs, app code, backend routes, forms, databases, analytics, auth, payments, ads, crash reporting, AI services, storage, email, maps, push notifications, and user-provided data collection details. Use when users ask to write a privacy policy, create PRIVACY.md, draft a privacy page, explain what data is collected, disclose why data is collected, identify third-party sharing, define retention and deletion processes, or audit product data practices for a privacy notice.

Create or update Terms of Use, Terms of Service, or user agreement drafts for SaaS products, platforms, apps, marketplaces, APIs, and digital products by inspecting the current codebase, README, docs, pricing, auth, billing, user-content, and product functionality. Use when users ask to write terms, terms of use, terms of service, legal terms, platform rules, subscription/payment terms, cancellation/refund policies, acceptable use rules, IP/user-content clauses, liability limits, suspension rules, or to create an in-app Terms page.

Create or update a project-level BRANDING.md for apps and digital products, focusing on emotional identity, visual identity, color direction, shape language, typography, UI tone, iconography, illustration style, brand metaphors, product copy, and design do/don't rules. Use when users ask to create a brand guide, define app branding, document product identity, generate BRANDING.md, convert product context into brand direction, or align designers, developers, copywriters, and AI coding agents around a practical visual and emotional brand system.

Create an English-only DESIGN.md that translates brand strategy and project context into practical, implementation-ready design direction for product UI, landing pages, visual systems, and AI coding agents. Use when users ask to create, update, or improve DESIGN.md; define visual direction for an app, website, SaaS, product, landing page, or design system; convert BRANDING.md into usable UI rules; or produce design tokens, palettes, component rules, responsive guidance, motion, and accessibility standards.

Automate semantic version releases across project types by detecting version files, bumping versions, updating changelogs, creating git tags, and optionally publishing GitHub releases. Use when users ask to cut a release, bump the version, prepare a new version, tag a release, update the changelog for a release, or publish a GitHub release.

Audit Python codebases for security, performance, correctness, and architecture antipatterns. Run optional trusted runtime checks (syntax, tests, lint, typing) plus static rule scans, then output a 0-100 health score with actionable fixes. Use when users ask to inspect a Python project, run a Python health check, review backend code quality, or perform a pre-release audit.

Audit Django codebases for security, performance, correctness, and architecture antipatterns. Run system checks, migration drift checks, and static rule scans, then output a 0-100 health score with actionable fixes. Use when users ask to scan a Django backend, run a Django health check, review backend code quality, or perform a pre-deploy audit.

Verify Dockerfiles and Docker Compose manifests for security issues, reliability risks, optimization opportunities, syntax errors, and misconfiguration before builds or deploys. Run deterministic checks (`scripts/verify-docker.sh`, `docker compose config -q`, optional `hadolint`) and produce a 0-100 health score with prioritized fixes. Use when users ask to validate Dockerfile(s), docker-compose/compose YAML files, harden container configuration, optimize image/runtime setup, debug configuration failures, or run a pre-deploy Docker audit.

Review Python dependencies for known security advisories, stale version pins, and unsafe upgrade paths. Use when users ask for dependency security reviews, requirements or lockfile audits, upgrade planning, pre-release risk checks, or remediation prioritization for Python projects.

Optimize Django ORM performance by detecting N+1 query patterns, missing `select_related`/`prefetch_related`, and likely index gaps. Run targeted static scans, optional runtime query capture, and produce a prioritized remediation plan with expected query-count impact. Use when users ask to speed up Django endpoints, reduce database hits, investigate slow views/serializers, or audit QuerySet efficiency before release.

Create Git commit messages that conform to Conventional Commits 1.0.0, including type/scope/description format, optional body, trailer-style footers, and explicit BREAKING CHANGE signaling. Use when users ask to draft commit messages, commit current changes, rewrite a commit message into conventional format, or enforce conventional commit standards in a repo.