adewale Skills

Use this skill to review, tighten, draft, and rewrite prose so it does not read like generic LLM output, AI writing, bland marketing, or generic launch copy. Apply it when the user asks to make writing less generic/AI-sounding, tighten a talk intro, sharpen presentation/slide copy, or improve articles, wiki pages, README text, emails, posts, scripts, product/DevRel copy, launch copy, and other important writing with AI tropes, inflated significance language, generic cadence, weak flow, or marketing fog.

> Help users prepare and review pull requests that maintainers actually want to merge. Use this skill whenever someone asks for help writing a PR description, preparing a contribution to an open-source project, reviewing their own PR before submitting, writing a bug fix PR, drafting a feature PR, or asks anything like "how do I make a good pull request", "review my PR", or "why do my PRs keep getting rejected". Also trigger when a user shares a diff or patch and wants help presenting it, when they mention contributing to a repo they don't maintain, when they're preparing their first contribution to a project, or when they want a pre-submission sanity check. Even if the user doesn't explicitly mention "PR" — if they're packaging a code change for someone else to review, this skill applies.

Create, improve, or audit README.md documents for GitHub projects. Use only when the user explicitly asks for a README, README quality/readability, README accuracy, or README examples. Do not use for full docs sites, API-reference-only work, general repo launch/readiness audits, topics/homepage metadata, or broad repository review.

> repo quality/adoption/trust, discoverability, contribution readiness, topics, homepage URL, description, issues/wiki/license/CI settings, owner/org-wide repo audits, repo popularity/adoption signals, README/package/GitHub metadata drift, URL/license/topics gaps, and Agent Skill repo packaging/evals. Use when the user asks for repo-level readiness, repo metadata/configuration, or visitor/contributor trust. Do not trigger for README-only writing, one PR descriptions/reviews, function-level code tests, or general implementation/architecture work; defer those to narrower specialists unless the user explicitly asks for repo-level readiness/proof/metadata judgment.

> Code quality verification gates wired into the agent lifecycle. Use this skill whenever writing, modifying, reviewing, or debugging code — including new features, bug fixes, refactors, troubleshooting, CI/CD setup, or project bootstrapping. Also use when the user mentions "quality", "testing strategy", "CI pipeline", "guardrails", "debugging", or asks how to improve code reliability. If you're writing code or trying to understand why code isn't working, this skill applies. Do not use for README/prose-only edits, copywriting, or documentation wording changes unless the user asks for code/build/CI verification or the docs change affects generated/runtime output.

Apply a Swiss Poster design system using Tailwind CSS. Use when asked to style a webpage with poster-style layouts where one dominant graphic event breaks the grid, overlaps, bleeds/crops at the edge, uses microtype, hard figure/ground contrast, and extreme typographic scale. Implements IBM Plex Sans, stone color palette, opacity hierarchy, and compositional techniques from Weingart, Troxler, Hofmann, and Odermatt & Tissi.

> Enforce testing best practices when writing, reviewing, or improving tests. Covers TDD/red-green-refactor, property-based testing, real objects over mocks, correctness by construction, assertion quality, E2E/contract tests, flaky-test upgrades, mock-reality drift, mutation-style gap analysis, and sabotaged/skipped/weak tests. Use when writing tests, reviewing test quality, fixing flaky tests, improving coverage quality, or when the user mentions TDD, testing, coverage, mocks, invariants, types vs tests, defense in depth, or test quality.