Make sense of your workflow
Learn how to choose, install, and evaluate skills, then build a practice that works for you.
Gemini Python SDK: request, polling and streaming checks
Test a Gemini API integration by separating SDK request handling from live model behavior. This guide records six unchanged Python examples from the Google Gemini skill…
By GX AI · Read guide →Practical guideChoose AI skills by task, output and required access
Choose an AI skill by the job it performs, the artifact you need and the access it requires. Similar labels can hide very different workflows, costs and effects on external…
By GX AI · Read guide →Practical guideTanStack Router and Query: preload, cache and SSR checks
When TanStack Router delegates fetching to TanStack Query, two caches can affect the same navigation. A repeated preload can stop at Router before it reaches Query, while a static…
By GX AI · Read guide →Practical guideAstro contributor checks: runtime boundaries and isolated builds
Check Astro contributor guidance with real lint and build evidence: distinguish Node API boundaries, runnable examples, shallow immutability and separate build outputs.
By GX AI · Read guide →Practical guideSvelte 5 reactivity: props, keyed lists and browser evidence
Debug Svelte 5 reactivity with a version-pinned official skill: distinguish compiler diagnostics from browser behavior, test changing props and verify keyed DOM identity.
By GX AI · Read guide →Practical guidePostgreSQL RLS tests: roles, writes and session context
PostgreSQL row-level security needs tests that use the same ordinary database roles as the application. A successful query from a superuser cannot establish that another user's…
By GX AI · Read guide →Practical guideFastAPI API contracts: response filtering and dependency tests
Test FastAPI's public response contracts with local examples: reject invalid input, detect direct-response bypasses, isolate dependency overrides and check when yield cleanup runs.
By GX AI · Read guide →Practical guidePydantic API models: preserve partial updates and reject invalid input
A Pydantic skill can help an agent draft API models, but a working class does not settle the meaning of a partial update. This guide uses a pinned Microsoft template and a small…
By GX AI · Read guide →Practical guideTest Playwright CLI skills while keeping your browser session
Start a browser skill review with a local page and an explicitly chosen browser session. Our Playwright CLI experiment completed 15 named observations: form controls, snapshot…
By GX AI · Read guide →Practical guideChoose frontend, artifact and browser-testing AI skills
Choose an AI skill by the deliverable you need: a web interface, a portable HTML artifact, a static visual or a browser test. This guide compares six Anthropic skill packages in…
By GX AI · Read guide →Practical guideTest Redis cache expiry and ACL boundaries before shipping
Test Redis cache expiry and ACL boundaries before shipping. Our disposable Redis fixture checked data types, TTL updates, conflicting writes, key-name visibility and connection…
By GX AI · Read guide →Practical guideRead WordPress diagnostic reports before changing a site
Read a WordPress diagnostic report before changing a site. Our disposable WordPress fixture exposed misleading autoload totals and default-path assumptions, then checked a revised…
By GX AI · Read guide →Practical guideTest WordPress REST skills with roles and real HTTP
Test a WordPress REST API skill with explicit user roles, invalid parameters and observable responses. Our isolated WordPress 7.1.2 fixture recorded 27 HTTP observations…
By GX AI · Read guide →Practical guideReview property-testing skills with real counterexamples
Review a property-testing skill by the guarantees its tests can falsify, the inputs it actually generates, and the failures it can explain. A large example count is useful…
By GX AI · Read guide →Practical guideInspect Python tooling skills before changing a project
Inspect a Python tooling skill before changing an existing project. A useful review separates the instruction files, tool versions, dependency model, migration cleanup and…
By GX AI · Read guide →Practical guideReview PostgreSQL RLS across roles, views and functions
Review PostgreSQL row-level security with separate database logins and a disposable fixture before trusting an agent's access-control checklist. Our recorded experiment shows how…
By GX AI · Read guide →Practical guideReview PostgreSQL query plans with a least-privilege fixture
Review a PostgreSQL query plan with a small, least-privilege fixture before treating an agent's recommendation as a production change. This guide uses recorded local observations…
By GX AI · Read guide →Practical guideChoose development skills by task, source and evidence
Choose development skills by the task you need to complete. A catalog category can narrow a search, but the original instructions, required tools and evidence for the current…
By GX AI · Read guide →Practical guideReview GitHub Actions changes with an agent skill
Review GitHub Actions changes with an agent skill, preserve required checks, and separate local syntax evidence from measured CI improvements.
By GX AI · Read guide →Practical guideAudit a website with agent skills and an evidence log
Use agent skills to organize a website audit around reproducible observations: what a visitor tried, what happened, where the evidence is and how to verify a fix. A polished…
By GX AI · Read guide →Practical guideReview and commit a small change with an agent skill
Use an agent skill to organize a small local change, while keeping the decision to commit grounded in a diff you can inspect. The Git Commits with Conventional Messages resource…
By GX AI · Read guide →Practical guideAnalyze local CSV data with DuckDB agent skills
DuckDB skills can help an agent turn a data question into SQL against files on your own machine. The result still needs checking: start with a small, non-sensitive fixture…
By GX AI · Read guide →Practical guideRepeat homepage timing sample: October 3, 2026
On October 3, 2026, a repeat six-load observation of bb.fouho.com recorded desktop TTFB values of 884.6, 433.1 and 240.9 ms. This log is tied to the revised Cloudflare Web…
By GX AI · Read guide →Practical guideHomepage timing baseline: October 2, 2026
On October 2, 2026, six loads of bb.fouho.com recorded a first desktop TTFB of 865.2 ms, followed by 255.2 and 280.8 ms. This initial three-second observation used the original…
By GX AI · Read guide →Practical guideA practical checklist for installing skills
Read SKILL.md and any scripts before running them. Check that requested permissions match the task.
By GX AIRead guide →Practical guideWhat makes a useful agent skill?
A good skill turns a repeated task into a clear workflow. It names inputs, defines the output, checks its work, and documents dependencies.
By GX AIRead guide →