AI-Graded Content Validation
Large question banks authored by multiple sources (human or AI) accumulate factual errors that are invisible to structur...
28 lessons
Large question banks authored by multiple sources (human or AI) accumulate factual errors that are invisible to structur...
When humans author multiple-choice questions, the correct answer tends to cluster in certain positions (often B or C). T...
A structured review skill turns the ad-hoc "look at this code and tell me what's wrong" request into a repeatable, evide...
A Claude Code skill file is a structured prompt that turns a repeatable workflow into a single slash command. The skill'...
A phased plan is only as good as its execution discipline. A /phase skill automates the mechanical parts of plan executi...
When hundreds of data records need the same type of update (adding titles, categories, tags, or enriched descriptions), ...
localStorage can serve as a full persistence layer for client-side applications when the data is user-specific, the data...
A whole-codebase code review is only as valuable as the remediation that follows it. The review itself produces a findin...
When you have hundreds or thousands of content items authored by different sources at different times, quality varies wi...
A Content Security Policy (CSP) is achievable on a static site without server-side headers by using a <meta> tag. The ch...
Migrating an existing multi-page site to a design system is a page-by-page operation, not a big-bang rewrite. The design...
Writing a design document and a Physical Design Requirements (PDR) document before coding catches architectural mistakes...
When migrating a data format (XML to JSON) that feeds a rendering pipeline, the only way to prove the migration is corre...
A progressive hint system (brief nudge → full explanation → deep-dive knowledge) is more pedagogically effective than a ...
A browser-based application that uses DOM APIs (querySelector, innerHTML, addEventListener) can be integration-tested in...
After a migration, the old system's artifacts (files, code, tests, scripts) must be actively removed in a deliberate cle...
Systematically extracting lessons from project work — and writing them as standalone documents — turns ephemeral experie...
Breaking large features into ordered phases — each independently shippable, each ending with a commit — transforms ambit...
When a system needs to support multiple "providers" (vendors, brands, data sources) that share the same behavior but dif...
Adding 50+ exams across 10 providers to a quiz application required zero changes to the core quiz engine, data loader, o...
Adding runtime schema validation to your data loading layer catches entire categories of bugs that would otherwise surfa...
When multiple people or processes author data files for the same system without a shared schema, variant schemas emerge....
A full-featured application (quiz engine, progress persistence, scoring, results dashboards, 10 providers, 50+ exams) ca...
When critical logic is embedded in a class that's hard to test (DOM-coupled UI class), developers sometimes copy the log...
When hints contain the exact text of the correct answer choice, they short-circuit learning. The learner reads the hint,...
XML entity encoding bugs (Q&A vs Q&A) are the most common class of data corruption in XML content pipelines. They're...
When migrating a live data format (XML to JSON), the key risk is not the conversion itself — it's proving that the new f...
Using innerHTML to render content from "your own" data files (XML, JSON, markdown) is an XSS vulnerability even when the...