explanatory-output-style
claudeAdds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
hooks
Teach from the dl-engine corpus with citations. One connector reads every subject you are assigned: prepare a concept, sweep a theme, audit the connection map, and trace a past paper question back to the lessons that teach it, every claim carrying its lesson slug and line number.
Plugin dl-engine from marketplace dinethlive in dinethlive/dl-engine-plugin. Commands read from the repo's manifest — 1 month ago.
auditAudit the bound subject's corpus for internal defects - edges pointing at slugs no lesson has, Atlas evidence quotes that no longer appear in their source lesson, lessons in no edge at all, and prerequisite topics nothing covers. Use when asked to check corpus quality, health, integrity or consisten
bloomRead a lesson, a past paper or a set of questions through the revised (2001) Bloom's taxonomy, and write questions or notes at a named cognitive level. Use when the teacher mentions Bloom, cognitive levels, higher order or lower order thinking, HOTS or LOTS, learning objectives, or asks what level a
evidenceThe provenance contract for teaching material. Use whenever answering about the bound subject or producing notes, lesson plans, questions, summaries, slides, handouts or artifacts, whether the material comes from the dl-engine corpus, from a past paper question, from a web search, or from all three.
setupConnect Claude to the dl-engine corpus, and tell the CURRENT folder which subject it is about. Use when the teacher asks to set up, connect or point a folder at a subject, to switch a folder to a different subject, or when a folder has no corpus tools yet.
sweepSweep the whole bound subject for one theme and report where it lives, how the syllabus builds it, and how the lessons connect. Use when the teacher asks a wide question across the subject rather than about one lesson, such as "where does this subject deal with X", "which lessons cover X", "how does
teachPrepare one concept or lesson to teach from the bound dl-engine subject corpus. Use when the user wants to prep, plan, outline or build material for a class, lesson, topic or concept, wants a teaching brief or lesson notes, asks what the corpus says about a concept before teaching it, or asks what s
traceTrace a past paper question back to where the syllabus teaches it. Use when the teacher names a paper question ("2023 Part II question 4", or a handle like al-ict-2025-part-i/q7), asks where a question comes from, what a question is really testing, which lesson covers it, what a student needed to kn
whatsnewShow what changed in the dl-engine plugin, and whether a newer version is available. Use when the teacher asks what is new, what changed, what version they are on, whether the plugin is up to date, or how to update it.
corpus-readerReads the bound dl-engine subject's corpus and returns cited findings instead of raw text. Use for any wide read that would otherwise fill the main context, such as several lessons at once, a term and all its variants, scouting which lessons matter before committing to them, or checking a claim acro
dl-engineconnects to: https://mcp.dlengine.xyz/mcp
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
hooks
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS
1 skill
Agent skills for Azure SQL Developer, the Azure SQL Database engine running locally in a container. Teaches your agent to run the engine, connect, migrate, scaffold, build RAG, wire CI, and go local-to-cloud, using the real Private Preview image instead of the SQL Server image.
17 skills
Teaching skill: cookbook-style walkthrough for signed audit trails on every Claude Code tool call. Cedar policy, Ed25519 receipts, offline verification, CI/CD integration, SLSA composition. Pairs with the protect-mcp runtime plugin.
1 skill
Evidence-first reading of supplied documents. Five modes (quick/deep/map/feynman/book), claim-reason-evidence decomposition, confidence labels, evidence ledger, knowledge maps, Feynman teach-back.
1 skill
Study p-hacking in econometric designs: map researcher degrees of freedom, audit a specification search with a complete ledger and null-calibrated honest p-values, replay realistic search procedures, detect p-hacking in a literature, immunise an analysis, and benchmark whether an AI agent p-hacks. Research and teaching use only.
11 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.