dbosk

@dbosk source repo

25 skills
0 followers
16 hours ago last updated

▌
Canvas · dbosk
Query KTH Canvas (course info, assignments, deadlines, modules, syllabus, pages) via the `canvaslms` CLI to answer natural-language questions like "when is the deadline for lab 2 in DD1301".

0
installs
▌
Honor Audit · dbosk
Audit a draft KTH submission for honor-code risk — copied content, missing citations, undisclosed AI use, group-attribution gaps, attendance-record issues.

0
installs
▌
Honor Disclose · dbosk
Generate an honest, structured disclosure block for a KTH submission — what was the student's own work, what help was used (people, sources, AI), and where each contribution appears.

0
installs
▌
Honor Aid Check · dbosk
Before giving or accepting help on a KTH assignment, check whether the help is within the assignment's permitted-aids and collaboration policy.

0
installs
▌
Honor Defense Prep · dbosk
Prepare a student to orally present and defend every part of their own submission, satisfying Rule 3 (oral competency) of the KTH EECS Code of Honour.

0
installs
▌
Honor Policy Draft · dbosk
(Teacher-side) Draft an unambiguous permitted-aids and collaboration policy for a KTH assignment, including explicit handling of generative AI.

0
installs
▌
Didactic Notes · dbosk bundle
Document pedagogical design decisions in educational materials using the didactic LaTeX package and \ltnote command. Use proactively when (1) writing or editing educational LaTeX materials with pedagogical content, (2) adding or revising variation-theory annotations such as "What varies" or "What stays invariant", (3) explaining design trade-offs or choices in educational materials, (4) documenting why specific examples or exercises are sequenced in a particular way (including the order in which a literate program explains its parts, e.g. why function A is presented before function B), or (5) moving pedagogical reasoning out of student-facing prose and into instructor notes. Invoke when user mentions didactic notes, \ltnote, pedagogical reasoning, learning theory notes, educational design documentation, or asks to move pedagogical reasoning to instructor notes. CRITICAL: \ltnote captures reasoning about how the teaching material itself is written and sequenced (variation/invariance labels, why this example, w

1
install
▌
Writing Crypto · dbosk bundle
Write cryptography prose and notation using the project's bibsp.sty + preamble.tex conventions (acro + biblatex footnote citations and standardized math macros). Use proactively when: (1) writing/editing cryptography sections in .tex files, (2) introducing or using crypto acronyms such as IND-CPA, IND-CCA, AE, MAC, PRF, ZK, and DH, (3) defining schemes/algorithms/variables in math notation, (4) adding citations for security notions or standard primitives, (5) writing security proofs or reductions, (6) user mentions biblatex, crypto notation, or security proof in cryptographic context.

1
install
▌
Document Issues · dbosk
IMPORTANT: load this skill the moment you notice an out-of-scope follow-up while working, and BEFORE filing any GitHub issue or importing to nytid todo. Captures unrelated follow-up issues discovered during repository work and records them for later. Use proactively when: (1) working inside a git repository and you spot a bug, cleanup, missing test/doc, or tech-debt item that is NOT part of the current task (even one you only mention in a comment, memory, or summary — capture it here instead); (2) the user mentions filing an issue, follow-up, backlog item, or nytid import. Prefer gh issue; ask before creating anything unless autonomous issue capture is enabled; optionally import created GitHub issues into nytid todo.

1
install
▌
Skill Management · dbosk bundle
IMPORTANT: Activate this skill BEFORE modifying any skill in ~/.claude/skills/. Guide for creating, updating, and maintaining Claude Code skills following best practices. Use proactively when: (1) creating a new skill, (2) modifying an existing skill in ~/.claude/skills/, (3) user requests to create, improve, update, review, or refactor a skill, (4) discussing skill quality or effectiveness. Always commit skill changes to the skills git repository after making modifications.

1
install
▌
Variation Theory · dbosk bundle
Apply variation theory of learning to structure content using contrast, generalization, and fusion patterns. Variation must target the critical aspects of the learning objective. Use proactively when (1) writing educational materials, explanations, tutorials, or lecture slides, (2) designing or reviewing examples in documentation, READMEs, or literate programs (.nw files), especially when multiple examples illustrate alternative approaches to the same task, (3) structuring code examples, CLI usage examples, or API examples where the reader should notice what differs between alternatives, (4) user mentions variation theory, pedagogy, contrast, invariance, or critical aspects. Also activate when asked to elaborate or add examples. Works alongside literate-programming and didactic-notes skills; in educational LaTeX or .nw materials, keep variation-analysis labels in \ltnote{} rather than student-facing prose, unless the design is the document's subject (e.g. prose documenting a tangled learner-facing tutorial).

1
install
▌
Scientific Writing · dbosk bundle
Structure and workflow conventions for research papers. Use proactively when (1) writing or revising a paper draft, its introduction, method, results or conclusions, (2) adding research questions, hypotheses, contributions, questionnaires or analyses to a paper, (3) processing a review round on a draft, or (4) starting a new paper repository. Covers question-hypothesis-contribution traceability, substantive vs methodological research questions, literate-program appendices for instruments and analyses, method-section chronology, and the review-round loop.

0
installs
▌
Worktree Subagents · dbosk
Orchestrate parallel fix/implementation subagents in isolated git worktrees without them testing the wrong code or colliding. Use proactively when (1) spawning Agent tasks with worktree isolation, (2) running a batch bug-fix or migration campaign where several agents edit the same repo in parallel, (3) a worktree agent reports import/venv/submodule build failures, (4) resuming subagents after a session limit or crash, or (5) writing prompts for agents that must build a generated-artifact project (e.g. noweb/literate programs) before testing. Documents obstacles observed in a real 47-branch campaign and the prompt preamble that avoids them.

1
install
▌
Update Project Docs · dbosk bundle
Keep CLAUDE.md and AGENTS.md current after significant project changes. Use proactively when: (1) adding new modules, packages, or top-level directories, (2) changing build/test commands or tooling, (3) renaming/moving/deleting files referenced in CLAUDE.md, (4) introducing new conventions or patterns, (5) reorganizing document structure, (6) adding dependencies requiring setup steps. Invoke when user mentions CLAUDE.md, AGENTS.md, project docs update, or after completing architectural changes.

1
install
▌
Literate Programming · dbosk bundle
CRITICAL: ALWAYS activate this skill BEFORE making ANY changes to .nw files. Use proactively when: (1) creating, editing, reviewing, or improving any .nw file, (2) planning to add/modify functionality in files with .nw extension, (3) user asks about literate quality, (4) user mentions noweb, literate programming, tangling, or weaving, (5) working in directories containing .nw files, (6) creating new modules/files that will be .nw format. Trigger phrases: 'create module', 'add feature', 'update', 'modify', 'fix' + any .nw file. Never edit .nw files directly without first activating this skill to ensure literate programming principles are applied. (project, gitignored)

1
install
▌
Try First Tell Later · dbosk bundle
Structure educational content using try-first-tell-later pedagogy where students predict, attempt, or reflect before receiving explanations. Creates active learning through cognitive engagement and variation theory's contrast patterns. Use when writing educational materials, designing exercises, creating lecture notes, structuring tutorials, writing teaching examples with LaTeX/Beamer or Mentipy, developing problem sets, or when user mentions try-first, predict-first, productive failure, Socratic method, question-before-answer, exercise-driven learning, inquiry-based teaching, polls, or interactive slide questions.

1
install
▌
Commit · dbosk
Create atomic git commits following best practices

1
install
▌
Kth Data · dbosk bundle
Where to find KTH facts Claude cannot know by itself: the user's Canvas sandbox course for write-testing canvaslms, KTH room facts (capacity, building, address) via kth.se/places, the academic-year period dates (läsårsindelning) which must be searched for because intranet URLs change, and the user's teaching schedule via `nytid schedule show`. Use proactively when: (1) a task needs a Canvas course to test canvaslms write commands against, (2) a task mentions KTH rooms, lecture halls, seats/capacity, room booking, or mapping students/TAs to rooms, (3) a task needs period, term, exam-period or läsår dates (P1–P4, HT/VT, tentaperiod), (4) a task needs the user's (or TAs') schedule, lecture times, or which room an event is in. Read-only sources; pair with canvas-info/canvaslms for Canvas edits and nytid-todo for work items.

1
install
▌
Inbox Info · dbosk bundle
Research and answer questions about email in the user's Maildir via mu (maildir-utils). Use proactively when: (1) user asks about emails, inbox, flagged messages, senders, subjects, or specific correspondence, (2) user asks "what do I need to handle / respond to?" — flagged emails are the user's marker for actionable items, (3) user mentions mu, mutt, neomutt, or Maildir, (4) user wants to convert email-derived work into nytid todos. Strictly read-only; never modifies mail state.

1
install
▌
Nytid Todo · dbosk
Manages work items via nytid todo subcommands as worker dan-claude. Relevant when the user asks to check, start, or complete tasks, view task details, add progress notes, create subtasks, reprioritize items, or import/sync GitHub issues. Also triggered by "what should I work on next?", "show my tasks", "mark that done", "what's in progress?", or mentions of nytid, todo, or work items. Also use when handing the user a batch of follow-ups from a session ("add todos to my nytid", papers to download, things only the user can do) and when a todo should resume the current Claude session (`claude --resume`) in a given working directory.

1
install
▌
Remarkable · dbosk bundle
IMPORTANT: load this skill BEFORE calling ANY remarkable-mcp tool — even a one-line upload — because the tools have silent-failure gotchas (address docs by path/name, NOT the UUID that upload returns; annotations only appear after the tablet syncs; render_merged needs the patched build). Work with a reMarkable tablet via the remarkable-mcp MCP server: upload PDFs/EPUBs, browse/search the cloud, render pages (optionally compositing annotations onto the PDF), read page text/OCR, extract highlighted text, and list which pages carry notes/highlights. Use when: (1) sending/uploading a document, paper, or PDF to the reMarkable ('put this on my reMarkable', 'upload to remarkable'); (2) reading/rendering/checking an annotation, note, or highlight, or extracting only the annotated pages; (3) the user mentions reMarkable, remarkable-mcp, rmapi, or their tablet; (4) setting up or troubleshooting the server. Covers auth, the tool inventory, annotation extraction, and more gotchas (1-based pages, mid-session MCP loading).

1
install
▌
Canvas Info · dbosk
Research and answer questions about Canvas LMS courses using the canvaslms CLI. Use proactively when: (1) user asks about course content, assignments, pages, grades, deadlines, or announcements, (2) user mentions a Canvas course name or course code, (3) user asks "what assignments/pages/modules are in [course]?", (4) user wants to find specific course materials or check deadlines. This skill is read-only; to create quiz content, use the canvas-quiz skill instead.

1
install
▌
Canvas Quiz · dbosk bundle
Write and review Canvas LMS quiz JSON files (INL1Quiz-*.json) for the tilkry cryptography course. Use proactively when: (1) creating, editing, or reviewing INL1Quiz JSON files, (2) user asks to write quiz questions for a lecture topic, (3) user asks to review quiz quality, redundancy, or distractor balance, (4) user mentions Canvas quiz, INL1Quiz, quiz JSON, or quiz questions. Covers JSON structure, question design, scoring, redundancy analysis, and validation.

1
install
▌
Latex Writing · dbosk bundle
Guide LaTeX document authoring following best practices and proper semantic markup. Use proactively when: (1) writing or editing .tex files, (2) writing or editing .nw literate programming files, (3) literate-programming skill is active and working with .nw files, (4) user mentions LaTeX, BibTeX, Mentipy in a Beamer/article/PythonTeX context, interactive slide questions in LaTeX, or document formatting, (5) reviewing LaTeX code quality. Ensures proper use of semantic environments (description vs itemize), csquotes (\enquote{} not ``...''), and cleveref (\cref{} not \S\ref{}).

1
install
▌
Backing Claims · dbosk bundle
Back factual and empirical claims with a small two-sided literature review — searches for literature that supports AND refutes/qualifies the claim (COUNTER) — verify sources in full text, and record provenance (how found, why picked, quote, counter-search outcome). Format-independent: papers, reports, memos, evidence logs, survey answers — any output resting on a factual claim, not just TeX. Use proactively when: (1) adding OR reusing a citation, page number, or attribution for a factual/empirical claim (inherited citations are NOT pre-verified), (2) attributing a claim to a source ("X found that…"), (3) the user asks to find a reference or check a citation — or wants an answer or decision backed by evidence, research, or literature, (4) writing related-work, background, or claims sections, (5) mentions of scholar, BibTeX, DOI, arXiv, OpenAlex, Crossref, or a literature search. (6) DELEGATING literature research to a subagent or teammate — the subagent prompt must tell it to load this skill, run every search

1
install

25 published skills