Write content using stored writing styles from the writing-styles/ collection. Use when the user wants to write in a specific voice, apply a stored style, list available writing styles, or evaluate text against a style rubric. Triggers on 'write in [style] style', 'use [style] voice', 'list writing styles', 'apply…
Run a Socratic teaching loop that quizzes you on a coding session until you have confirmed mastery of every concept. Use when you want to learn or lock in what happened in a Claude Code session, understand a transcript, PR, or design decision, be quizzed/tested/drilled on recent work, or prepare to teach someone else…
Skill "ty" from dashed/claude-marketplace, covering ty — python type checker, mental model (read this before configuring anything), when to use this skill, install & run and commands.
Invoke deep sequential thinking for complex problem-solving. Use when the user says 'use ultrathink', 'ultrathink', or when tackling problems that require careful step-by-step reasoning, planning, hypothesis generation, or multi-step analysis.
Skill "uv" from dashed/claude-marketplace, covering uv - python package & project manager, mental model (read this first), prerequisites, install and windows (powershell).
Convert game walkthroughs and guides from plain text into structured, interlinked Obsidian markdown pages. Use when the user wants to convert a walkthrough, FAQ, guide, or reference document into Obsidian vault pages. Triggers on mentions of converting walkthroughs, guides, or FAQs to Obsidian, or splitting a large…
Terminal workspace and multiplexer for interactive CLI sessions. Use when managing terminal sessions, running interactive REPLs, debugging applications, automating terminal workflows, or when user mentions zellij, terminal multiplexer, floating panes, or session layouts. Simpler alternative to tmux with native session…
Shrink a test suite without losing a single asserted fact or covered branch — the fact-matrix method: read every test into a matrix of the propositions it pins, measure per-test branch coverage and a covering set, and delete only on the intersection of both oracles; relocate a fact to a cheaper layer only after a…
Review and improve engineering Markdown designs, analyses, implementation plans, and architecture decision records. Use for section-level clarity edits, requirement and evidence preservation, or comparing a proposed rewrite with its original. Uses static Markdown checks; not a general prose or code-comment reviewer.
Use Jev as a bounded second opinion during agent work. Use when asked to consult Jev, compare explicit plans or candidates, check claims against supplied evidence, prioritize follow-up work, or challenge a proposed conclusion with typed judgments. For building TypeSafe-powered applications, use the typesafe-ai skill…
Decide whether a test earns its place, at write time and in audits: an authoring gate for every new or changed test (what it protects, which regression fails it, why existing coverage misses that, whether it needs a test-only seam, and a regression test that fails before the fix); a checklist of low-value patterns …
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts. Use when the user asks to see the current topic instead of reading about it, such as "show me", "/show-me", "draw it", "diagram this", "visualize this", or "what does the call tree look like", or…
★not rated 25 16d agoA120 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: