elliotjlt/claude-skill-potions
39 skills · 443 total installs
$npx skills add elliotjlt/claude-skill-potionsSkillInstalls
rubber-duckWhen a user is stuck, frustrated, or describing a problem vaguely, do NOT immediately suggest solutions.battle-planBefore ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in…learn-from-thisWhen a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented…etaWhen a user asks how long a task will take, requests a time estimate, or before starting any non-trivial coding task, immediately run scripts/estimate_task.py…pre-mortemBefore starting ANY significant task (feature build, refactor, integration, migration, or architectural change), first imagine the project has failed.stay-in-laneBefore making changes, verifies they match what was actually requested. Activates when about to modify files, add features, or refactor code.breadcrumbsLeaves notes for future Claude sessions in .claude/breadcrumbs.md.careful-deleteBefore any destructive or irreversible operation (rm -rf, DROP TABLE, DELETE, force push, branch deletion, truncate), orchestrate a safety cycle: assess blast…debug-to-fixWhen debugging frustration appears ("why isn't this working?", "it should work", "I don't understand"), orchestrate the full debug cycle: clarify → investigate…safe-refactorWhen refactoring, rewriting, or migrating critical code paths, orchestrate a safe cycle: assess risks → implement → verify → document.sanity-checkBefore building on assumptions, validates them first. Activates when making claims about how code works, what exists, or why something happens.you-sureBefore ANY destructive, irreversible, or high-impact action, pause and surface a clear checklist of what's about to happen.dont-be-greedyWhen a user uploads or references a data file (CSV, JSON, XLSX, TXT, LOG) or any file larger than 100KB, immediately estimate token cost using…fan-outOrchestration pattern for parallelizable tasks. When facing work that can be split into independent subtasks (research multiple topics, analyze multiple files,…keep-it-simpleBefore adding abstraction, asks "do we need this now?" Activates when proposing factories, abstract classes, config-driven behavior, or "for future…loose-endsBefore declaring work complete, checks for loose ends: unused imports, TODO comments created, missing tests, stale references, incomplete error handling.map-reduceOrchestration pattern for large-scale processing where work is distributed, processed independently, then combined.pipelineOrchestration pattern for sequential, dependent tasks. When work must flow through stages where each stage depends on the previous (design → implement → test →…prove-itBefore declaring any task complete, actually verify the outcome. Run the code. Test the fix. Check the output.retrospectiveAfter completing a significant task or experiment, documents what worked, what failed, and key learnings.split-decisionWhen facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and require explicit trade-off…trace-itBefore modifying shared code (utilities, types, configs, base classes), traces all callers and dependents first.zero-inBefore searching a codebase, forces you to zero in on the target: what exactly are you looking for, what would it look like, where would it live, what else…dripskill-creatorMeta-skill for creating well-structured skills with proper progressive disclosure.skill-forgeWhen Claude discovers a non-obvious solution, unusual pattern, or hard-won insight during a session, automatically forge it into a new skill.skill-gateBefore starting any significant task, force explicit evaluation of available skills. For each potentially relevant skill, state YES/NO with reasoning.agent-auditWhen reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft.obsidian-note-createCreates well-structured Obsidian notes with proper frontmatter, wikilinks, and template adherence.obsidian-vault-initInitialises an Obsidian vault for Claude Code workflows. Sets up folder structure, frontmatter conventions, templates, starter .base views, and a CLAUDE.md…obsidian-vault-searchSearches an Obsidian vault intelligently — combines CLI search, frontmatter filtering, content grep, and wikilink traversal.pair-modeWhen activated, Claude becomes a pair programming partner rather than a code-generation tool.obsidian-base-createGenerates Obsidian .base files from natural language descriptions.obsidian-canvas-createGenerates Obsidian .canvas files from intent. Takes a description of what you want to visualise and produces valid JSON Canvas — mind maps, flowcharts, kanban…obsidian-daily-driverManages daily notes workflow in Obsidian. Appends tasks, session logs, and learnings to today's daily note. Creates the daily note if it doesn't exist.obsidian-session-syncEnd-of-session ritual that syncs Claude Code session artifacts to an Obsidian vault.geordiegranola-syncSyncs Granola meeting notes to Obsidian vault. Reads from Granola's local cache to extract meeting metadata and notes, then creates properly formatted markdown…youtube-transcriptExtracts YouTube video transcripts and saves them as structured markdown files with metadata and timestamped content.