thumbnail
Create high-performing thumbnails and cover images optimized for click-through rate. Use when asked to create a thumbnail, design a cover image, generate a YouTube thumbnail, or when the user mentions "thumbnail", "cover image", "CTR", or needs a visual asset for video or course content.
title
Generate optimized titles, headlines, and subject lines for any content type. Use when asked to create a title, headline, subject line, or when the user says "title ideas", "what should I call this", "subject line options", or needs engagement-optimized naming for videos, newsletters, or social posts.
voice
Apply Kenny Liao's authentic writing voice to any written content. This is a PERSONALITY skill invoked by other skills that produce written output — it handles parenthetical asides, sentence rhythm, fragments, counterpoint patterns, and raw-over-polished quality.
write-note
Create high-engagement Substack Notes. Use when asked to write a Substack Note, create a note for Substack, share an insight on Notes, promote a newsletter issue via Notes, or post between newsletter issues. Also use when the user mentions "note", "Substack Note", or "short-form Substack content".
write
Generalized writing skill that produces written content for any platform and format. Use when asked to write, draft, or create a newsletter, YouTube script, guide, sales page, Twitter thread, LinkedIn post, Substack Note, or community post. Also use when the user says "write this up", "draft a post", "create content about", or needs any written output.
youtube-data
Retrieve YouTube data using the YouTube Data API. Use when you need to search videos, get video or channel details, fetch transcripts, read comments, find trending or related content, or when the user mentions 'YouTube data', 'video stats', 'transcript', or 'channel info'.
context-health
Audit your Elle context system for staleness, contradictions, bloat, and missing data. Use when context feels stale, after major life changes, or periodically for maintenance. Also use when you notice Elle's responses feel generic or out of date.
evolve
Research-driven self-upgrade pipeline for the Elle personal assistant. Fetches latest Claude Code features, audits Elle's architecture, plans upgrades, executes them, and verifies results. Use after Claude Code updates, when exploring new features, or periodically. Also use when the user says "let's modernize Elle", "evolve Elle", or "what Claude Code features are we missing".
migrate
Migrate your Elle installation between versions. Handles any version-to-version upgrade path with sequential, idempotent steps. Use when updating Elle, when prompted by a version mismatch, or when the user says "migrate Elle" or "upgrade Elle".
onboard
Get to know the user through a guided conversation to personalize Elle's context.
retrospective
Use when ending a working session to capture lessons learned, when the user corrects Claude or asks to redo work, when the user expresses frustration with output quality, or when user triggers /retrospective
setup
Set up the personal assistant plugin. Run this once after installing the plugin.
sync-context
Regenerate ~/.claude/rules/elle-core.md from your context files. Run after significant context updates to keep your session rules current. Use when context feels stale, after /update-context changes rules/preferences/identity, or after /upgrade.
update-context
Update the context system based on our conversation so far.
test-skill
Run or generate test suites for any skill. Use when testing a skill before deployment, after making changes, before/after plugin upgrades, when validating skill behavior, or when the user says "test skill", "run skill tests", "generate tests for skill", or "check for regressions".
skill-retro
Use when reviewing how skills performed during a session, when the user wants to analyze skill invocations and identify improvements, or when the user says "skill retro", "review skills", "how did skills do", "improve this skill", or "skill retrospective".
upgrade-plugin
Upgrade a plugin's skills, hooks, and patterns to align with latest Claude Code capabilities and best practices. Use when a plugin needs modernization, after Claude Code updates, or when the user says "upgrade plugin", "modernize plugin", or "update plugin to latest patterns".
newsletter-to-video
Repurpose a newsletter issue into a high-level YouTube video outline. Use when asked to "create a YouTube outline from this newsletter", "turn this newsletter into a video", "repurpose for YouTube", "video outline from newsletter", or when converting any newsletter issue into video format.
newsletter-visuals
Audit a newsletter draft for visual opportunities and generate on-brand visual assets. Use when enhancing a newsletter draft with visuals, when a draft has [screenshot] placeholders, or when the user says 'add visuals', 'create images for this issue', 'make this more visual', or 'add diagrams to the newsletter'.
optimize-newsletter
Optimize a newsletter draft or write a full issue from an outline. Use when asked to 'optimize this draft', 'polish this newsletter', 'write from this outline', 'improve this issue', or when transforming an existing draft or outline into a publication-ready issue. Distinct from plan-newsletter which starts from a topic — this starts from existing content.
plan-newsletter
Plan a complete newsletter issue from a topic or idea, including research, draft, subject line, opening hook, and social promotion posts. Use when the user says 'plan a newsletter', 'create a newsletter about', 'newsletter plan', 'write a newsletter issue', or wants to turn an idea into a full issue plan.
plan-video
Create a complete YouTube video plan with title options, thumbnail concepts, hooks, and content outline. Use when planning a new video, creating title/thumbnail/hook options, or when the user says 'plan a video', 'video plan', 'plan my next YouTube video', or 'I want to make a video about'.
manage
Manage scheduled Claude Code tasks — add (recurring or one-off), list, pause, resume, remove, view results, and test execution of skills, prompts, and scripts with safety controls and notifications. Use when the user mentions scheduling, cron, automated tasks, recurring tasks, background tasks, running something on a schedule, periodic execution, or wants a skill/prompt/script to run automatically at a set time. Cross-platform (macOS, Linux, Windows).
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
ast-grep-outline
Use when exploring or modifying a codebase and you need a cheap structural map of files, directories, imports, exports, or direct members before reading full source.
commit-message
|
jira-write
|
pull-request
|
weekly-production-review
|
turborepo
|
storybook
Use when writing or reviewing Storybook stories (`.stories.tsx`) for React components.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
add-model-price
Use when editing worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, pricing tiers, tokenizer IDs, or matchPattern regexes for OpenAI, Anthropic, Bedrock, Vertex, Azure, or Gemini model pricing.
infra-scaling
Tune and review Langfuse autoscaling for web, web-iso, and web-ingestion. Use for Terraform scale settings, RPM targets, scaling bounds, task counts, cost/performance tradeoffs, or Datadog evidence in the infrastructure repo.
clickhouse-best-practices
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
react-component-cleaner
Use this skill to clean up a React component. Only use this skill when instructed to do so by the user.
react-component-guidelines
Guidelines for writing React components. Use this when creating a new react component.
create-repo-agent
Design, implement, review, or harden Langfuse repo-owned autonomous agents. Use for LLM-powered GitHub Actions, scheduled or dispatched agents, agent-created PRs, prompts, allowlists, tokens, untrusted content, or self-updating instructions.
langfuse-codebase-navigator
Navigate Langfuse repositories, code areas, and agent skills. Use to locate code, choose the right repo or skill, search across the Langfuse organization, or orient before implementation, debugging, documentation, support, or operations.
code-review
Review Langfuse code changes for correctness, regressions, and best practices.
backend-dev-guidelines
Build or review Langfuse backend code. Use for tRPC routers, public REST APIs, BullMQ processors, services, middleware, Prisma or ClickHouse access, OpenTelemetry, Zod, environment configuration, or backend tests.
security-review
Review Langfuse changes for SSRF, tenant isolation, secret handling, unsafe redirects or uploads, RBAC drift, and client telemetry privacy. Use when a design or change accepts URLs or host fields, handles secrets or cross-tenant data, makes outbound requests, adds an integration, follows redirects, widens permissions, or can send customer-controlled UI data through analytics, monitoring, or session replay.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
housekeeping
Triage an engineer's work queue across Linear, Pylon, and GitHub. Use for assigned, urgent, waiting, or stale issues, support follow-ups, and PR reviews.
agent-setup-maintenance
|
analyze-cloud-costs
|
changelog-writing
|
cursor-agents-workflow
|
datadog-query-recipes
|
debug-issue-with-datadog
|
Page 815 of 1653 · 82615 results