🎯
Skills
Loading...
Showing 30 of 146048 results
Systematically optimizes conversion rates by deeply understanding visitor behavior, objections, and user experience through evidence-based research and testing techniques.
Designer skill that orchestrates the full design-to-build workflow as a guided sequence: Grill Me, Design Brief, Information Architecture, Design Tokens, Brief to Tasks, Frontend Design, and (on request) Design Review. Runs each sub-skill in order and can resume mid-flow by inspecting the .design/<feature-slug>/ folder.
Three-stage pipeline (Fork → Sanitize → Package) that turns any private project into a safely public release — stripping secrets, verifying the repo is clean, then generating CLAUDE.md, setup.sh, and README. Triggered by `/opensource fork|verify|package` or phrases like "open source this" and "make this public".
A Claude Code plugin marketplace from Trail of Bits providing skills for AI-assisted security analysis, testing, and development workflows.
Generates comprehensive software testing handbooks covering test cases, scenarios, and best practices for development and QA teams
A four-phase self-debugging loop (failure capture → root-cause diagnosis → contained recovery → introspection report) for AI agent runs that are looping, burning tokens, or drifting from the task. Provides a pattern table (tool-call loops, context overflow, `ECONNREFUSED`/429s, stale diffs, wrong hypotheses) and forces the agent to verify world state, shrink scope, and run one discriminating check before retrying.
Creates a design brief through an interactive interview that first scans the codebase for existing tokens, Tailwind configs, theme providers, and component directories, then walks through problem, experience principles, aesthetic direction, constraints, and component inventory. Saves the output as `.design/<feature-slug>/DESIGN_BRIEF.md`.
Reorganizes the user's X and LinkedIn networks with review-first prune queues, follow/add recommendations, and warm-path identification scored by reciprocity, recent activity, and bridge value across `light-pass`/`default`/`aggressive` modes. Drafts channel-specific outreach (X DM, LinkedIn message, Apple Mail) in the user's voice via `brand-voice`, `lead-intelligence`, and `x-api`.
A comprehensive agent toolkit providing Claude Code skills for software diagramming, code review, QA planning, and professional communication workflows.
Automates Notion databases and workflows with cross-platform integrations for Slack, Calendar, email, and CRM, including form-to-database pipelines, weekly digests, task creation from Slack messages, and content management automation.
Automates audio and video transcription workflows including speech-to-text conversion, meeting transcription with speaker diarization, and subtitle generation in SRT/VTT formats using engines like Whisper, AssemblyAI, and Deepgram.
Enables efficient bulk processing of documents with parallel execution, supporting batch conversion, text extraction, file renaming, and mass updates with progress tracking, error handling, and checkpoint-based resume capability.
An agent skill for comprehensive Shopify e-commerce automation covering inventory management with predictive reordering, order processing pipelines, customer lifecycle workflows, multi-channel synchronization, and analytics reporting.
Guides structured analysis of user feedback to extract actionable insights and improvement directions for products and services.
Automates document workflows using n8n, the workflow automation platform with 7800+ community templates, enabling integration with 400+ apps and building complex document processing pipelines with conditional logic.
A Claude office skill for designing and building AI agents with tools, memory, and multi-step reasoning capabilities. Covers agent architecture patterns (reactive, conversational, tool-using, reasoning, multi-agent), platform integrations with Slack and Telegram, and integration with ChatGPT, Claude, and Gemini.
Read-only audit of the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup to answer "what can this workspace actually do right now, and what should we add next?". Separates already-available, available-but-unwrapped, and not-yet-available capabilities, surfacing only key names (never secret values).
Part of LaunchDarkly's official agent skills collection encoding repeatable workflows for feature flags, AI configs, and onboarding, enabling coding agents to execute LaunchDarkly tasks safely and consistently.
A comprehensive agent toolkit providing Claude Code skills for software diagramming, code review, QA planning, and professional communication workflows.
Run a multi-layered knowledge base — GitHub/Linear as live execution truth, Claude Code memory files, MCP memory graph, a durable KB repo, Supabase/Postgres, and a local archive folder — with a strict ingestion workflow (classify → dedupe → store → index). Syncs conversations and workspace state, redacts secrets before commits, and prefers one canonical home per fact instead of parallel copies.
A comprehensive agent toolkit providing Claude Code skills for software diagramming, code review, QA planning, and professional communication workflows.
Scans Algorand blockchain smart contracts for security vulnerabilities and provides detailed remediation insights
Build a new API connector or provider that exactly matches the host repo's existing integration pattern — connector layout, config schema, auth model, error handling, test style, and registry wiring — instead of inventing a parallel architecture. Guides the workflow from inspecting at least two existing in-repo connectors through building repo-native slices (config, client, mapping, entrypoint, registration, tests) and a quality checklist before completion.
Skill for applying clean code principles and practices, from a collection that also covers microinteractions, lean UX, clean architecture, and software design philosophy.