creating-agent-skills
Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
file-todos
This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
dspy-ruby
This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.
ashby
This skill should be used when the user asks about "Ashby API", "how to use Ashby tools", "Ashby authentication", "recruiting workflows", "candidate pipeline", "interview scheduling", "hiring process", "move candidate through pipeline", "schedule an interview", "manage applications", "track hiring progress", "source candidates", or "advance to next stage". Provides complete API reference and recruiting workflow guidance for the Ashby ATS integration.
atlas
macOS-only AppleScript control for the ChatGPT Atlas desktop app. Use only when the user explicitly asks to control Atlas tabs/bookmarks/history on macOS and the \"ChatGPT Atlas\" app is installed; do not trigger for general browser tasks or non-macOS environments.
cloudflare
|
council
Multi-agent codebase exploration and synthesis. Use when the user asks for /council, wants a council-style multi-agent scan, requests a broad codebase exploration and synthesis, asks for a codebase audit, architecture review, CTO-level assessment, or quality/readiness evaluation. Spawns multiple agents (default n=10) with diverse perspectives and synthesizes their findings.
docs
>
frontend-design
This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
every-style-editor
This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.
git-worktree
This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.
rclone
Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
skill-installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
figma
Translate Figma designs into production-ready code using the Figma MCP server. Trigger on: Figma URLs, node IDs, 'implement design', 'design to code', Figma MCP setup/troubleshooting, or any Figma-related task.
developing-nextjs
Use this skill when developing Next.js 16+ applications - creating pages, components, layouts, API routes, implementing proxy.ts, adding caching with Cache Components, or refactoring frontend code. This includes working with App Router patterns, Server Components, Server Actions, React 19+ features, and Tailwind CSS v4.
tox-paper-extractor
End-to-end OA literature pipeline for toxicity/peptide experimental data. Use to discover candidates (Europe PMC), download OA full text + supplementary (PDF/JATS XML/PMC OA packages), extract traceable raw records (tables/supp → raw_extractions.csv + raw_experimental_records.csv + extracted_tables), generate monitoring reports, and screen records for training readiness (units/aggregation/censoring).
lsky-uploader
Upload files to the self-hosted Lsky image bed (https://lsky.xueguo.us/api/v1), fetch the returned URLs/Markdown snippets, and manage albums or strategies via the REST API. Use this skill whenever you need to programmatically push screenshots/assets to Lsky and return shareable links inside Codex.
dl-paper-code-blog
Craft long-form, Chinese blog posts that connect deep-learning papers with their code repositories using the auto-collected bundle (materials_manifest, paper_text, figures, repo_context, lsky cache). Use this skill whenever a user provides such a bundle and wants a TL;DR, method deep dive, experiment analysis, reproduction guide, and media assets.
Planning
Generate an implementation plan for new features or refactoring existing code.
commit-messager
Write clear and concise commit messages that accurately describe the changes made in the codebase
code-reviewer
Review code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.
Debug
Debug your application to find and fix a bug or errors
Architect
Architect or technical leader mode.
vd-create
Create or refine a VibeDev Studio UnifiedWorkflow graph via tool calls. Use when the user says `$vd-create`, asks the model to “build the workflow graph”, “set up Research/Planning/Execution/Review steps”, or wants the model to collaboratively design prompts/conditions/breakpoints and write them into `unified_workflows` so the UI canvas shows the plan before running `$vd-next`.
vd-next
Advance a VibeDev workflow from chat. Use when the user types `$vd-next` / says “vd next” and wants the agent to fetch the next compiled step prompt from the VibeDev MCP HTTP server (`vibedev-mcp serve`) and handle breakpoint/new-thread/diagnose states.
vibedev-flow-designer
Use when translating a program/app idea into a VibeDev MCP Job (deliverables, definition of done, invariants, and a small step plan) and preparing it to transition to READY without implementing features yet
duckdb-alb-log-analyzer
Analyze AWS Application Load Balancer (ALB) logs stored in S3 using DuckDB. Use when users request ALB log analysis, error investigation, performance analysis, traffic analysis, or need to query ALB access logs. Supports analyzing response times, status codes, error patterns, and traffic trends from S3-stored logs.
skill-creator
|
deep-research
|
dealer-proposal
|
debug-mode
Run an iterative, hypothesis-driven “debug mode” loop to diagnose and fix a bug using targeted instrumentation and log capture. Use when the user wants an interactive debug loop, when you need to quickly narrow a failure via added debug statements, or when you need a lightweight way to centralize logs from a repro run (via `agent-skills debug` server + SSE UI).
context7-cli
Use the local Context7 CLI in this repo to search libraries and fetch Context7 context for skills or documentation tasks. Trigger when you need to run `c7 search`/`c7 context`, resolve library IDs, or retrieve text/json outputs from Context7 via the CLI.
crypto-expert
Crypto best-practices guidance and review across languages and domains. Use whenever cryptography, encryption, hashing, signatures, key/nonce/IV handling, randomness, password storage, TLS/PKI, secure channels, token formats, or "roll your own crypto" is mentioned, including high-level questions or code/design reviews. Trigger broadly to prevent subtle security mistakes.
gh-cli
Standardize all GitHub interactions via the GitHub CLI (`gh`) instead of ad-hoc URLs, UI clicks, or direct REST API calls. Use when you need to read or change GitHub state (repos, issues, pull requests, reviews, check status, Actions workflows/runs, releases, labels, milestones, discussions, gists) and want deterministic output (prefer `--json` + `--jq`). Also use when the user provides a GitHub URL, including deep links like `https://github.com/OWNER/REPO/pull/123`, `.../issues/123`, `.../pull/123/files`, or comment permalinks like `#issuecomment-...`, and you need to fetch the underlying PR/issue/thread and reply. Fall back to `gh api` only when there is no first-class `gh NOUN VERB` command.
commit-message
Format git commit messages combining Conventional Commits summary lines with Linux kernel-style bodies. Use when writing, reviewing, or formatting commit messages.
software-architecture
Document software architecture using ARCHITECTURE.md and docs/*.md files with Mermaid diagrams. Use proactively when ARCHITECTURE.md exists in project root, or invoke to create initial architecture documentation. Covers system design, data flows, component relationships, and code organization with references to key entry points and abstractions.
structured-logging
Guide for writing effective log messages using wide events / canonical log lines. Use when writing logging code, adding instrumentation, improving observability, or reviewing log statements. Teaches high-cardinality, high-dimensionality structured logging that enables debugging.
feature-file
Manage features.yml for tracking requirements and progress; use proactively ONLY when features.yml already exists, or invoke manually to create one; complements TodoWrite for persistent project state.
waterfall-development
Enforces strict waterfall development workflow with phase gates. Use when (1) features.yml exists in project root, (2) user asks to implement/develop/build a feature, (3) user explicitly requests waterfall workflow. Creates features.yml if missing when invoked.
git-commit
Guide for breaking changes into logical, atomic commits using interactive staging. Use when committing changes that span multiple concerns, when needing to stage parts of files (hunks), when asked to create well-organized commit history, or when changes should be split into multiple commits.
signal-factory-core
>
telemetry-validator-agent
>
ci-gatekeeper-agent
>
pr-author-agent
>
rca-copilot-agent
>
python-code-review
Production-grade Python code review. Use when reviewing code, PRs, or analyzing code quality. Checks architecture, security, quality, testing, documentation, deployment, and consistency. Provides severity-rated issues with fix suggestions.
eda
Exploratory Data Analysis for tabular data. Use when analyzing column distributions, checking data quality, examining class balance, detecting missing patterns, or generating summary statistics for datasets.
auto-duplicate-fixer
Automate detection and removal of duplicate files/functions in TypeScript, JavaScript, and Python projects. Safely refactor imports, validate with tests, and deploy changes with zero risk of breaking the system.
Page 1336 of 1369 · 68432 results
