AI & ML

ethpandaops Skill

Run schema probing self-play loop to find and fix ClickHouse schema ambiguity in the panda repo. Use when the user wants to improve query reliability by finding where the agent picks different tables for the same question.

ethpandaops Skill

Install panda as an MCP server in AI coding assistants (Claude Code, Claude Desktop, Cursor). Use when setting up panda, configuring MCP, or connecting AI tools to panda. Triggers on: install mcp, setup mcp, configure mcp, register mcp, add mcp server.

sendbird Bundle

Delegate a substantial diagnosis, implementation, or follow-up task to Claude Code through the tracked-job runtime. Args: --background, --wait, --resume, --resume-last, --fresh, --write, --model <model>, --effort <low|medium|high|xhigh|max>, --prompt-file <path>, [task text]. Defaults to opus with no forced effort. Use when Claude should investigate or change things, not when the user only wants review findings.

sendbird Bundle

Run a standard Claude Code review of local git changes in this repository. Args: --wait, --background, --base <ref>, --scope <auto|working-tree|branch>, --model <model>, --effort <low|medium|high|xhigh|max>. Defaults to opus with no forced effort. Use as the default path for ordinary code-review requests when the user did not explicitly ask for stronger adversarial scrutiny or for Claude to own the implementation work.

sendbird Bundle

Run a design-challenging Claude Code review of local git changes in this repository. Args: --wait, --background, --base <ref>, --scope <auto|working-tree|branch>, --model <model>, --effort <low|medium|high|xhigh|max>, [focus text]. Defaults to opus with no forced effort. Use only when the user wants stronger scrutiny than a normal review, such as explicit tradeoff challenge, risky-change review, or custom focus text.

jayteealao Bundle

Consult external models as READ-ONLY oracles — plan critique, code/implementation review, design analysis, diagnosis, second opinion. Fans out to all available providers by default (codex, claude, gemini, openai; a provider keyword narrows to one). Returns a panel of opinions and never edits the repo. The model may invoke it autonomously when a second opinion adds material value; model-initiated runs pin a free subscription CLI (codex/claude).

launchdarkly-labs Bundle

Create a new LaunchDarkly AI Config with variations, model configurations, and targeting. Use this skill to programmatically create AI Configs for agent or completion mode.

launchdarkly-labs Bundle

Use Online Evaluations (LLM-as-a-judge) to automatically score AI Config responses for accuracy, relevance, and toxicity.

launchdarkly-labs Bundle

Build safe, scalable contexts for LaunchDarkly AI Configs with cardinality controls, multi-context patterns, and agent graph attributes.

kitsunekode Bundle

Audit CLAUDE.md/AGENTS.md for context bloat, duplication, and misplaced guidance. Use when agent docs feel too long, redundant, or slow the agent at startup.

jayteealao Bundle

Generate images from a text prompt. Fans out to all available providers by default (built-in image_gen, gpt-image-2, nano-banana) → a variant set; a provider keyword yields one. Internal to `/wf design`; invoke it through that key.

dupe-com Bundle

Pin a short personal reminder to the agent's status line. Use when the user types "/note", or says "remind me", "note to self", "pin a note", "set a reminder", or "clear my note". The note is synthesized into a terse line and shown on its own status-line row with a bold sticky-note background, scoped to the current session, until cleared.

dupe-com Bundle

Error prevention and best practices enforcement for agent-assisted coding. Use when writing code to catch common mistakes, enforce patterns, prevent bugs, validate inputs, handle errors, follow coding standards, avoid anti-patterns, and ensure code quality through proactive checks and guardrails.

miles990 Skill

Run all mini-agent health-check and janitor scripts in one pass and summarize the results. Use when the user wants a project health check or types /health-sweep.

ghostscientist Skill

Guides you through implementing a research paper step-by-step from scratch. Use when asked to implement a paper, code up a paper, reproduce research results, or build a model from a paper. Focuses on building understanding through implementation with checkpoint questions.

junhua Skill

Product design guide for Omnisonant - omni-channel voice agents that replace call center staff. Use when designing, reviewing, or improving Omnisonant interfaces, voice agent behaviors, or architecture.

junhua Skill

Product design guide for Inframagics - the agent-native workspace that replaces enterprise systems + operations teams. Use when designing, reviewing, or improving Inframagics interfaces, features, or architecture.

7hinkdifferent Skill

Codex workflow adapter for this repository. Use when working in agent-cracker to translate Claude-style slash workflows into skill usage, remember manual checks that Claude hooks would normally perform, and keep docs/config/progress files in sync.

kaichen Skill

Discover available Agent skills. Use when users ask "what skills are available", "list skills", "show me skills", or want to browse installed skill capabilities.

kaichen Skill

Analyze Claude Code CLI source code to understand its architecture design and implementation details(prompts, built-in tool, agents). Use when users want to explore how Claude Code works internally, understand specific features like tools/hooks/MCP/permissions, or learn from its codebase design. Triggers on questions about Claude Code internals, source code analysis requests, or "how does Claude Code implement X" or "what's the prompts of claude code's X" queries.

itamarzand88 Bundle

Use this skill when controlling agent behavior in TypeScript Agent SDK platforms — restricting allowed tools, setting budget and turn limits, crafting system prompts that guide agents to specific behaviors, implementing the file pre-creation pattern, augmenting prompts with runtime context, building message loggers, or tracking agent run metadata (cost, duration, iterations).

itamarzand88 Bundle

Use this skill when implementing TypeScript hook callbacks for the Claude Agent SDK — creating PreToolUse hooks to allow/deny tool calls, PostToolUse hooks to inject additionalContext, building factory functions for parameterized hooks, using HookCallback and HookJSONOutput types, applying isPreToolUseInput and isPostToolUseInput type guards, or designing a hooks strategy for an Agent SDK platform. Hooks in the TypeScript SDK are async functions, NOT JSON config files.

itamarzand88 Bundle

Use this skill when developing TypeScript applications with the Claude Agent SDK (@anthropic-ai/claude-agent-sdk), implementing query() calls, configuring SDK options, handling streaming message iteration, working with SDKMessage and SDKResultMessage types, managing AbortSignal, passing custom env variables, or setting up the single-point-of-contact types file for SDK imports.

miethe Bundle

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating plan/phase frontmatter, enforcing the canonical NodeStatus enum.

miles990 Bundle

Pre-edit coordination ritual for the shared mini-agent tree — checks Kuro's cycle state, current branch, and whether worktree isolation is needed before touching src/ or memory/. Use before editing src/ or memory/ in the mini-agent repo.

jack-taylor-gorman Skill

Design RESTful and GraphQL APIs following industry best practices for consistency, usability, and maintainability.

jack-taylor-gorman Skill

End-to-end testing and browser automation using Playwright.

sreenivasanac Skill

Improve prompts before sending them to get better results. Use when you want to refine a task description.

sreenivasanac Skill

Refine prompts for GPT models (GPT-5, GPT-5.1, Codex) using OpenAI's best practices. Use when preparing complex tasks for GPT.

thirdlf03 Skill

Claude Code Subagentsのレビューと品質改善。ベストプラクティスに基づいてSubagentを分析し、評価レポートと改善提案を提供。"review agent", "agentをレビュー", "subagent品質チェック" で起動。

thirdlf03 Bundle

Comprehensive .claude/ directory inspector. Orchestrates multiple specialized subagents to analyze settings, hooks, memory, MCP, rules, and skills/subagents classification. Provides prioritized recommendations with examples and rationale.

thirdlf03 Bundle

Create, edit, or audit Claude Code custom agents (subagents), including file locations, YAML frontmatter, tool/permission settings, skills preloading, and prompt design. Use when asked to define a new Claude Code subagent, update an existing one, or review subagent configs for correctness and best practices. Triggers on "create agent", "new subagent", "define custom agent", "audit agent".

shawn-sandy Skill

Runtime-verify a change to a published skill in this repo by driving its script as a CLI and running its SKILL.md steps as a fresh agent. Repo-local tooling, not a published skill.

shawn-sandy Bundle

Scores SKILL.md files across 5 quality dimensions. Audits against the Agent Skills open standard's authoring best practices and optionally generates a fix. Use when the user asks to review, audit, or score a skill.

shawn-sandy Bundle

Reviews code for bugs, security issues, and breaking changes. Produces prioritized findings on quality, vulnerabilities, and regressions. Use when asked to review code or check a PR diff.

shawn-sandy Bundle

Suggests purpose-driven tests tied to actual behavior. Writes test files covering untested paths and behavior gaps in the codebase. Use when the user asks to suggest tests or find untested behavior.