Claude Skills by tools-only

Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket. Triggers: "VoiceLiveClient java", "voice assistant java", "real-time voice java", "audio streaming java", "voice activity detection java".

Safely analyzes and cleans up local git branches and worktrees by categorizing them as merged, squash-merged, superseded, or active work.

Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion.

Use when the user wants to execute an implementation plan and build a companion project. Triggers on requests to build, execute tickets, start implementation, or run the shaping phase. Requires /plan to have been completed first with a tickets.yaml in place.

Salesforce debugging and troubleshooting skill with log analysis, governor limit detection, and agentic fix suggestions. Parse debug logs, identify performance bottlenecks, analyze stack traces, and automatically suggest fixes.

Agent Script DSL development skill for Salesforce Agentforce. Enables writing deterministic agents in a single .agent file with FSM architecture, instruction resolution, and hybrid reasoning. Covers syntax, debugging, testing, and CLI deployment.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Manage all GitHub operations: issues, PRs, repos, Actions, releases, secrets, and API calls. Uses MCP tools first for issues/PRs; falls back to GitHub CLI (gh) for Actions, releases, repos, and advanced operations. Triggers: "create issue", "file bug", "feature request", "create PR", "merge branch", "request review", "gh cli", "workflow run", "gh api", "gh release", "gh repo".

Build UIs with Tailwind CSS v4 and shadcn/ui. Covers CSS variables with OKLCH colors, component variants with CVA, responsive design, dark mode, and Tailwind v4.2 features. Supports Radix UI and Base UI primitives, CLI 3.0, and visual styles. Use when building interfaces with Tailwind, styling shadcn/ui components, implementing themes, or working with utility-first CSS. Triggers on tailwind, shadcn, utility classes, CSS variables, OKLCH, component styling, theming, dark mode, radix ui.

Verify claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that MUST use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Triggers on "fact check", "verify claims", "check against primary sources", or when backlog items are marked UNVERIFIED.

Make application behavior visible to coding agents by exposing structured logs and telemetry. Use when asked to "add telemetry", "make logs accessible to agents", "add observability", "debug with logs", or when an agent needs to understand runtime behavior but has no way to query logs. Also use when debugging is difficult because there are no structured logs, when agent docs (CLAUDE.md, AGENTS.md) lack instructions for querying application logs, or when setting up logging infrastructure for a...

Generate api client generator operations. Auto-activating skill for API Integration. Triggers on: api client generator, api client generator Part of the API Integration skill category. Use when working with APIs or building integrations. Trigger with phrases like "api client generator", "api generator", "api".

Controls interactive terminal sessions for running long-lived processes, servers, REPLs, debuggers, and TUI programs without blocking. Use when you need to run dev servers (npm run dev), debuggers (pdb, gdb), REPLs (python, node), databases (psql, mysql), SSH sessions, or editors (vim, nano) — any interactive or blocking program.

This skill should be used when the user asks to "improve a skill", "make this skill better", "add features to a skill", "this skill is missing something", "upgrade my skill", "what's missing from this skill", "improve how the skill works step by step", "the skill doesn't do X", "make this more useful", "the skill isn't working well for me", "can this skill do more", or wants to improve skill effectiveness rather than structural correctness.

Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data. Use when the user wants to set up, fix, or evaluate analytics tracking (GA4, GTM, product analytics, events, conversions, UTMs). This skill focuses on measurement strategy, signal quality, and validation— not just firing events.

This skill should be used when searching, fetching, or downloading emails from Gmail. Use for queries like "search Gmail for...", "find emails from John", "show unread emails", "emails about project X", or "download attachment from email".

Agent Script DSL development skill for Salesforce Agentforce. Enables writing deterministic agents in a single .agent file with FSM architecture, instruction resolution, and hybrid reasoning. Covers syntax, debugging, testing, and CLI deployment.

Generate descriptive commit messages by analyzing git diffs, very fast and context-pollution safe. Use when the user asks to commit staged changes or needs a conventional-commits message generated from the current diff.

Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks.

Controls interactive terminal sessions for running long-lived processes, servers, REPLs, debuggers, and TUI programs without blocking. Use when you need to run dev servers (npm run dev), debuggers (pdb, gdb), REPLs (python, node), databases (psql, mysql), SSH sessions, or editors (vim, nano) — any interactive or blocking program.

Initialise a git repository with optional agent commit instructions and .gitignore. Use when users say "here be git", "init git", "initialise git", or otherwise indicate they want to set up version control in the current directory.

Provides AWS messaging patterns using AWS SDK for Java 2.x for SQS queues and SNS topics. Handles sending/receiving messages, FIFO queues, DLQ, subscriptions, and pub/sub patterns. Use when implementing messaging with SQS or SNS.

AI-powered visual content generation for Salesforce development. Generates ERD diagrams, LWC mockups, architecture visuals using Nano Banana Pro. Also provides Gemini as a parallel sub-agent for code review and research.

Check for `.claude/apple-design-context.md` before asking questions. Use existing context and only ask for information not already covered.

**Pattern ID:** `tool-evaluation-framework-001` **Category:** Decision Making **Confidence:** High **Last Updated:** 2025-11-01 **Reuse Count:** 0 (newly created) ---

**Date:** 2025-11-01 **Session Type:** Debugging & System Configuration **Skill Used:** learning-capture **ROI Estimate:** 500+ tokens saved per similar incident × 5-10 future occurrences = 2500-5000 tokens ---

``` /app/ ├── browser_guard.py (41,635 bytes) - Playwright automation ├── jupyter_kernel.py (17,246 bytes) - IPython kernel management ├── kernel_server.py (9,434 bytes) - FastAPI control plane ├── utils.py (1,252 bytes) - Utility functions ├── data/ │ └── chrome_data/ (~272 files) - Chromium runtime │ ├── Default/ - Browser profile │ │ ├── Cache/ - HTTP cache │ │ ├── Coo

The `/app/` directory constitutes the runtime environment for the Kimi AI agent system. It contains the foundational Python infrastructure, browser automation subsystem, Jupyter kernel management, and skill-based domain extensions. This analysis examines the five core files at the root level that form the backbone of the agent's operational capabilities.

Page capture tool for visual inspection and documentation. Returns screenshot as embedded image or saves to filesystem.

Bash command execution in non-persistent environment providing system-level access to Debian GNU/Linux 12 (bookworm) container. Enables file operations, package management, and binary execution.

The `scripts/` directory contains 13 files implementing the PDF skill's multi-route architecture. These scripts handle HTML-to-PDF conversion (via Playwright + Paged.js), LaTeX compilation (via Tectonic), and existing PDF manipulation (via pikepdf/pdfplumber).

MCP Gateway: Full Project Overview - Purpose: One-stop guidance for LLMs to develop, run, test, document, and deploy the MCP Context Forge gateway. - Tech: FastAPI + Pydantic + SQLAlchemy; optional Redis; Alembic migrations; hybrid plugin framework (native + external MCP). **Core Capabilities** - Unified gateway for MCP servers: tools, prompts, and resources via HTTP/SSE/WebSocket/STDIO/streamable HTTP. - Plugin framework: AI safety, content filtering, policy enforcement, and transformations ...

ContextForge: Full Project Overview - Purpose: One-stop guidance for LLMs to develop, run, test, document, and deploy ContextForge gateway. - Tech: FastAPI + Pydantic + SQLAlchemy; optional Redis; Alembic migrations; hybrid plugin framework (native + external MCP). **Core Capabilities** - AI gateway, registry, and proxy exposing a unified control plane for MCP servers: tools, prompts, and resources via HTTP/SSE/WebSocket/STDIO/streamable HTTP. - Plugin framework: AI safety, content filtering,...

ContextForge: Full Project Overview - Purpose: One-stop guidance for LLMs to develop, run, test, document, and deploy ContextForge gateway. - Tech: FastAPI + Pydantic + SQLAlchemy; optional Redis; Alembic migrations; hybrid plugin framework (native + external MCP). **Core Capabilities** - Unified gateway for MCP servers: tools, prompts, and resources via HTTP/SSE/WebSocket/STDIO/streamable HTTP. - Plugin framework: AI safety, content filtering, policy enforcement, and transformations with pre...

**Version**: 1.2 **Status**: Design + implementation notes **Date**: February 2026 **Related**: [OAuth Design Document](./oauth-design.md)

**Version**: 1.2 **Status**: Design + implementation notes **Date**: February 2026 **Related**: [OAuth Design Document](./oauth-design.md)

> A quick reference for what’s already in `vm-alert-config.yaml`. Update thresholds only if needed, and **remember to set the Discord `webhook_url` correctly**. As of 2025-10-22 ---

Source + contribution: - Full guide: https://clig.dev/ - Propose changes: https://github.com/cli-guidelines/cli-guidelines Table of contents: - Foreword - Introduction - Philosophy - Human-first design - Simple parts that work together - Consistency across programs - Saying (just) enough - Ease of discovery - Conversation as the norm - Robustness - Empathy - Chaos - Guidelines - The Basics - Help - Documentation - Output - Errors - Arguments and flags - Interactivity - Subcommands - Robustnes...

Source + contribution: - Full guide: https://clig.dev/ - Propose changes: https://github.com/cli-guidelines/cli-guidelines Table of contents: - Foreword - Introduction - Philosophy - Human-first design - Simple parts that work together - Consistency across programs - Saying (just) enough - Ease of discovery - Conversation as the norm - Robustness - Empathy - Chaos - Guidelines - The Basics - Help - Documentation - Output - Errors - Arguments and flags - Interactivity - Subcommands - Robustnes...

```bash gh repo create Scottcjn/grazer-skill --public --description "🐄 Claude Code skill for grazing worthy content"

Currently, 6 skill files detect `rp-cli` and `codex` availability at runtime using `which rp-cli` and `which codex`. This causes:

Ralph runs as a foreground process. Users want to: - Start Ralph, walk away, monitor from phone/Discord via Clawdbot - Pause/resume without killing the process - Rollback failed tasks and retry without restarting everything - Check status from any CLI tool

Terminal UI for flow-next Ralph mode. Real-time visibility into autonomous agent runs.

Add `flowctl ralph` subcommand group with pause/resume/stop/status.

Add a review backend question to the `/flow-next:setup` workflow.

Remove runtime `which rp-cli` / `which codex` detection from flow-next-work skill.

Remove runtime `which rp-cli` / `which codex` detection from flow-next-plan skill.

Create CLI entry point with argument parsing.

Identify documentation that may need updates based on the planned changes.

Identify documentation that may need updates based on the planned changes.