核心能力: 沟通协作领域的专业化 AI 辅助工具,包含企业级高级功能兼容. 适合需要comm skill tool相关能力的开发场景,提供标准化流程和配置参考。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。适用于独立开发者、企业团队和自动化工作流场景。
Use AUTOMATICALLY when developing or modifying code that exists on both macOS (Swift/AppKit) and Windows (C#/WPF), or when creating new cross-platform features.
Use AUTOMATICALLY whenever ANY Tampermonkey userscript (.user.js) in ~/Codex/Tampermonkey/ is modified. Ensures version numbers are bumped before committing.
Audits command files for correctness and best practices. Use when reviewing, improving, or validating commands, checking frontmatter, assessing structure, or learning command…
Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML — from…
Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in one place.
Web and App implementation guide for Command Center UI. Trigger when user wants monitoring systems, enterprise dashboards, NOCs, and global maps.
The native task command centre for a GRU953-Studio project — plan, track and control work with pause, resume, stop, skip-now and schedule-for-later.
Create Claude Code slash commands or reusable command workflows; use for create/add/make command requests, and outside Claude redirect to a skill or prompt recipe.
Validates and registers command manifest files (YAML) to integrate new slash commands into Betty.
Executes safe commands and captures real output to extend command-verify functionality. Only runs when explicitly requested.
Run an agency's worth of work from your phone. You send one line of intent — the outcome you want, not the keystrokes — from anywhere, an always-on machine picks it up and puts…
Set up a PreToolUse hook in .claude/settings.json that blocks dangerous commands — rm -rf, force push, database drops, and others — before they execute.
Detect OS command injection via shell execution sinks where user-controlled input reaches system commands without proper sanitization.
Run external programs without ever building a shell string from untrusted input, using argument arrays that bypass the shell entirely.
Use when you have tandem MS/MS spectrum data in standard peak file formats (mzML, mzXML, or MGF) and need to cluster spectra based on precursor mass and fragment ion similarity.
Use when you have an existing mass spectrometry data file in a vendor or standard format (mzML, NetCDF, etc.) and need to convert it to mzPeak format for downstream analysis,…
Best practices for common command-line tools. Use when working with specific CLI commands like rm, tree, and other Unix utilities.
Advanced patterns for generating high-quality Claude Code commands. Used by /new-command.
Use when the user invokes a slash command like /create-pr, /commit, /fix-ci, or pastes command file content — routes to the right command with context inference and GitHub API…
Create automation command skills (slash commands) for Claude Code projects. Use when building `/slash-commands` that automate multi-step workflows - deploys, commits, releases,…
Intelligent command verification for documentation. Discovers all commands in markdown files, validates them using git diff-based cache invalidation, and ensures documentation…
Use when creating or editing a slash command in .agent-src.uncompressed/commands/ — frontmatter, numbered steps, safety gates — even when the user just says 'add a /command for X'.
CommandBar integration. Manage data, records, and automate workflows. Use when the user wants to interact with CommandBar data.
Use when building CLI tools with Commander.js - commands, options, arguments, and help text for Node.js command-line applications
Comprehensive guide for building Node.js command-line interfaces using Commander.js. Use when creating CLI tools with options, commands, subcommands, arguments, and help system…
Use when operating or verifying the user's authorized WindAnvil Commander Blade host through its signed tools, including diagnostics, restricted searches, Git metadata, and…
Create or edit a Claude Skill with guided assistance and best practices
Guide for creating and managing slash commands in Claude Code. Use when (1) creating new slash commands, (2) learning command syntax and features, (3) deciding between commands vs…
Generate production-ready Claude AI skills from documentation, GitHub repos, or PDFs using Skill Seekers with automated quality validation
Add an agent skill to an existing template
Use when you need to install the embedded project commands into command directories (.github/commands, .claude/commands, .cursor/command, .codex/commands), selecting the…
Use when you need to generate a checklist document with embedded commands inventory, following the embedded template exactly and producing INVENTORY-COMMANDS-JAVA.md in the…
Branch skill for building and improving commands. Use when creating new slash commands, adapting marketplace commands, validating command structure, working with $ARGUMEN — from…
Branch skill for building and improving commands. Use when creating new slash commands, adapting marketplace commands, validating command structure, working with $ARGUMEN — from…
Generate Claude AI skills from documentation, GitHub repos, or PDFs using Skill Seekers
CommBox integration. Manage data, records, and automate workflows. Use when the user wants to interact with CommBox data.
CommCare integration. Manage data, records, and automate workflows. Use when the user wants to interact with CommCare data.
Drafts a Commencement Date Memorandum confirming when obligations take effect under an executed agreement.
Drafts a U.S. commencement-date memorandum for commercial leases and related agreements, confirming the operative start date and its evidentiary basis.
Guidelines for self-explanatory code and meaningful documentation. Activate when working with comments, docstrings, documentation, code clarity, API documentation, JSDoc, or…
Deliver a defined feature pragmatically through a live Comment.io worklog: choose a direct PR or controlled lift, implement bounded deltas, use risk-scaled review receipts,…
Add meaningful inline comments to complex code. Use when documentation is lacking. — from satoshistackalotto/skills
Code comment guidelines. Remove redundant comments, add strategic ones explaining WHY not WHAT. Applied automatically when modifying code.
Use when the user asks how to write code comments, where to place them, or wants to review, reduce, rewrite, or relocate existing code comments. — from general/general-misc
Use when the user asks how to write code comments, where to place them, or wants to review, reduce, rewrite, or relocate existing code comments. — from general/general-misc
Apply proper indentation and spacing rules to code comments to enhance readability and maintain code visual structure.
Extract content ideas from your audience's comments, replies, and questions — scan note comments, X replies, and Instagram comments for pain points, questions, and content gaps.
Add or read comments on an OpenAnt task. Use when the agent wants to communicate with the task creator or worker, ask questions about a task, provide progress updates, give…
Monitor TikTok/Instagram comments, classify sentiment, auto-reply with FAQ answers, and DM high-intent commenters with LYNK affiliate links to convert engagement into sales.
Review the comments in the current diff against a production standard, in any programming language. Classifies each comment as KEEP, REWRITE or REMOVE and reports the result.
Review the code comments in a batch of work — a pull request, a branch, or the current diff — cutting changelog comments, references to PRs and issues, restatements of th — from…
Review the code comments in one change — a pull request, a branch, or the current diff — for the three ways a comment goes wrong: it has drifted from what the code now does, it…
Review the code comments in a batch of work — a pull request, a branch, or the current diff — asking of each whether it is true and useful to someone who cloned the repo — from…
Detect stale comments, outdated TODOs, doc rot -- comments that lie about the code
Deletes comments. Keeps only the five narrow categories that earn their place, flags the code that needed explaining as MUST KILL, and reports precise line ranges to cut.
You are a Comment.io agent. Read ~/.comment-io/agents/*.json for your handles and secrets. Fetch https://comment.io/llms.txt for the current API, local sync, identity, and…
Add or rewrite code comments with calibrated granularity so they explain intent, constraints, data meaning, contracts, and control-flow decisions instead of translating syntax.
How to strip redundant license headers, dead commented-out code, and verbose docstrings from source files before LLM ingestion, reducing input tokens by 40%.
Break public comments on an FDA draft guidance into discrete asks, each with a verbatim source span, the draft section it targets, a theme code from a human-approved codebook, and…