AI & ML

britt Bundle

Use when starting a new feature, project, or bug fix in a repository that uses SGAI - interactively composes a GOAL.md with agent flow graph, model preferences, completion gate, and outcome-based success criteria

windschord Bundle

Orchestrates multi-step tasks autonomously using a 3-tier agent hierarchy (Director/Manager/Worker). Use when user says "run this end-to-end", "handle everything", "execute all tasks", or needs parallel task execution with queuing, course correction, and session resume. Provides FIFO task queue, escalation policy, git worktree isolation, and context persistence across agent sessions.

shunkakinoki Bundle

Resume a third-party coding-agent session from a local transcript, path, or session id.

shunkakinoki Skill

Structured problem-solving with Serena MCP

shunkakinoki Skill

Locate and read Muse Code's OWN session logs — the current session or a prior one. Use when the user asks to pull context from, continue, summarize, or inspect a previous Muse Code (tbh/muse) session, asks to restore or recover work that was lost, wiped, or overwritten and might survive in an earlier session's log, references an earlier session's id, log, tail, or output, or asks where Muse sessions are stored. Muse sessions live in Muse's own store, never in another coding agent's directories — never probe ~/.claude, ~/.codex, or ~/.grok for Muse context, even when quoted content mentions them; for another agent's (Claude Code/Codex/Grok) session, use the import skill.

shunkakinoki Skill

Explain and safely update persistent Muse Code product settings, including model/reasoning effort and /settings options. Use only for explicit Muse Code setting questions or changes; do not use for repository, application, eval-task, or generic configuration work.

scottermonk Skill

Compact the current conversation into a handoff document for another agent to pick up. Use this skill whenever the user asks for a handoff, continuation note, session summary for another agent, compacted context, or a document that lets a fresh agent continue the work. Load with read_file on .kilocode/skills/handoff/SKILL.md (ignore the absolute path in the location tag).

krafton-ai Skill

Create or refine KiraClaw/Codex skills as concise SKILL.md packages. Trigger on: "make a skill", "create a skill", "update this skill", "seed skill", "default skill", or when the user wants reusable agent workflow instructions instead of one-off prompt text.

krafton-ai Skill

Make channel-facing speak output sound natural and easy to read. Trigger on: preparing a Slack, Telegram, or Discord reply with speak; rewriting markdown-heavy or AI-sounding prose before delivery; or when a response feels too formal, too structured, or too obviously model-written for a chat conversation.

nibzard-skills-kit Bundle

Create new Agent Skills interactively or from templates. Use when user wants to create, generate, scaffold, or build a new skill, or mentions creating skills, writing skills, skill templates, skill development.

chujianyun Bundle

微信公众号关注二维码生成助手。当用户要根据公众号 ID、微信号、原始 ID 或 `gh_...` 生成公众号二维码、下载成本地图片并在 Agent/Codex 聊天里显示，或不知道如何在微信里找到公众号 ID、需要操作引导图时使用此技能。只适用于微信公众号二维码，不用于小程序码、个人微信二维码或企业微信二维码。

tilmon-engineering Skill

Use when user wants to create new autonomy branch with dedicated worktree for parallel agent workflows

scottermonk Bundle

Use when a coding-capable agent is starting or finishing implementation work. At start, clarify intent, scope, context, and verification strategy. At finish, run appropriate quality checks, assess impact, capture lessons, and produce a concise completion report. Trigger for both implementation intake and implementation closeout. Load with read_file on .kilocode/skills/coding-lifecycle/SKILL.md (ignore the absolute path in the location tag).

scottermonk Skill

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing code, reviewing code, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Load with read_file on .kilocode/skills/coding-guidelines/SKILL.md (ignore the absolute path in the location tag).

scottermonk Bundle

Call a Hermes agent from Kilo Code via the local chat completions API. Use for web scraping, browser automation, and research tasks that Hermes handles better (saved credentials, browser tools, web search). Load with read_file on .kilocode/skills/hermes-api-client/SKILL.md (ignore the absolute path in the location tag).

lycfyi Skill

Smart Discord sync - automatically detects tokens and permissions to choose the optimal sync method. Use when user asks to sync Discord messages.

lycfyi Bundle

Show unified status of all community platforms. Use when user wants to check their setup, see sync status, or get an overview.

lycfyi Bundle

Community management best practices and patterns. Automatically loaded when handling community-related tasks to provide domain expertise.

nibzard-skills-kit Bundle

AI-Powered Security Testing Toolkit - Professional penetration testing scripts for discovering vulnerabilities, analyzing application structure, and generating context-aware security tests. All scripts return structured JSON for agent consumption.

tilmon-engineering Skill

Use when interacting with a TypeDB 3.x database via the typedb MCP tools (typedb-query, typedb-database_schema, etc.) - covers schema-first workflow, transaction types, TypeQL 3.x syntax (which differs materially from 2.x), and the most common failure modes

borkweb Skill

Compact the current conversation into a handoff document for another agent to pick up.

borkweb Skill

Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.

borkweb Bundle

Assess whether compacting or clearing the current session is worth it right now, and whether a reinit-ready handoff that survives /clear would carry real value. Not a threshold nag — it X-rays context composition (how much is stale vs. still load-bearing), which only the agent can see. Use when the user says "session budget", "should I compact", "should I clear", "is this session getting heavy", "token budget", invokes /session-budget, or when the budget hook requests a proactive assessment.

greyhaven-ai-claude-code-config Bundle

Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use when testing prompts, validating outputs, comparing models, or when user mentions 'evaluation', 'testing LLM', 'rubric', 'LLM-as-judge', 'output quality', 'prompt testing', or 'model comparison'.

greyhaven-ai-claude-code-config Bundle

Python Test-Driven Development expertise with pytest, strict red-green-refactor methodology, domain-first modeling (DDD), principled DRY discipline, FastAPI testing patterns, and Pydantic model testing. Use when implementing Python features with TDD, writing pytest tests, testing FastAPI endpoints, developing with test-first approach, modeling domain concepts, refactoring duplication, or when user mentions 'Python TDD', 'pytest', 'FastAPI testing', 'red-green-refactor', 'Python unit tests', 'test-driven Python', 'domain modeling', 'value object', 'ubiquitous language', 'DRY', or 'Python test coverage'.

greyhaven-ai-claude-code-config Bundle

Design effective MCP tools and Claude Code integrations using the consolidation principle. Fewer, better-designed tools dramatically improve agent success rates. Use when creating MCP servers, designing tool interfaces, optimizing tool sets, or when user mentions 'tool design', 'MCP', 'fewer tools', 'tool consolidation', 'tool architecture', or 'tool optimization'.

henkisdabro Bundle

Chrome DevTools MCP setup and live-browser debugging for visual app inspection, console/network/performance triage, and automation. Use when the user asks to set up browser debugging, launch Chrome with DevTools, configure chrome-devtools-mcp, see what my app looks like, take screenshots of my web application, debug console errors, inspect network requests and API responses, measure Core Web Vitals or page performance, run a Lighthouse audit, test button clicks or form submissions, automate browser interactions, fill out forms programmatically, simulate user actions, emulate mobile devices or slow networks, capture DOM snapshots, execute JavaScript in the browser, or troubleshoot Chrome DevTools MCP connection issues. Supports Windows, Linux, and WSL2 environments. Do NOT use for headless CI test runs - use Playwright tests directly. Do NOT use for Selenium/Puppeteer setup.

whu125 Bundle

Build and install Soul Code persona skills from the bundled persona dataset. Use when the user wants to generate, install, list, or switch to stylized coding personas such as CTRL, BOSS, LOVE-R, or MUM.

greyhaven-ai-claude-code-config Bundle

Master TDD orchestration with multi-agent coordination, strict red-green-refactor enforcement, a Layer-0 domain-modeling gate (DDD) that blocks Red until concepts are named in domain vocabulary and primitives promoted to types, and principled DRY enforcement at Refactor (same-concept repetition ≥3 sites only). Automated test generation, coverage tracking, >90% coverage quality gates. Supports Claude Teams for parallel TDD workflows with plan approval gates, or falls back to sequential subagent coordination. Use when implementing features with TDD workflow, coordinating multiple TDD agents, enforcing test-first development, modeling a domain, orchestrating TDD teams, or when user mentions 'TDD workflow', 'test-first', 'TDD orchestration', 'multi-agent TDD', 'domain modeling', 'value object', 'ubiquitous language', 'DRY', 'test coverage', or 'red-green-refactor'.

greyhaven-ai-claude-code-config Bundle

Master 26 documented prompt engineering principles for crafting effective LLM prompts with 400%+ quality improvement. Includes templates, anti-patterns, and quality checklists for technical, learning, creative, and research tasks. Use when writing prompts for LLMs, improving AI response quality, training on prompting, designing agent instructions, or when user mentions 'prompt engineering', 'better prompts', 'LLM quality', 'prompt templates', 'AI prompts', 'prompt principles', or 'prompt optimization'.

ibutters Bundle

This skill should be used when the user asks to "create a prompt", "optimize a prompt", "improve this prompt", "engineer a prompt", "prompt engineering best practices", "make this prompt better", "recommend a model", "which model should I use", "best model for", "GPT vs Claude", "Opus vs Sonnet", "Haiku vs Sonnet", "analyze prompt quality", "fix my prompt", "prompt for Claude", "prompt for GPT", or needs help with prompt engineering techniques, model selection, or prompt optimization for any LLM (Claude Opus/Sonnet/Haiku 4.5, GPT 5.1/Codex, Gemini Pro 3.0).

zot24 Bundle

Expert on Pi (pi.dev, @earendil-works/pi-coding-agent) — the minimal terminal coding harness. Use when extending or improving Pi, adding a custom provider, writing Pi extensions, Pi skills, Pi themes, or a pi package, forking pi-mono, working in pi-agent-core, pi-ai, pi-coding-agent, or pi-tui, running Pi from source, or debugging the agent loop. Triggers on pi.dev, pi-coding-agent, pi-agent-core, pi-ai, custom provider, pi package, fork pi-mono, extend Pi, improve Pi.

zot24 Bundle

Run a control tower over a fleet of herdr agents — delegate every project task to a pane, dispatch from a spec file, watch a completion marker, and verify independently before calling anything done. Includes acceptance gates — a gates file of CHECK/EXPECT/EVIDENCE outcomes verified by a vendored checker, so a completion marker carries proof and "done" is an exit code instead of a claim. Use when operating or staffing a herdr fleet, writing a delegation spec, deciding whether an agent is finished, writing acceptance criteria, or verifying a delivered job. Use at session start; when the user asks for status, catalog, an unpaid ask, or to reconvene; when choosing a plane; when escalating, handing off, or seating a write on a worktree. Triggers on herdr, control tower, tower, fleet, agent pane, marker, land-check, idle vs done, definition of done, gates file, gate-check, GATES.md, MARKER_OK, CHECK/EXPECT, unlazy, session start, catalog, unpaid ask, reconvene, planes, escalate, handoff, worktree, auto-wiki.

ooooooooooooooooooop Bundle

按任务规模与风险选择执行深度，避免流程过度或风险失控。用于判断代码、配置、文档和工作流请求应采用小型直接修改、中型计划变更、大型分阶段执行，还是高风险流程；高风险场景包括安装工具、修改全局配置、添加 MCP 服务或 hooks、删除文件、修改权限和使用浏览器登录状态。

ooooooooooooooooooop Bundle

Personal AI Infrastructure 多设备生命周期同步总入口：一句“同步一下我的 Personal AI”自动判断 PULL/MERGE/NO ACTION/REVIEW/BLOCKED（AUTO_SYNC），覆盖 agent-tools、personal-ai-state（curated + Dynamic Memory 合并）、项目仓库、runtime refresh 与新设备 Fresh Restore；同时保留 DSH 四层环境上传/更新/体检/复现作为子步骤。只自动处理确定安全的变更，冲突与 dirty 一律留给人工；commit/push 受 canonical ownership lease 与 receipt 约束。

datarails Skill

Profile Datarails Finance OS table fields — how is a field distributed? Per-field statistics over the table's whole history — ranges, approximate percentiles, null rates, cardinality interpretation, and range-outlier flags — no severity ranking, no period scope. The MCP tools return baseline aggregates (SUM/AVG/MIN/MAX/COUNT for numeric, distinct-value samples for categorical); this skill derives the statistics client-side. For severity-ranked data-quality findings scoped to the latest fiscal year, use the anomalies skill.