Prompts
Prompt engineering and templates
tooyoung:openclash-merger
by shiqkuangsan
"将 vless+reality 等新协议配置转换为带 ACL4SSR Full NoAuto 规则的配置文件，支持分组+分流，可直接上传 OpenClash 使用。触发词：合并 OpenClash、转换订阅、Clash 配置"
init-deep
by TechDufus
"Initialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any directory it reads, enabling true contextual guidance. Triggers on: '/init-deep', 'deep init', 'initialize deeply', 'setup claude deeply', 'refactor claude.md', 'migrate claude.md', 'nested claude', 'progressive disclosure'."
ralph-loop-init
by TechDufus
"Transform approved plans into ralph loop infrastructure. Triggers on: '/ralph-loop-init', '/ralph-init', 'setup ralph loop', 'generate ralph loop'. Creates .ralph/ directory with prd.json, loop.py, CLAUDE.md, and supporting files."
tooyoung:easy-openrouter
by shiqkuangsan
"Quickly test and compare LLM models via OpenRouter. Find the fastest/cheapest model, compare response quality. Trigger words: openrouter, test model, compare models, find fastest model, find cheapest model"
tooyoung:nano-banana-builder
by shiqkuangsan
"Build full-stack web applications powered by Google Gemini's Nano Banana & Nano Banana Pro image generation APIs. Use when creating Next.js image generation apps, text-to-image tools, or iterative image editors."
personal:expense-receipt
by shiqkuangsan
"AI 订阅报销统计。识别收据+发票，自动匹配最优发票组合，输出统计表和报销备注。触发词：报销统计、收据识别、统计报销、AI 订阅费用"
agent-audit
by ElliotJLT
When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.
geordie
by ElliotJLT
When activated, respond entirely in Geordie dialect from Newcastle upon Tyne. Use proper Geordie words, phrases, and grammar. Reference Newcastle United players, legends, and lore when making analogies or celebrating wins. Channel the spirit of St James' Park, The Entertainers, and Wor Jackie himself. Howay the lads!
rubric-creator
by reggiechan74
Professional-grade rubric creation skill with validity, reliability, and fairness controls. USE RUBRIC-CREATOR FOR: - Creating assessment frameworks for any domain - Building scoring systems with inter-rater reliability - Generating pilot testing and calibration materials - Converting existing rubrics to new domains Three modes: interactive (guided questionnaire), template (pre-built domains), example-based (adapt existing rubric). Includes: anchor examples, critical barriers, confidence flagging, bias review, maintenance lifecycle. See templates/ for detailed template definitions with anchor examples.
obsidian-vault-init
by ElliotJLT
Initialises an Obsidian vault for Claude Code workflows. Sets up folder structure, frontmatter conventions, templates, starter .base views, and a CLAUDE.md that describes the vault so future sessions understand it instantly. Activates on "set up obsidian", "init vault", "new vault", or first contact with an Obsidian project that has no CLAUDE.md.
stay-in-lane
by ElliotJLT
Before making changes, verifies they match what was actually requested. Activates when about to modify files, add features, or refactor code. Catches scope creep before it happens - no "while I'm here" improvements.
obsidian-session-sync
by ElliotJLT
End-of-session ritual that syncs Claude Code session artifacts to an Obsidian vault. Chains breadcrumbs, retrospective, note creation, and daily driver into a single flow. Creates session notes, updates daily note, and leaves breadcrumbs. Activates on "sync to obsidian", "save session", "end session", or when user wraps up significant work in a vault-connected project.
skill-forge
by ElliotJLT
When Claude discovers a non-obvious solution, unusual pattern, or hard-won insight during a session, automatically forge it into a new skill. Don't just note the learning - create the actual skill file so future sessions benefit immediately. This is the flywheel: work → discovery → skill → smarter future sessions → repeat.
pb-new-agent-session
by agentproto
Spawn one worker agent on the agentproto daemon, drive it with a brief and follow-ups to a verified result, then tear it down cleanly. Trigger when delegating a single task - 'spawn an agent', 'delegate this to a worker', 'run an agent to completion', 'drive an agent session'.
managing-artifacts
by axiomantic
Use when generating documents, reports, plans, audits, or when asked where to save files. Triggers on "save report", "write plan", "where should I put", "project-encoded path"
ap-spawn-agent
by agentproto
Spawn a new agentproto agent session (claude-code, hermes, ...) with a model, cwd, prompt, and optional MCP tool access. Use when the user says "spawn an agent", "start a session", "launch claude-code on this task", "run hermes in the background", or "kick off a worker". Also covers listing already-running sessions before spawning a duplicate.
ap-workflows
by agentproto
Run multi-stage session pipelines with agentproto workflows — workflow_start with barrier-gated stages of concurrent steps, sessionRef to reuse earlier output, workflow_status/cancel/retry, workflow_run_file for AIP-15 WORKFLOW.md, and workflow_escalation_resolve for human answers. Trigger when asked to pipeline agents, fan out stages, run a WORKFLOW.md, or retry a failed run.
council
by rube-de
Consult external AI council (Gemini, Codex, Qwen, GLM-5) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough review".
avp
by portofcontext
Use this skill for ANY work on AVP (Agent Voyager Project): agents, supervisor Commissions, conformance cases, or debugging AVP runs. AVP wires agents (drive an LLM, emit events) to supervisors (declare environment).
pydantic-ai-agents
by Fuenfgeld
"Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection."
pydantic-evals
by Fuenfgeld
"Test and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing. Use when the user wants to: (1) Create evaluation datasets with test cases for AI agents, (2) Define evaluators (deterministic, LLM-as-Judge, custom, or span-based), (3) Run evaluations and generate reports, (4) Compare model performance across experiments, (5) Integrate evaluations with Pydantic AI agents, (6) Set up observability with Logfire, (7) Generate test datasets using LLMs, (8) Implement regression testing for AI systems."
agentproto-llm-endpoint
by agentproto
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public
pb-supervise-parallel-mission
by agentproto
Run N parallel worker agents on disjoint file/topic ownership and fan their results into one verified deliverable. Trigger when supervising - 'I am the supervisor', 'spawn parallel workers', 'fan-in several agents', 'decompose this mission and delegate'.
ap-prompt-agent
by agentproto
Send a follow-up prompt to a live agentproto session, interrupt its in-flight turn, switch its model/effort/posture without restarting, or manage its queued prompts. Use when the user says "tell the agent to also...", "interrupt and redirect it", "switch that session to a cheaper model", "promote/skip that queued prompt", or "cancel that queued message".