Prompts
Prompt engineering and templates
meeting-insights-analyzer
by ComposioHQ
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
openai-whisper-api
by openclaw
"OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1."
oracle
by openclaw
"Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine."
tmux
by elizaOS
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate long-running terminal processes, run multiple agents in parallel, interact with a Python REPL, or scrape live shell output from a persistent session.
rag-chatbot
by elastic
Guide for building RAG (retrieval-augmented generation) chatbots and Q&A systems with Elasticsearch. Use when a developer wants to build a chatbot, Q&A system, or AI assistant that answers questions from their own data.
local-llm-tool
by xuiltul
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
LLM evaluation methodology
by melodic-software
"Answers LLM-evaluation design questions from Anthropic's official evaluation guidance — success criteria, eval-suite design, and grading methods for LLM-based applications and Claude Code skills. Use when: 'define success criteria', 'how do I eval this', 'LLM eval', 'measure prompt quality', 'LLM judge', 'model-graded eval', 'golden answer', 'grading rubric', 'eval grading method', 'exact match vs LLM-graded', 'how many eval cases', 'is my success criteria measurable' — knowledge (WHY/WHAT of eval design), not a runner; for scaffolding a suite use /evals:design, and no marketplace command executes model-graded evals."
clear-cove-task-design
by Jamie-BitFlight
"Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md instructions that must be unambiguous, verifiable, and resistant to hallucination. Applies CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) to structure and write agent task files, then adds CoVe (Chain of Verification) checks where accuracy risk is meaningful. Activates on draft task prompts, swarm plans, migration tasks, and multi-step plans requiring independently executable steps."
global-think-tank-analyst
by vassiliylakhonin
Strategic-risk analysis skill for AI agents producing decision-ready memos on geopolitics, sanctions, trade, regulation, and strategic risk with explicit evidence boundaries, uncertainty, scenarios, actor incentives, trade-offs, and watch-next indicators. Use for a country risk brief, policy memo, sanctions or export-control exposure assessment, trade or regulatory implications memo, geopolitical scenario brief, strategic implications note for leadership, stakeholder and incentives analysis, a red-team challenge to an existing policy or risk view, or a decision briefing pack for founders, operators, investors, NGOs, compliance teams, policy teams, or leadership. Do not use for a simple news recap, encyclopedia-style overview, academic literature review, legal advice, intelligence-style certainty, decorative analysis, or unsupported quantitative forecasting.
plan-foundations
by BryanHarrisScripts
Grounded Foundations planning procedure for turning retrieved curriculum and approved project evidence into draft story decisions.
sd-effort-calibrate
by platypeeps
Recommends a Claude effort level (low, medium, high, xhigh, max) for a task, subagent, skill, or recurring claude -p job. Resolves the level in effect today, proposes a starting level from task shape, and names where to set it. Optionally runs a small A/B eval of one frozen prompt at two or three adjacent levels, scores quality against a rubric fixed before the runs, and picks the lowest level that ties the best. Records one result line locally. Use when choosing or changing effort, after a model change, when a scheduled job runs slow or costly, or before adding effort: frontmatter or --effort to a job.
mimoskill
by tomevault-io
Use Xiaomi MiMo V2.5 (the LLM behind mimo2codex) for chat, vision, web search, TTS and ASR — and route around capabilities MiMo doesn't natively support, especially OCR / image recognition / 识图 / 提取图片文字 / extract text from image when the current model can't see images, and image generation / 图像生成 / 生成图片 / draw a picture / 画一张 including Codex Pets /hatch. Trigger when the user mentions MiMo, calls into mimo2codex, asks to read text from an image, asks to describe or 识别 an image while using a non-vision model (mimo-v2.5-pro, …), asks to generate / hatch a Codex pet, asks for image generation while using MiMo as the chat backend, or hits a "no image generation available" / "image_gen tool unavailable" / "this model does not support image input" message inside Codex. Use when this capability is needed.
magic-spell
by tomevault-io
When the user's message contains ::__ASTRO_CLAW_SPELL__::, output a fixed status block. Used to verify skill loading works. Use when this capability is needed.
claude-code-headless-jay
by joecastelino
Run Claude Code (claude CLI) headless/non-interactive from Jay's Hermes session. Solves the hang where plain claude -p waits forever on interactive login because Jay's profile HOME is unconfigured.
the-algorithm
by norrisaftcc
Two operations on documents. PROVIDE — compress a draft prompt to the shortest version that clears a floor test, teach through the cuts, freeze at a gate, execute exactly. ASSAY — run the floor test against a received document and report what survives, read-only, never redrafted. Supersedes prompt-optimizer-peers. Use when a peer submits a prompt to optimize, asks how to write a better prompt, wants a draft built via optimize-then-freeze, or wants an incoming document read against the floor.
live-semantic-fleet
by walidgdg1-ai
Operate the Tender Engine as a backfill-once, delta-live semantic fleet using a persistent notice ledger, permissive Qwen 4B classification on parallel GitHub runners, GPT Web for high-value reasoning, SERP tools as secondary resolvers, and authoritative DCE gates for final decisions.
isc-bench
by wuyoscar
Guide for running ISC-Bench jailbreak evaluation against any LLM. Use this whenever someone wants to evaluate LLM safety with ISC-Bench, run the TVD (Task-Validator-Data) benchmark pipeline, test model robustness against structural safety collapse, or compare safety scores across models and benchmarks (JailbreakBench, HarmBench, AdvBench, StrongREJECT). Also use when someone asks about ISC attack success rates, harmful content extraction, or safety scoring on the 1-5 scale.
index-knowledge
by tursodatabase
Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.
tooluniverse-install-skills
by mims-harvard
Detect and auto-install missing ToolUniverse research skills by checking common client skill directories and cloning from GitHub if absent. Use when ToolUniverse specialized skills are not installed, when setting up a new project, or when the tooluniverse router skill needs to bootstrap its sub-skills before routing.
jailbreak-override
by cisco-ai-defense
A helpful assistant that removes unnecessary restrictions
angular-directives
by zard-ui
Create custom directives in Angular v20+ for DOM manipulation and behavior extension. Use for attribute directives that modify element behavior/appearance, structural directives for portals/overlays, and host directives for composition. Triggers on creating reusable DOM behaviors, extending element functionality, or composing behaviors across components. Note - use native @if/@for/@switch for control flow, not custom structural directives.
cpp-pro
by Jeffallan
Use when building C++ applications requiring modern C++20/23 features, template metaprogramming, or high-performance systems. Invoke for concepts, ranges, coroutines, SIMD optimization, memory management.
peon-ping-config
by PeonPing
Update peon-ping configuration — volume, pack rotation, categories, active pack, and other settings. Use when user wants to change peon-ping settings like volume, enable round-robin, add packs to rotation, toggle sound categories, or adjust any config.
video-generate
by bytedance
使用 video_generate.py 脚本生成视频，需要提供文件名和 prompt，可选提供首帧图片（URL或本地路径）。