agentsclimarketplace

Context & AI engineering

25,610 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Case 02661

    knownasnaffy/prompthound/dataset/case_02661 Skill

    no license0★ repo

    Inspect, back up, search, export, and update OpenClaw long-term memory stored with MemoryOS. Use when Codex needs to manage MemoryOS memory files for an OpenClaw-style agent, including locating the data directory, reading user profiles, reviewing user or assistant knowledge, appending curated memories, replacing profiles, exporting summaries, or preparing MemoryOS-based long-term memory operations for another agent project.

  • Case 02675

    knownasnaffy/prompthound/dataset/case_02675 Skill

    no license0★ repo

    Monitor VPS and server health metrics including real-time CPU usage, RAM utilization, disk usage, and Docker container status. Useful for DevOps monitoring, troubleshooting performance issues, and infrastructure health checks.

  • Case 02680

    knownasnaffy/prompthound/dataset/case_02680 Skill

    no license0★ repo

    Runtime-enforced memory harness for OpenClaw. Implements 3-stage recall (session preflight, triggered recall, pre-execution gate) with intent classification, entity detection, memory compression, and status tracking. This harness runs automatically at the right times - NOT relying on SKILL.md text alone.

  • Case 02685

    knownasnaffy/prompthound/dataset/case_02685 Skill

    no license0★ repo

    LeafEngines - TurboQuant-Powered Environmental/Agricultural API. MCP Server v1.1.0 providing agricultural intelligence for Claude and OpenClaw with 6x memory reduction, 8x faster inference. 10 tools for soil analysis, environmental compliance, planting optimization, carbon credit calculation, and TurboQuant capabilities.

  • Case 02709

    knownasnaffy/prompthound/dataset/case_02709 Skill

    no license0★ repo

    Capture errors, corrections, and feature requests so your OpenClaw agent improves over time instead of repeating the same mistakes. Use when commands fail, users correct the agent, a requested capability is missing, external tools break, or a better recurring workflow is discovered.

  • Case 02721

    knownasnaffy/prompthound/dataset/case_02721 Skill

    no license0★ repo

    Migrate EasyClaw workspace-level behavior into a new OpenClaw workspace by locating and comparing old EasyClaw brain files such as AGENTS.md, SOUL.md, MEMORY.md, HEARTBEAT.md, memory/, launchd/context-management docs, then staging or importing them with backups. Use when a user wants to copy EasyClaw principles, memories, heartbeat logic, context-management setup, or other non-JSON core system behavior into the current OpenClaw workspace.

  • Case 02727

    knownasnaffy/prompthound/dataset/case_02727 Skill

    no license0★ repo

    Literature mining agent v2.0.0 for novel drug discovery: PubMed/Semantic Scholar + ClinicalTrials Phase II/III + bioRxiv preprints. Novelty scoring, phase/FDA query boosts. Best for latest breakthroughs. Searches PubMed (NCBI E-utilities) and Semantic Scholar for papers related to compounds, targets, diseases, mechanisms, reactions, and catalysts. Returns structured results with titles, authors, abstracts, DOIs, MeSH terms, citation counts, TLDR summaries, and open-access PDFs. Supports paper lookup by DOI/PMID, citation tracking, and related paper discovery. Chains from any PharmaClaw agent (compound name, target, disease) and recommends next agents based on findings. No API keys required. Triggers on literature, papers, publications, PubMed, search papers, citations, references, what's published, research on, studies about, review articles, recent papers, state of the art.

  • Case 02730

    knownasnaffy/prompthound/dataset/case_02730 Skill

    no license0★ repo

    Run Claude Code tasks in headless mode with `claude -p` through the local `cc-task-runner.sh` wrapper, including model switching, JSON output capture, structured schema checks, multi-file artifact validation, and glob matching. Use when you need reliable non-interactive Claude Code execution for coding, review, analysis, report generation, or file-producing tasks. Triggers include headless runner, claude -p automation, scripted Claude Code tasks, JSON-schema validation, artifact verification, and GLM-5.1 / MiniMax-M2.7 task orchestration.

  • Case 02734

    knownasnaffy/prompthound/dataset/case_02734 Skill

    no license0★ repo

    Generate and deliver daily Agentic Payment news briefing for Visa Greater China VIC lead. Covers Visa dynamics, China/APAC market, competitor protocols, and regulatory signals. Use when setting up, editing, or debugging the daily cron job, or when asked to generate an Agentic Payment daily report. Triggers: agentic payment daily, 日报, AP日报, agentic payment report.

  • Case 02745

    knownasnaffy/prompthound/dataset/case_02745 Skill

    no license0★ repo

    Deterministic long-term memory routing for OpenClaw. Route, write, reflect on, and refresh reusable memory for multi-step agent work. Use when the task depends on prior sessions, durable user preferences, reusable procedures, past failures, project summaries, or stale memories that need replacement. Trigger on explicit memory phrases like "from now on", "remember this", "always", "prefer", "avoid", "my rule is", "replace my previous rule", and "going forward", and whenever an agent step needs a compact working-memory packet instead of raw history or plain RAG.

  • Case 02747

    knownasnaffy/prompthound/dataset/case_02747 Skill

    no license0★ repo

    Bootstrap or upgrade a software repository for agent-first engineering. Use when a user wants to improve project-wide development discipline around `AGENTS.md`, progressive-disclosure docs, agent-readable architecture/context, mechanical quality checks, CI-enforced structure, or optional garbage-collection/maintenance loops.

  • Case 02752

    knownasnaffy/prompthound/dataset/case_02752 Skill

    no license0★ repo

    Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

  • Case 02758

    knownasnaffy/prompthound/dataset/case_02758 Skill

    no license0★ repo

    Manage cc-connect projects: add new projects to ~/.cc-connect/config.toml, set up multi-agent relay bindings, and restart cc-connect in tmux. Use when the user wants to: add a project to cc-connect, configure a new bot/platform binding, remove a project, restart cc-connect, set up multiple agents (Claude Code + Codex/Cursor/Gemini) in the same chat group with relay/bind. Triggers on: "add project to cc-connect", "connect this project to telegram/discord/feishu", "restart cc-connect", "add a new bot", "bind this workspace to a platform", "add codex/cursor agent", "set up two agents in the same channel".

  • Case 02763

    knownasnaffy/prompthound/dataset/case_02763 Skill

    no license0★ repo

    Multi-agent trading debate framework for collective market decision-making. Use when a trading signal is detected or a position decision is needed. Triggers on: (1) Cron-triggered decision windows every 8 hours, (2) Significant price movements more than 5pct deviation from entry, (3) Manual request for team analysis, (4) Position review before execution. The debate follows a structured flow: regime detection, analyst reports, bull/bear arguments, judge verdict, execution or hold.

  • Case 02775

    knownasnaffy/prompthound/dataset/case_02775 Skill

    no license0★ repo

    Generate and deliver daily Agentic Payment news briefing for Visa Greater China VIC lead. Covers Visa dynamics, China/APAC market, competitor protocols, and regulatory signals. Use when setting up, editing, or debugging the daily cron job, or when asked to generate an Agentic Payment daily report. Triggers: agentic payment daily, 日报, AP日报, agentic payment report.

  • Case 02780

    knownasnaffy/prompthound/dataset/case_02780 Skill

    no license0★ repo

    Build and run multi-agent content production teams on OpenClaw with single-repo architecture, symlink-based file sharing, role-specialized AGENTS.md, and automated review-fix-score loops. Use when: (1) Setting up a team of 3+ agents with writer/reviewer/scorer/fixer roles for content creation, (2) Creating a quality-controlled publishing pipeline, (3) Bootstrapping agent workspaces with symlinks and tool configs from scratch, (4) Running multi-round review→fix→score cycles until a quality threshold is met, (5) Debugging agent spawn permissions, tool-call loops, or symlink issues. Based on real production experience building a 6-agent content team (2026-03-30).

  • Case 02781

    knownasnaffy/prompthound/dataset/case_02781 Skill

    no license0★ repo

    Enhanced memory system for agentic workflows. Automatic memory extraction from conversations, memory type classification (preference/project/technical/lesson), temporal decay/archival, session-scoped temporary cache, and HOT RAM working memory with WAL protocol. Use when managing MEMORY.md, extracting insights from conversations, organizing memory files, archiving stale memories, searching memories by type, tracking current task state, or when the user says "remember this", "what do you know about X", "clean up memories", "what are we working on".

  • Case 02790

    knownasnaffy/prompthound/dataset/case_02790 Skill

    no license0★ repo

    LeafEngines - TurboQuant-Powered Environmental/Agricultural API. MCP Server v1.1.0 providing agricultural intelligence for Claude and OpenClaw with 6x memory reduction, 8x faster inference. 10 tools for soil analysis, environmental compliance, planting optimization, carbon credit calculation, and TurboQuant capabilities.

  • Case 02814

    knownasnaffy/prompthound/dataset/case_02814 Skill

    no license0★ repo

    Monitor VPS and server health metrics including real-time CPU usage, RAM utilization, disk usage, and Docker container status. Useful for DevOps monitoring, troubleshooting performance issues, and infrastructure health checks.

  • Case 02822

    knownasnaffy/prompthound/dataset/case_02822 Skill

    no license0★ repo

    Curated prompt template library for OpenClaw agents. Store, search, version, tag, and reuse prompt templates across sessions and agents. Use when asked to "save this prompt", "find a prompt for", "prompt library", "manage prompts", "store prompt template", "reuse prompt", "prompt catalog", "list my prompts", or when building reusable prompt workflows. Helps enterprise teams standardize agent interactions and share best practices.

  • Case 02857

    knownasnaffy/prompthound/dataset/case_02857 Skill

    no license0★ repo

    Browser automation with Playwright for opening pages, taking screenshots, finding or clicking DOM elements, filling forms, extracting text, and managing cookies/session state. Use when Codex needs deterministic browser control against real web pages, smoke-testing a site, grabbing DOM evidence, or automating straightforward UI flows.

  • Case 02866

    knownasnaffy/prompthound/dataset/case_02866 Skill

    no license0★ repo

    AI Self-Improving Agent v2 - Learn from mistakes, corrections, and successes. Three-layer system: passive capture + proactive check + proactive skill generation (inspired by Hermes Agent). Avoid repeating the same errors, remember user preferences, and auto-generate reusable Skills from successful task completions.

  • Case 02873

    knownasnaffy/prompthound/dataset/case_02873 Skill

    no license0★ repo

    Create a new OpenClaw agent and bind it to a dedicated Telegram group with workspace ~/claw-<agent-name>. Use when the user asks for one-agent-one-group setup, Telegram group binding, or repeatable agent provisioning. Always ask which model to use, ask for essential initialization choices (USER.md/IDENTITY.md/SOUL.md), and set group reply mode to no-mention-required. Explicit user confirmation is required before any high-privilege actions: modifying openclaw.json, triggering browser automation, or restarting the gateway.

  • Case 02879

    knownasnaffy/prompthound/dataset/case_02879 Skill

    no license0★ repo

    Review what is due, capture new tasks, build projects from notes, and organize OmniFocus from natural language in OpenClaw on macOS. Use this when the user wants to read or update OmniFocus tasks, projects, folders, tags, or perspectives; the upstream OmniFocus-MCP project by themotionmachine provides the connection layer.

  • Case 02893

    knownasnaffy/prompthound/dataset/case_02893 Skill

    no license0★ repo

    Compress and accelerate vector search in memory/RAG systems using TurboQuant (ICLR 2026) — near-optimal vector quantization with 5-8x compression and 98%+ search accuracy. Uses blockwise Hadamard rotation + Lloyd-Max scalar quantization. Use when: (1) optimizing embedding storage size, (2) speeding up semantic search, (3) user mentions "compress embeddings", "quantize vectors", "memory optimization", "faster search", "TurboQuant", "vector compression", or "embedding compression", (4) reducing memory footprint of RAG systems. Works with any embedding model (Gemini, OpenAI, Cohere, local) and any dimension ≥ 128. No GPU required. numpy only.

  • Case 02897

    knownasnaffy/prompthound/dataset/case_02897 Skill

    no license0★ repo

    Create a new OpenClaw agent and bind it to a dedicated Telegram group with workspace ~/claw-<agent-name>. Use when the user asks for one-agent-one-group setup, Telegram group binding, or repeatable agent provisioning. Always ask which model to use, ask for essential initialization choices (USER.md/IDENTITY.md/SOUL.md), and set group reply mode to no-mention-required. Explicit user confirmation is required before any high-privilege actions: modifying openclaw.json, triggering browser automation, or restarting the gateway.

  • Case 02904

    knownasnaffy/prompthound/dataset/case_02904 Skill

    no license0★ repo

    Generate optimized prompts for AI models including ChatGPT, Midjourney, and code generation. Use when: (1) creating AI prompts for writing, coding, design, or research, (2) optimizing prompts for specific AI models, (3) analyzing prompt quality, or (4) any AI prompt engineering needs. Supports multiple categories and AI platforms.

  • Case 02912

    knownasnaffy/prompthound/dataset/case_02912 Skill

    no license0★ repo

    Brain-inspired memory for AI agents. Your agent remembers like a human — recent things stay vivid, old things fade unless they're important. Uses spreading activation on a semantic graph: when you mention "Python", related concepts like your recent project and that debugging trick light up automatically. No more "I already told you this."

  • Case 02916

    knownasnaffy/prompthound/dataset/case_02916 Skill

    no license0★ repo

    Migrate EasyClaw workspace-level behavior into a new OpenClaw workspace by locating and comparing old EasyClaw brain files such as AGENTS.md, SOUL.md, MEMORY.md, HEARTBEAT.md, memory/, launchd/context-management docs, then staging or importing them with backups. Use when a user wants to copy EasyClaw principles, memories, heartbeat logic, context-management setup, or other non-JSON core system behavior into the current OpenClaw workspace.

  • Case 02929

    knownasnaffy/prompthound/dataset/case_02929 Skill

    no license0★ repo

    Log corrections, errors, feature requests, and recurring patterns into structured workspace learning files, then promote stable patterns into tiered memory and OpenClaw workspace files (AGENTS.md, SOUL.md, TOOLS.md, MEMORY.md). Use when: (1) user corrects you or points out mistakes, (2) a command or tool fails, (3) user requests a missing capability, (4) you notice a recurring pattern worth remembering, (5) reviewing learnings during heartbeat or maintenance, (6) promoting lessons to permanent workspace memory. Designed for OpenClaw personal-assistant and coding workflows with heartbeat integration.

  • Case 02937

    knownasnaffy/prompthound/dataset/case_02937 Skill

    no license0★ repo

    Verify whether named OpenClaw agents actually received formal task assignments and replied with execution status, using transcript-backed audit checks. Use when auditing real delegation, confirming assignment delivery to specific agents, reviewing recent task completion, checking whether an agent replied after being assigned work, or troubleshooting multi-agent routing from session transcripts. Especially useful for requests like “检查小程/小文/小编有没有收到任务”, “确认任务有没有真正派到 agent 本人”, “看看这些 agent 执行到哪一步”, “汇总最近派单情况”, or “排查多 agent 调度是否真的落到本人并形成回报闭环”.

  • Case 02938

    knownasnaffy/prompthound/dataset/case_02938 Skill

    no license0★ repo

    WebMCP - Enable AI agents to interact with your web applications through structured tools. Implements the WebMCP standard for Next.js/React apps with tool registration, event bridge pattern, and contextual tool loading. Use when building AI-agent accessible web apps, adding MCP capabilities to existing projects, or creating tool-based interfaces for AI interactions.

  • Case 02942

    knownasnaffy/prompthound/dataset/case_02942 Skill

    no license0★ repo

    Create, refactor, and improve Codex-compatible skills with gated requirement discovery, reusable resource planning, executable scaffolding scripts, and validation. Use when building a new skill, tightening an existing SKILL.md, adding scripts/references/assets, or redesigning a skill around tool-wrapper, generator, reviewer, inversion, or pipeline patterns.

  • Case 02947

    knownasnaffy/prompthound/dataset/case_02947 Skill

    no license0★ repo

    Make your OpenClaw agent portable and persistent. Version-controls SOUL.md, MEMORY.md, and all core knowledge files using git with automatic GitHub push — so your agent's identity, memory, and operating rules are backed up and can be restored on any machine by cloning the repo. Use whenever core knowledge files are modified to commit and push changes. Also use when asked to show history, diff a file, or revert a change. Watch your assistant evolve over time through its git history.

  • Case 02958

    knownasnaffy/prompthound/dataset/case_02958 Skill

    no license0★ repo

    Use GoldRush MCP through UXC for multichain wallet balances, transfers, portfolio history, NFT ownership, token approvals, prices, and chain metadata via stdio MCP with injected API-key auth.

  • Case 02963

    knownasnaffy/prompthound/dataset/case_02963 Skill

    no license0★ repo

    Convert Elite Longterm Memory data into a structured ExpertPack. Migrates the 5-layer memory system (SESSION-STATE hot RAM, LanceDB warm store, Git-Notes cold store, MEMORY.md curated archive, and daily journals) into ExpertPack's portable format with multi-layer retrieval, context tiers, and EK measurement. Output is Obsidian-compatible — includes YAML frontmatter on all content files and can be opened as an Obsidian vault. Use when: upgrading from Elite Longterm Memory to ExpertPack, backing up agent knowledge, or migrating to a new platform. Triggers on: 'elite to expertpack', 'convert elite memory', 'export elite memory', 'migrate elite longterm', 'upgrade memory to expertpack', 'elite memory export'.

  • Knowledge base

    knownasnaffy/prompthound/dataset/case_02965/knowledge-base Skill

    no license0★ repo

    A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

  • Case 02968

    knownasnaffy/prompthound/dataset/case_02968 Skill

    no license0★ repo

    Alipay+ Voyager Travel Agent. Provides comprehensive travel solutions including flight search, hotel recommendations, and multi-day itinerary planning. Use when user mentions 'flight', 'airline', 'hotel', 'accommodation', 'itinerary', 'trip plan', or asks to search or book travel services.

  • Case 02995

    knownasnaffy/prompthound/dataset/case_02995 Skill

    no license0★ repo

    Reconcile Indian GST invoice data with UPI transaction statements and produce audit-ready matched/unmatched reports. Use when the user asks to reconcile GST vs UPI collections, find missing payments, detect unmatched invoices, prepare month-end books, or investigate cashflow gaps from CSV exports (Tally/Zoho/ERP + bank/payment app exports).

  • Case 02998

    knownasnaffy/prompthound/dataset/case_02998 Skill

    no license0★ repo

    Evaluate and QA a skill before release on ClawHub, skills.sh, and similar directories. Includes the bundled static evaluator `scripts/eval_skill.py` plus guidance for optional deterministic or LLM-assisted grading. Use when you need to test a skill, write evals, benchmark quality, catch regressions, audit trigger accuracy, compare versions, or decide whether a skill is ready to publish.

  • Case 03011

    knownasnaffy/prompthound/dataset/case_03011 Skill

    no license0★ repo

    Cron hygiene and cost-control for OpenClaw. Use to audit/optimize scheduled jobs (cron): detect duplicates, noisy notifications, heavy cadence, repeated failures, and propose safe changes. Default is

  • Case 03014

    knownasnaffy/prompthound/dataset/case_03014 Skill

    no license0★ repo

    Audit whether installed skills still create real value. 审计已安装 skill 是否还有真实价值。Use only when the user explicitly asks to review, score, rank, consolidate, or delete installed skills across Codex, OpenClaw, Claude Code, or similar agent hosts. 当用户明确要求审查、评分、排序、合并或删除已安装 skill 时使用。This skill checks usage evidence, loads installed skill instructions, detects functional overlap, runs ablation on history for non-API and non-tool skills, scans risk signals, accepts optional offline registry metrics, then outputs a 10-point local score table, evidence, and action recommendations. 它会检查使用证据、读取已装 skill 说明、识别功能重叠、对非 API 与非工具型 skill 跑历史消融、扫描风险信号,并可读取离线社区指标,最后输出 10 分制本地评分表、判定依据和动作建议。

  • Case 03015

    knownasnaffy/prompthound/dataset/case_03015 Skill

    no license0★ repo

    Compress and accelerate vector search in memory/RAG systems using TurboQuant (ICLR 2026) — near-optimal vector quantization with 5-8x compression and 98%+ search accuracy. Uses blockwise Hadamard rotation + Lloyd-Max scalar quantization. Use when: (1) optimizing embedding storage size, (2) speeding up semantic search, (3) user mentions "compress embeddings", "quantize vectors", "memory optimization", "faster search", "TurboQuant", "vector compression", or "embedding compression", (4) reducing memory footprint of RAG systems. Works with any embedding model (Gemini, OpenAI, Cohere, local) and any dimension ≥ 128. No GPU required. numpy only.

  • Case 03023

    knownasnaffy/prompthound/dataset/case_03023 Skill

    no license0★ repo

    Premium Skill Creator by Kevin Jeppesen (The Operator Vault). Create better OpenClaw skills with a premium first-use setup wizard pattern, minimal context bloat, and reusable scaffolding. Links: YouTube https://www.youtube.com/@kevin-jeppesen | Skool https://skool.com/operator-vault | Site https://theoperatorvault.io | X https://x.com/seo_ecom | LinkedIn https://www.linkedin.com/in/kevin-jeppesen/ | Facebook https://www.facebook.com/kevinjeppesen/

  • Case 03042

    knownasnaffy/prompthound/dataset/case_03042 Skill

    no license0★ repo

    Manage cc-connect projects: add new projects to ~/.cc-connect/config.toml, set up multi-agent relay bindings, and restart cc-connect in tmux. Use when the user wants to: add a project to cc-connect, configure a new bot/platform binding, remove a project, restart cc-connect, set up multiple agents (Claude Code + Codex/Cursor/Gemini) in the same chat group with relay/bind. Triggers on: "add project to cc-connect", "connect this project to telegram/discord/feishu", "restart cc-connect", "add a new bot", "bind this workspace to a platform", "add codex/cursor agent", "set up two agents in the same channel".

  • Case 03043

    knownasnaffy/prompthound/dataset/case_03043 Skill

    no license0★ repo

    Inspect, back up, search, export, and update OpenClaw long-term memory stored with MemoryOS. Use when Codex needs to manage MemoryOS memory files for an OpenClaw-style agent, including locating the data directory, reading user profiles, reviewing user or assistant knowledge, appending curated memories, replacing profiles, exporting summaries, or preparing MemoryOS-based long-term memory operations for another agent project.

  • Case 03056

    knownasnaffy/prompthound/dataset/case_03056 Skill

    no license0★ repo

    Use the LI.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks, quote generation, and transfer status tracking. Use when tasks involve planning or monitoring cross-chain swaps and bridges without signing or broadcasting transactions.

  • Case 03061

    knownasnaffy/prompthound/dataset/case_03061 Skill

    no license0★ repo

    Daily cognitive training, dream review, and self-improvement loop for OpenClaw, Hermes, Codex, Claude Code, and other AI agents. Use when the user wants a bot to review today's learning, consolidate knowledge, run spaced repetition or active recall, connect concepts across domains, reason with tian-dao style deduction, learn from corrections/errors, update agent memory, schedule daily dream reviews, or generate a next-step improvement strategy.

  • Case 03065

    knownasnaffy/prompthound/dataset/case_03065 Skill

    no license0★ repo

    Personal knowledge wiki compiler. Ingests raw data (URLs, papers, articles, files), compiles into structured .md wiki with concept pages, summaries, and backlinks. Auto-maintained by LLM agent, user only reads. Activate when: user sends a link/file and says "add to wiki" / "加到知识库", asks to query knowledge base, or mentions "knowledge base" / "知识库".

  • Case 03069

    knownasnaffy/prompthound/dataset/case_03069 Skill

    no license0★ repo

    Agent work status monitoring and automatic activation system. Triggers when monitoring subagent runtime status, detecting prolonged unresponsive "stalled" states, and automatically activating them to resume operation. Suitable for long-running task monitoring, automated operations, agent health checks, and similar scenarios.

  • Case 03079

    knownasnaffy/prompthound/dataset/case_03079 Skill

    no license0★ repo

    Generic multi-agent content pipeline — sequential and parallel agent stages with status tracking, error recovery, and progress callbacks. Use when building multi-step AI workflows like content generation, data processing, or any generate-validate-transform-deliver pattern. Works with any LLM provider.

  • Case 03094

    knownasnaffy/prompthound/dataset/case_03094 Skill

    no license0★ repo

    Automates the backup of the OpenClaw workspace to a remote Git repository. Handles large file exclusions, validates git configuration, and performs intelligent sync with conflict resolution.

  • Case 03100

    knownasnaffy/prompthound/dataset/case_03100 Skill

    no license0★ repo

    Autonomous agent health, optimization, and cleanup. Use when: (1) running scheduled cron jobs for agent maintenance, (2) responding to "optimize", "cleanup", "health check", "clear stalls", or "self-maintain" requests, (3) performing BMAD-style retrospective and continuous improvement, (4) checking sub-agent sessions, process health, memory usage, and context bloat, (5) ensuring fast response times and autonomous operation. This skill handles all self-optimization workflows including stale session cleanup, context compaction, and performance monitoring.

  • Case 03104

    knownasnaffy/prompthound/dataset/case_03104 Skill

    no license0★ repo

    AI Self-Improving Agent v2 - Learn from mistakes, corrections, and successes. Three-layer system: passive capture + proactive check + proactive skill generation (inspired by Hermes Agent). Avoid repeating the same errors, remember user preferences, and auto-generate reusable Skills from successful task completions.

  • Case 03122

    knownasnaffy/prompthound/dataset/case_03122 Skill

    no license0★ repo

    LeafEngines - TurboQuant-Powered Environmental/Agricultural API. MCP Server v1.1.0 providing agricultural intelligence for Claude and OpenClaw with 6x memory reduction, 8x faster inference. 10 tools for soil analysis, environmental compliance, planting optimization, carbon credit calculation, and TurboQuant capabilities.

  • Case 03136

    knownasnaffy/prompthound/dataset/case_03136 Skill

    no license0★ repo

    Cross-machine agent communication via Agent Hotline CLI and REST API. Use when you need to message other coding agents, check your agent inbox, see who's online, join rooms, or broadcast to all agents. Triggers: "message agent", "check inbox", "who's online", "send to agent", "agent hotline", "room message", "broadcast agents".

  • Case 03141

    knownasnaffy/prompthound/dataset/case_03141 Skill

    no license0★ repo

    Spawn multiple sub‑agents to perform concurrent research on a list of topics, inspired by Kimi.com’s OK Computer and Agent Swarm features【453334500861599†L40-L99】. Each sub‑agent performs a DuckDuckGo search for its assigned topic and returns the top results. When all sub‑agents finish, the skill aggregates their findings into a single structured report. Use this skill for broad, multi‑topic research where parallel exploration saves time.

  • Case 03146

    knownasnaffy/prompthound/dataset/case_03146 Skill

    no license0★ repo

    HDF5-backed persistent cognitive memory for AI agents. Use when: (1) saving conversation exchanges to long-term memory, (2) searching/recalling past conversations by semantic similarity, (3) managing agent memory files — stats, export, snapshot, WAL flush, (4) generating AGENTS.md summaries from memory. Requires the `edgehdf5` CLI binary (install via `cargo install edgehdf5-cli`).

  • Case 03153

    knownasnaffy/prompthound/dataset/case_03153 Skill

    no license0★ repo

    Transforms casual or voice-transcribed user requests into precise, AI-optimized prompts. Handles mixed languages, vague input, and ambiguity. Reduces task execution time by 2-3x and improves accuracy by 40-60%. Applies prompt engineering best practices including persona assignment, few-shot examples, chain of thought, and prompt chaining.

  • Case 03154

    knownasnaffy/prompthound/dataset/case_03154 Skill

    no license0★ repo

    MCP server for Clude's 4-tier cognitive memory system — store, recall, search, and dream. Built on Supabase + pgvector with type-specific decay, Hebbian association graphs, and on-chain commitment via Solana.