New: Skill bounties are live. Post a request, fund the bounty, and creators compete for 7 days to build it -> See open bounties
THE AGENSI STORE
484 skills found
Lint a prompt template for the issues that cause injection and flaky output. Flags untrusted variables interpolated straight into the instructions (the injection surface), placeholders that are never provided or never used, contradictory instructions, a missing output-format spec where the result is parsed, unbounded context interpolation, and leftover placeholders. It detects problems; it does not write prompts.
by Joker
5 realistic visual styles, character modeling, I2V prompts, cinematic shot design, uncanny valley prevention.
A structured recovery framework to stop agent loops, handle malformed output, and manage autonomous error escalation.
Autonomous loop that iteratively modifies, evaluates, and selects the best version of any text resource — skills, prompts, or campaigns — using a modify-measure-keep/discard cycle.
by servrox
Audit, prune, and secure your AI agent's long-term memory to prevent pollution and data leakage.
by LocoLoboZ
A structured governance auditor to optimize AI project instructions, clean up context, and manage workspace health.
by Roy Yuen
Architect durable multi-agent Kanban boards with structured handoffs and role-based task decomposition.
by Danejw
Convert product specs into a vertical-slice implementation roadmap with ready-to-use prompts for AI coding agents.
Drastically reduce RAG costs and latency while improving retrieval accuracy through advanced memory architecture.
by Shippers
Avoid context bloat and high costs with a 3-line verdict on expensive AI operations before you run them.
An adversarial reviewer for AGENTS.md and agent instruction files. It flags ambiguous or contradictory rules, missing guardrails, vague tool and scope definitions, and untestable instructions, then returns a PASS / REVISE / BLOCK verdict — before the config drives your agent.
by Jeet Dhandha
Drive several real Chrome profiles, each with its live Google login, at once via Kimi WebBridge — multi-profile browser automation in your real Chrome, not headless.
Systematic audit for AI prompts to detect security flaws, bias, and cost-inefficiencies with auto-optimization.
An advanced FinOps engine to analyze AI usage, optimize token spend, and reduce LLM costs by up to 60%.
by Nex AI
Builds a Python FallbackProvider that chains Claude, Gemini, Qwen, and Ollama so your AI pipeline never fully stops.
Lint the function-calling tool definitions your agent exposes. Flags tools with no description, parameters missing a description or a type, overlapping or near-duplicate tools, too many tools for reliable selection, an unsafe tool exposed without a guard, required parameters missing from the schema, and free-form parameters that should be bounded with an enum. Cleaner tool schemas mean an agent that picks the right tool.
by Nex AI
Canonical Next.js bridge for secure, real-time communication between browser UIs and local agent gateways.
by openfate ai
Deterministic Bazi / Four Pillars skill using OpenFate MCP for True Solar Time, Ten Gods, Da Yun, and branch interactions.
An iterative agent loop that optimizes any prompt, config, or artifact by making one change at a time, scoring it against a metric, and keeping only the winners.
Scaffold and audit secure MCP servers with input schemas, confirmation gates, and safety-first tool definitions.
by Zotri
Run Claude Code unattended with a battle-tested safety framework, hardened deny-rules, and a 6-layer rollback ladder.
by Samoxis
Your headless Ollama box crashes at 3am and you find out hours later. OllamaWatch pings your Telegram the instant a model dies, the GPU runs out of memory, or the API hangs — with a fix hint in every alert. One Python file, no SaaS, no dashboards.
by Nex AI
Builds a self-hosted second brain on a Raspberry Pi: pgvector RAG over your notes with local Ollama embeddings and a Telegram interface.
by Joker
Video type matrix, platform specs, AI prompt recipes (Seedance/Sora/Kling), zero-cost SOP, quality gates.