discoverllm-executing-intents-discovering
Help users discover and form their intents through adaptive diverge-converge interaction, rather than just asking clarifying questions. Use when the user gives…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,155 results
failure-aware-enhancements-code-generation
Diagnose why generated code fails and apply the right fix strategy (self-critique, RAG, multi-model, or progressive prompting) based on a data-driven decision…
fraudshield-knowledge-graph-empowered
Detect and defend against fraudulent content in LLM inputs using knowledge-graph-augmented analysis. Builds a fraud tactic-keyword bipartite graph, scores…
from-assumptions-actions-turning
Build uncertainty-aware planners for multi-agent systems using the PCE (Planner-Composer-Evaluator) decision tree framework. Converts implicit LLM reasoning…
humans-welcome-observe-first-look
Analyze AI agent social network activity using topic taxonomy classification and multi-level toxicity scoring. Detects content flooding, topic concentration,…
isd-agent-bench-comprehensive-benchmark-evaluating
Build and evaluate LLM-based Instructional Design agents using the ADDIE framework, Context Matrix scenario generation, and multi-judge evaluation. Triggers:…
markovscale-optimal-sequential-scaling
Implement MarkovScale's principled sequential scaling for LLM inference pipelines. Models retry/refinement loops as a two-state Markov chain to compute optimal…
medbeads-agent-native-immutable-data
Build immutable, agent-native medical data pipelines using Merkle DAG structures (MedBeads pattern). Converts mutable EMR/FHIR records into…
perfguard-performance-aware-agent-visual
Performance-aware multi-tool orchestration for visual content generation pipelines. Implements PerfGuard's three mechanisms (PASM, APU, CAPO) to select, score,…
polarmem-training-free-polarized-latent
Build polarized memory systems for multimodal agents that encode both positive and negative evidence as graph constraints, suppressing hallucinations without…
predicting-improving-test-time-scaling
Implement Scaling-Law Guided (SLG) Search for test-time compute optimization. Uses reward tail distribution estimation (GPD fitting) to predict scaling laws…
safepred-predictive-guardrail-computer-using
Implement predictive safety guardrails for computer-using agents and automated pipelines using world-model-based risk prediction. Catches long-term risks that…
scidatacopilot-agentic-data-preparation
Build agentic pipelines that ingest heterogeneous raw scientific data, parse research intent, and produce analysis-ready unified datasets. Use when user says…
semanticalli-caching-reasoning-not
Implement pipeline-aware intermediate representation (IR) caching for agentic systems. Instead of caching final LLM responses, decompose multi-step pipelines…
sparseeval-evaluation-sparse-optimization
Efficiently evaluate LLMs on benchmarks by selecting a small subset of anchor items via sparse optimization, reproducing full-benchmark rankings at a fraction…
thinking-makes-agents-introverted
Prevents the "introverted agent" problem where extended reasoning causes agents to give shorter, less informative responses in interactive/user-engaged tasks.…
thinktank-me-multi-expert-framework-middle
Build multi-expert forecasting systems where specialized LLM agents collaborate through routing and aggregation to predict complex events. Use when asked to:…
understanding-agent-scaling-llm-based
Design diversity-aware multi-agent systems that maximize performance with fewer agents. Uses information-theoretic K* effective channel analysis to replace…
when-agents-fail-comprehensive
Diagnose and fix bugs in LLM agent systems using a research-backed taxonomy of 11 bug types, 9 root causes, and 12 observable effects across agent core, tools,…
whispers-wealth-red-teaming-googles
Red-team LLM-based agentic payment systems against prompt injection attacks targeting transaction integrity and credential isolation. Use when: 'red-team my…
whitespaces-dont-lie-feature-driven
Detect whether source code was written by a human or generated by an AI (ChatGPT, Copilot, etc.) using whitespace, indentation, and stylometric feature…
argument-builder
Craft contribution strategies and draft Theory sections for sociology research. Guides cluster selection, arc structure, paragraph functions, and the pivotal…
lit-synthesis
Deep reading and synthesis of literature corpus. Theoretical mapping, thematic clustering, and debate identification using Zotero MCP for full-text access.
handoff
Compact the current conversation into a handoff markdown document for another agent or session to pick up. Use when handing off a side task, spawning a…