Claude Code skills tagged Agents
Skills for multi-agent orchestration and harness construction — autonomous loops, parallel dispatch, agent evaluation, safety guardrails, team composition.
11 skills
-
agent-eval
Replace 'which coding agent feels better' with pass-rate + cost + time + consistency on your own codebase
-
agent-harness-construction
Design agent tools and observations so the agent has a fighting chance of finishing the task
-
agent-payment-x402
Let an agent pay 402-gated APIs without giving it unbounded spend or pooled-custody risk
-
agents-orchestrator
Run a full spec-to-ship pipeline with task-level QA gates instead of one big agent call
-
autonomous-loops
Pick the right autonomy pattern (claude -p pipeline through RFC-driven DAG) for the problem
-
ce-agent-native-architecture
Design — or audit — systems where agents drive features through tools and prompts instead of hardcoded code paths
-
council
Surface structured disagreement before a go / no-go decision, not after
-
deep-research
Produce cited research reports from multiple web sources without making up findings when search fails
-
dispatching-parallel-agents
Fan out independent work across parallel subagents instead of working serially
-
llm-trading-agent-security
Layer prompt-injection, spend-limit, simulation, and wallet-isolation defenses on an agent that signs transactions
-
safety-guard
Block destructive commands and restrict edits to a directory when running agents autonomously