Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

token-conservation

Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads.

323 repo starsObserved in 1 repos
Agent Building

workflow-improvement

Evaluates and improves skills, agents, commands, and hooks after a workflow slice. Use when execution felt slow, confusing, repetitive, or fragile.

323 repo starsObserved in 1 repos
Agent Building

A2A JSON-RPC Call

Call a peer agent's A2A JSON-RPC endpoint. Supports tasks/send (send a task message) and tasks/get (query task status).

322 repo starsObserved in 1 repos
Agent Building

adversarial-pairing

Coordinate Pairing-mode doer/reviewer sessions through a Markdown blackboard. Use when the user invokes /adversarial-pairing with role and blackboard-path arguments or asks multiple pairing agents to coordinate plan review, implementation, staged code review, and follow-up review rounds without §BRAND_NAME_TITLE§ multi-agent mode.

322 repo starsObserved in 1 repos
Agent Building

bash-policy

Generate and curate Claude-oriented bash-policy project rules. Use to run bash-policy export/report, review .bash-policy-candidates.yaml from Claude settings, update .bash-policy.yaml, normalize command-shape identities, or validate bash-policy configuration.

322 repo starsObserved in 1 repos
Agent Building

§BRAND_BINARY_NAME§-operator

Operate a running §BRAND_NAME_TITLE§ multi-agent run from outside the agent pool: keep the orchestrator healthy, review checkpoints, recover stalls, wire agent environments, plan the next run, and escalate to the human only at genuine forks. Use when operating/babysitting a §BRAND_NAME_TITLE§ run (interactive `§BRAND_BINARY_NAME§ tui` or a headless watch loop), not when authoring the work yourself.

322 repo starsObserved in 1 repos
Agent Building

Fetch Agent Card

Fetch an A2A agent card JSON from a given endpoint URL. Tries direct GET first, then falls back to /.well-known/agent.json.

322 repo starsObserved in 1 repos
Agent Building

generic-subagent

Context-efficient delegation to subagents (read-only default, READ-WRITE opt-in)

322 repo starsObserved in 1 repos
Agent Building

maa-punish-pipeline-guide

MAA_Punish 任务流水线 JSON/JSONC 编写与审查指南。含 Pipeline 速查表(识别类型、动作类型、节点字段默认值、JumpBack/Anchor、Custom)。基于 MaaFramework 协议与本仓库 protocol-3.1-task-pipeline.md。在编写或审查 pipeline、排查超时/on_error、或使用 TemplateMatch/OCR/Custom 时使用。

322 repo starsObserved in 1 repos
Agent Building

autogen

AutoGen (Microsoft) — multi-agent conversation framework. Agent-to-agent chat, code generation & execution, tool use, group chat, and human-in-the-loop. Build collaborative AI systems with specialized agents.

320 repo starsObserved in 1 repos
Agent Building