Agent Building skills

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

skill-selector

Meta-skill for picking project skills via APM. Invoke ONLY when the user explicitly asks to set up apm.yml, choose which skills a project needs, or evaluate a catalog match — do NOT auto-invoke on routine project-init or apm-management tasks. Two-phase: pick from a curated catalog first; only escalate to broader search/evaluation when the catalog has no fit. Avoids the failure mode of impulse-installing skills you never use or hand-searching GitHub when a vetted answer already exists.

305 repo starsObserved in 1 repos
Agent Building

waxa-eval

Use when iterating on a skill's prompt with the waxa CLI (https://github.com/mizchi/skills/tree/main/tools/waxa) — authoring scenarios, choosing graders, interpreting unclear-points, advancing a ledger, and judging convergence. Encodes the four-stage iteration pattern observed in real iter loops (structural fix → grader breadth → surface-form coverage → residual unclear) and the scenario-design pitfalls (blank-slate executor's network limit, prompt expectation explicitness, regex coverage of Japanese/English surface forms). Meta-skill: do NOT auto-invoke for routine skill edits; fires only when the user explicitly runs waxa or asks for a skill-quality eval.

305 repo starsObserved in 1 repos
Agent Building

shifu-authoring-flow

Use when changing backend shifu authoring, draft history, publish, outline structure, or import/export behavior. Keep draft and publish flows consistent and protect outline integrity.

303 repo starsObserved in 3 repos
Agent Building

skawld-sdk-dev

Build and run AI agents with the Skawld Agent SDK (@skawld/agent-sdk), a TypeScript/Bun agent harness with tools, sessions, permissions, hooks, streaming events, MCP, skills, and subagents. Use this skill whenever the user is writing code against @skawld/agent-sdk, importing Agent/Session/AnthropicProvider/OpenAIResponsesProvider/defaultTools, embedding an agent loop into a Node or Bun app, wiring custom tools, permission callbacks, hooks (preToolUse/postToolUse/userPromptSubmit/stop/preCompact), the AskUser tool, MCP servers, skills, or subagents, streaming agent events, steering or interrupting a run mid-flight, persisting/resuming sessions, or asks "how do I build an agent with skawld".

303 repo starsObserved in 1 repos
Agent Building

creating-workflows

当用户想「创建/生成一个 workflow(可复用的多子-agent 编排脚本)」时使用。讲清 deepx workflow 的 JavaScript 脚本格式、可用 API,以及如何用 Workflow 工具保存与运行。

302 repo starsObserved in 1 repos
Agent Building

eval-auth

Use for `/eval-auth` requests in auth-resume evals. Always connect through the disclosed MCP tool before answering, then continue the user's actual request using prior thread context when needed.

302 repo starsObserved in 1 repos
Agent Building

eval-mcp

Use for `/eval-mcp` requests that need the eval MCP handbook lookup.

302 repo starsObserved in 1 repos
Agent Building

jr-rpc

Manage low-level config and plugin introspection flows via jr-rpc bash commands. Use only when the user explicitly asks to read or update provider defaults/config or list installed plugins. Do not use for PR, branch, push, or auth-order questions; load the matching provider skill instead.

302 repo starsObserved in 1 repos
Agent Building

pi-agent-integration

Integrate the latest `@earendil-works/pi-agent-core` APIs into an app, library, runtime, or agent harness. Use for Pi `Agent`, `AgentHarness`, streaming bridges, tool execution hooks, `convertToLlm`/`transformContext`, queueing via `steer`/`followUp`, `continue()` semantics, `streamFn`/`streamProxy`, timeout/abort, session, skill, or compaction behavior.

302 repo starsObserved in 1 repos
Agent Building

superpowers

开始任何非琐碎任务时使用——确立 Superpowers 方法论及如何发现/使用其 skill。在任何回复(包括澄清提问)之前先调用相关 skill。对应 deepx 工作模式 sp。

302 repo starsObserved in 1 repos
Agent Building