Relay agent results without corrupting exact counts, failure reasons, source scope or status. Use when receiving agent output or handing results to another actor; distinguish observations from attributed conclusions and reference complete artifacts.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Read fidelity rules and the execution contract.
Preserve the caller's return vocabulary and structure. Relay exact counts/denominators, material
warnings, failure reasons and artifact paths: 7 of 10 found; 3 requests timed out, not most found
or the rest do not exist. Missing results or idle workers do not establish completion.
If a worker wrote an artifact, name the exact accessible artifact reference rather than replacing it with a shortened retelling. Keep observations separate from conclusions: an absent timeout field and an agent's asserted default of 30 seconds are two different claims.
Summarize a result only when requested, when combining workers for the caller's decision, or when selecting the relevant portion of a larger result. Preserve all material counts, reasons, scope and qualifiers, and reference the complete result. Use multi-source-synthesis for genuine integration rather than silently strengthening or merging claims during relay.
For retained evidence handoffs, follow the evidence record.
Validate the actual final artifact after any transformation. Unchanged verbatim relay may reuse
validation only when the evidence still describes the exact delivered bytes and source/request
identity. Keep failed and unperformed checks visible; never interpret NOT_VALIDATED as success.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.
中文简介正在准备中。当前显示原文说明。
SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.
中文简介正在准备中。当前显示原文说明。
Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.
中文简介正在准备中。当前显示原文说明。
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
中文简介正在准备中。当前显示原文说明。
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.
中文简介正在准备中。当前显示原文说明。
Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.
中文简介正在准备中。当前显示原文说明。