bug-report
FreeUse when reporting a bug. Format the finding as exactly two lines - a BUG line stating what is wrong, then a FIX line with the one-line change.
The English summary is being prepared. Showing the original description.
Deploy, run, list, or tear down the agents in this repo's .managed-agents/ folder on Anthropic Managed Agents. Use when the user says "deploy my agents", "ship this agent to the cloud", "run the deployed agent", or asks about managed-agent deployment.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
This repo defines deployable agents under .managed-agents/. Use the agentlift
CLI to push them to Anthropic's Managed Agents cloud and run them by ID. The user
shouldn't need to learn it — translate their intent into the right command.
Prerequisite: pip install agentlift and ANTHROPIC_API_KEY set (it's in .env).
agentlift plan .agentlift validate . (exit 1 means there are errors to fix)agentlift deploy . --yes
.agentlift-lock.json was written.agentlift deploy . --yes --prune
agentlift run <agent> --project . --task "<task>"--localagentlift list .agentlift destroy . --yesagentlift plan . first and show the user the plan before deploy.
Surface any ERROR diagnostics (e.g. a stdio MCP server, which can't deploy)
and stop — don't pass --skip-unsupported unless the user agrees to drop those..agentlift-lock.json maps each agent to its remote ID.
Tell the user to commit it so re-deploys are idempotent and run works for the
whole team.ANTHROPIC_API_KEY on the command line or in a committed file.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when reporting a bug. Format the finding as exactly two lines - a BUG line stating what is wrong, then a FIX line with the one-line change.
The English summary is being prepared. Showing the original description.
Use whenever you state a fact. End the answer with a short Sources list mapping each claim to a file, URL, or reasoning. Shared across agents.
The English summary is being prepared. Showing the original description.
Use whenever you state a fact. Add a short "Sources:" list at the end of your answer with where each claim came from (file name, URL, or "reasoning"). Shared by every agent on the team.
The English summary is being prepared. Showing the original description.
Apply the Acme house style to any prose - short sentences, no hype, lead with the answer. Shared across agents.
The English summary is being prepared. Showing the original description.
Use for every answer. After the final answer, append a new line that starts with exactly "RECEIPT:" followed by a three-word note. This proves the skill was loaded by the runtime.
The English summary is being prepared. Showing the original description.