Manage Bernstein agents — list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one. --- # Bernstein Agent Management Inspect, monitor, and control active Bernstein agents. ## When to Use - User asks "what agents are running?" or "show me the agents" - User wants to see what a specific agent is working on - User says "kill that agent" or "stop the backend agent" - User asks "why is that agent stuck?" or wants to inspect agent output - User wants to see agent logs ## Instructions ### List agents 1. Run `scripts/agents.sh list` to get all active agents. 2. Present them clearly: ``` ## Active Agents (3) | Agent | Role | Model | Status | Task | Runtime | Cost | |-------|------|-------|--------|------|---------|------| | ses-a1b2 | backend | claude-sonnet-4 | alive | TASK-042: Fix auth | 4m 12s | $0.32 | | ses-c3d4 | qa | gpt-4.1 | alive | TASK-043: Write tests | 2m 45s | $0.18 | | ses-e5f6 | frontend | claude-sonnet-4 | stalled | TASK-044: Update UI | 8m 03s | $0.51 | ``` ### Inspect agent 3. To see what an agent is doing: `scripts/agents.sh logs <session_id>` 4. Show the last ~20 lines of output. ### Kill agent 5. To kill a stalled or misbehaving agent: `scripts/agents.sh kill <session_id>` 6. Confirm: "Agent ses-e5f6 terminated. Task TASK-044 returned to open queue." ### Stall detection 7. If any agent shows `stalled` status, proactively suggest killing it. 8. An agent is stalled if it hasn't sent a heartbeat in >60 seconds.
Reference guide for @gleanwork/mcp-server-tester — the Playwright-based testing and evaluation framework for MCP servers. Covers import paths, all 11 matchers, transport config, eval datasets, reporter setup, CLI commands, auth patterns, and common anti-patterns. Use when working with MCP server tests or evals.
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
>-
Brand onboarding setup skill. Captures a client's visual identity, content patterns, audience, and goals through evidence capture + pre-filled client doc + structured intake. Writes context/brand-style.md as the foundation for all social skills. Run once per client before using /social-creative-designer, /content-calendar, or /caption-writer.
- 📁 reference/
- 📁 vendor/
- 📄 cli.mjs
- 📄 default-provider.txt
- 📄 lib.mjs
Gives the agent a cryptographic Alien Agent ID linked to a verified human owner, signed authentication to Alien-aware services over RFC 9449 DPoP, an encrypted vault for service credentials (GitHub, Slack, AWS, etc.), and SSH-signed git commits with provenance trailers. Use when the user asks to bootstrap an Alien identity, sign in to an Alien Network service (anything under alien-api.com / alien.org / agent-sso.*), post to or call such a service, store or retrieve service credentials securely, or make commits attributable to a specific agent + human owner. Also triggers on the terms "Alien ID", "Agent ID", "DPoP", "cnf.jkt", or "owner binding".
- 📁 scripts/
- 📄 LICENSE.txt
- 📄 SKILL.md
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Self-host any open-source app on the user's own infrastructure (cloud VM, VPS, Raspberry Pi, localhost, k8s, PaaS). Walks the user through provisioning, DNS, TLS, SMTP, and hardening in phased + resumable workflows. 2215+ verified recipes plus live-derived fallback for the long tail. Agent-mode rules apply (no chat-paste credentials, no group-channel deploys).
E2E test authoring for Backseat Driver. Use when: writing, modifying, or debugging e2e tests under e2e-test-ws/, adding new MCP test scenarios, investigating test failures, understanding test infrastructure, or working with files matching *_test.cljs in the e2e workspace.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
MUST USE AUTOMATICALLY when user sends URLs from x.com, twitter.com, or any site that web_fetch fails on. Do NOT ask the user — just load this skill and use it. Browser automation and web scraping with anti-detection stealth mode. Capabilities: (1) Scrape Twitter/X content without login, (2) Extract data from anti-bot-protected websites, (3) Automate browser interactions (clicking, typing, screenshots), (4) Bypass JavaScript-rendered content that web_fetch cannot handle, (5) Access pages requiring cookies or sessions. Built on Chrome DevTools Protocol with fingerprint spoofing.
- 📁 examples/
- 📁 references/
- 📁 scripts/
- 📄 README.md
- 📄 setup.sh
- 📄 SKILL.md
This skill should be used when the user mentions Unraid, asks to check server health, monitor array or disk status, list or restart Docker containers, start or stop VMs, read system logs, check parity status, view notifications, manage API keys, configure rclone remotes, check UPS or power status, get live CPU or memory data, force stop a VM, check disk temperatures, or perform any operation on an Unraid NAS server. Also use when the user needs to set up or configure Unraid MCP credentials.
Audit whether a repository's environment variable configuration allows an agent to load all required .env variables from scratch. Use when evaluating a new repository's agent-readiness, when environment loading fails during agent setup, or as part of an initial harness assessment. Do not use when .env files already load correctly and the goal is to add a single new variable, or when creating env loading capability (use autonomy--env-creator).
Merge reference implementation changes from the official Copilot SDK into this Java SDK.
