Evaluate and score agent behavior against a golden reference. Use this skill whenever the user wants to run evaluation, check pass/fail status, understand metric scores, compare sessions for regressions, validate agent behavior, or score a trace from a file or a live session. Trigger on phrases like "eval this trace", "check my agent output", "did my agent do the right thing", "compare runs", "did my agent regress", "score session X", "evaluate against golden", "run evals". Works with both local trace files and live streaming sessions. --- Evaluate agent behavior and explain what the scores mean. ## Determine the input type First, figure out what to evaluate: - **Trace file(s)** — user mentions a `.json` or `.jsonl` file path → use `evaluate_traces` - **Sessions vs golden** — user has multiple live sessions and wants regression testing → use `evaluate_sessions` - **Single live session** — user wants to score one session against a golden eval set → guide them to use `evaluate_sessions` with one session as golden ## Evaluating trace files 1. Get the file path(s). Check the extension: `.jsonl` → `trace_format: "otlp-json"` | `.json` → `"jaeger-json"` (default) 2. Ask if they have a golden eval set JSON. For `tool_trajectory_avg_score` (the default metric), an eval set is required — it provides the expected tool call sequence to compare against. If they don't have one yet, explain this and suggest starting with `hallucinations_v1`, or ask if they want to create a golden set from a reference run first. 3. Call `evaluate_traces` with the file(s), format, and eval set. 4. Present results as a score table (see Score interpretation below) and explain failures. ## Evaluating sessions (regression testing) This workflow requires the server to be running with the `--dev` flag (which enables WebSocket and session streaming). Plain `agentevals serve` will not have sessions. If you get a connection error from any tool below, tell the user: ```bash uv run agentevals serve --dev ```
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\".
Deep code scan for AI security issues — prompt injection, PII in prompts, hardcoded keys, unguarded agents.
Neues Projekt im aktuellen Workspace verknüpfen — nur Projekt-ID in project.json schreiben
A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate", "stress test this idea", "poke holes in my plan", "help me decide between X and Y", "what are the second-order effects", "I'm stuck on a decision", names any specific model (SWOT, first principles, inversion, pre-mortem, etc.), or asks for structured reasoning on any ambiguous, high-stakes, or complex problem. Also trigger when the user seems uncertain, is rationalizing, or is asking "am I thinking about this right?" Even casual phrases like "what do you think about..." on non-trivial topics should trigger this skill. --- # Thinking Partner A deterministic thinking partner that challenges assumptions and applies mental models to help users think better and clearer. Not a lecture — a sparring session. ## Core Philosophy Good thinking is an active achievement, not a default state. The goal is not to tell the user what to think, but to sharpen *how* they think by: 1. **Challenging assumptions** — Surface hidden beliefs the user is treating as facts 2. **Applying mental models** — Select and deploy the right thinking frameworks for the situation 3. **Detecting orientation capture** — Notice when thinking serves comfort instead of truth 4. **Maintaining productive tension** — Hold complexity open long enough to find real insight You are not a yes-machine. You are not an interrogator. You are a thinking partner: respectful, direct, genuinely curious, and willing to push back. ## When This Triggers - "Help me think through X" - "Challenge my thinking / assumptions" - "What am I missing?" - "Apply [any model name] to this" - "Play devil's advocate" - "Stress test this idea / plan" - "Help me decide between X and Y" - "What are the second-order effects?" - "Am I thin
Best practices for integrating TanStack Query with TanStack Router and TanStack Start. Patterns for full-stack data flow, SSR, and caching coordination.
Routing guide -- when to use `nansen agent` (AI research) vs direct CLI data commands. Use when deciding how to answer a user's research question with Nansen tools.
Use when working in a Ruby project - provides authoritative sources for documentation, typing, and tooling
- 📁 scripts/
- 📄 config.json
- 📄 SKILL.md
The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization across Claude Code, Gemini CLI, Google Anti-Gravity, OpenCode, and other AI tools. Handles User-level (Global) and Project-level (Local) scopes.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Headless browser automation for AI agents using agent-browser CLI. Use when Claude needs to automate web browsing, scrape web data, interact with web pages, fill forms, take screenshots, or perform any browser-based tasks. Supports reference-based element targeting, session management, and semantic locators.
Creating and refining Mermaid diagrams with live reload. Use when users want flowcharts, sequence diagrams, class diagrams, ER diagrams, state diagrams, or any other Mermaid visualization. Provides best practices for syntax, styling, and the iterative workflow using mermaid_preview and mermaid_save tools.
Post a coordination message from this bot to the shared bot2bot channel, @-mentioning the other Sutando node.
