Agent Trajectory Evaluator
imtiazrayhan/agentscamp-libraryEvaluate a multi-step AI agent's whole run — tool calls, intermediate steps, and final result — not just final-answer correctness, so you can pinpoint WHERE it went wrong. Use when building or debugging a tool-using or multi-step agent, when final-answer-only evals can't explain failures, or when a prompt/model change quietly makes the agent less efficient or more error-prone even though the answer still looks right.
At a glance
This skill is for Coding and helps you debug a multi-step agent failure, evaluate agent tool-call sequences, and identify where an agent went wrong.
git clone --depth 1 https://github.com/imtiazrayhan/agentscamp-library
cp -r agentscamp-library/skills/agent-trajectory-evaluator ~/.claude/skills/agent-trajectory-evaluator
Setup, runtime and requirements describe imtiazrayhan/agentscamp-library, the repo this skill ships in.
agentsllmdebuggingevaluationtool-useMulti Step Reasoning
Also in imtiazrayhan/agentscamp-library
View the repoAudit a UI change for accessibility regressions by combining automated checks with keyboard, focus, semantic, name-role-value, contrast, zoo...
Write an Architecture Decision Record capturing a decision the user describes, in Michael Nygard ADR format (Status, Context, Decision, Cons...
Design a project's CLAUDE.md and memory hierarchy by exploring the repo to learn its real build/test/lint commands, architecture, and non-ob...
Cut alert noise and make every page mean something — rewrite alerting rules to fire on user-felt symptoms (error rate, latency SLO burn, fai...
Plan the retirement of an API endpoint, field, event, tool, or version without surprising active consumers. Use when replacing an interface,...
Design or normalize an API's error contract so clients get stable machine-readable codes, safe human messages, field-level validation detail...
Generate accurate architecture diagrams as Mermaid — straight from the codebase, not from imagination — by first choosing which view answers...
Read-only review of authentication AND authorization flows — session/token model, cookie flags, CSRF, token rotation, password-reset/email-v...
Audit scheduled jobs, queue consumers, workers, and asynchronous workflows for delivery assumptions, idempotency, retries, poison messages,...
Rebase the current branch onto its base and walk every conflict methodically, resolving each by understanding both sides. Use when your feat...
Analyze a JS/TS production bundle and surface the biggest size wins — heavy dependencies, duplicate packages, missing code-splitting, oversi...
Design a cache policy from data ownership, freshness, privacy, invalidation, and failure requirements across browser, CDN, reverse-proxy, ap...
Other Coding skills
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI be...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design...
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model...
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS,...
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.