القائمة
Use when the user wants to profile or improve the agent/codebase based on the current session. Profiles this session's traces against a chosen evaluator and proposes concrete edits.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when instrumenting an application with OpenTelemetry for Agent Health. Provides span structure, required attributes, and config setup for routing traces.
Use when instrumenting an application with OpenTelemetry for Agent Health. Provides span structure, required attributes, and config setup for routing traces.
Add OpenTelemetry instrumentation to an AI agent for Agent Health observability. Use when a user wants to make their agent's traces visible in Agent Health dashboards, or when debugging why traces aren't appearing. Covers span structure, Gen AI semantic conventions, required attributes, and OTLP exporter setup.
Evaluate, benchmark, and improve an AI agent with the Agent Health CLI and server APIs. Use when the user wants to run evaluations/benchmarks, interpret judge results (matcherResults / improvementStrategies), diagnose eval-vs-reality gaps, or raise an agent's pass rate. Mirror of docs/skills/AGENT_HEALTH.md.
Use when adding, modifying, or debugging agent connectors. Provides connector architecture, built-in types, and custom connector template.
Use when working on config loading, authentication, AWS profiles, or data source resolution. Explains the two config systems (TS vs JSON), auth priority, and multi-profile setup.
| name | agent-health-profile |
| description | Use when the user wants to profile or improve the agent/codebase based on the current session. Profiles this session's traces against a chosen evaluator and proposes concrete edits. |
When the user asks to profile/improve the agent (or runs /agent-health:profile):
-e my-eval),
use it; otherwise default to system-rca-default. You can list options with
agent-health list if needed.1b. Ask the user for any upfront feedback on the session before profiling
(e.g. "anything you want me to focus on — a wrong decision, a skipped step?").
If they give some, pass it via --feedback "..."; it becomes the primary lens
over the deterministic signals. Skip if they have nothing to add.
Run:
__AH_CLI__ profile -e <evaluator-id> [--feedback "<their feedback>"] --output json
It auto-detects the current session id (from .claude/agent-health/current-session,
written by the setup hook) and prints a JSON profile: the evaluator rubric,
the session trajectory (reconstructed from traces), deterministic signals, and
your userFeedback.
Using evaluator.systemPrompt as the rubric, review together:
userFeedback (weight it highest, if present),trajectory and signals from the JSON profile,Produce a prioritized list of concrete edits. For each: the file, the change,
why (tie it to a signal or a rubric criterion), a priority, and cite the
evidence — the signal that triggered it and the session's traceIds
(open them in the Traces tab to verify).
Apply the edits on a new branch (never the working tree directly), then summarize the diff for the user to review.