ratel-ai/skills

1

ratel-assessment Read a partner's agent codebase, score it across the 12-dimension catalog, and emit an evidence-cited markdown plus b…

ratel-ai/skills

107

2

ratel-integrate Inspect an existing agent codebase, map each agent's tools and skills, then implement Ratel so every agent discovers …

ratel-ai/skills

107

3

ratel-decompose-prompt Break a bloated, monolithic agent system prompt into a lean stable core plus extracted Ratel-style skills. Use when a…

ratel-ai/skills

91

4

ratel-tune-definitions Audit a codebase's tool and skill definitions against a failure-mode rubric and write a markdown tuning plan with per…

ratel-ai/skills

91

5

ratel-observability-assessment Inspect an agent codebase to decide where tracing belongs, turn on Ratel's native OTLP telemetry, and pick the OTel b…

ratel-ai/skills

89

6

ratel-langfuse-analyze Read a customer's live Langfuse traces, sessions, and scores via the Langfuse MCP server, pattern-match against a kno…

ratel-ai/skills

67

7

ratel-langfuse-integrate Inspect an agent codebase and write a markdown plan wiring Langfuse tracing/observability (session/trace boundaries, …

ratel-ai/skills

47

8

ratel-langsmith-analyze Read a customer's live LangSmith runs, traces, threads, and feedback scores via the LangSmith MCP server (or langsmit…

ratel-ai/skills

47

9

ratel-langsmith-integrate Inspect an agent codebase and write a markdown plan wiring LangSmith tracing/observability (run-tree boundaries, sub-…

ratel-ai/skills

47

10

ratel-langfuse-dashboards Decide which Langfuse dashboards a customer should build now that their agent is instrumented, and produce a markdown…

ratel-ai/skills

19

11

ratel-langfuse-instrument Inspect an agent codebase, decide where Langfuse tracing belongs, and produce a concrete instrumentation plan coverin…

ratel-ai/skills

19