agent-ops
agent-ops is an LLM evaluation & observability skill for AI agents, published by ibm-self-serve-assets in the building-blocks repository on GitHub. Skillspace rates agent-ops C (77/100) and it passed the safety scan; the rating is based on static analysis only.
Plan and run evaluations, red-teaming, and runtime observability for watsonx Orchestrate (WXO) agents across Developer Edition and SaaS. Use when validating WXO agents pre-deploy, authoring benchmark JSON DAGs, interpreting Journey Success / Tool Call Recall / Agent Routing F1 / RAG Faithfulness, diagnosing agent failures, running adversarial red-teaming (Instruction Override, Jailbreaking, Crescendo Attack), searching runtime traces, exporting traces via the Python SDK, wiring Langfuse for cost & latency analysis, or registering model pricing in Langfuse. Interview-first; emits bash commands for the user to run in their IDE terminal.
- Grade
- C
- Quality
- 77 / 100
- Safety
- Passed
- GitHub stars
- 20
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.