BF agent-evals-and-observability
Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders, trajectory review, regression analysis, release gates, production traces, or privacy-aware telemetry. Covers task and trajectory contracts, statistical comparisons, and incident-to-case learning; route framework implementation to pydanticai or langgraph when needed. Do not use this skill for unrelated requests; route to the nearest named specialist.
Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents.
As a process F 39/100 · Will not run — References files that are not bundled: ../release-engineering/SKILL.md, ../system-one/SKILL.md, ../supabase/references/agent-evals.md
How to improve
- The text references files that are not there: add them or drop the references.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../release-engineering/SKILL.md - warning
missing-refreference to a missing file: ../system-one/SKILL.md - warning
missing-refreference to a missing file: ../supabase/references/agent-evals.md - warning
missing-refreference to a missing file: ../systematic-debugging/SKILL.md - warning
missing-refreference to a missing file: ../verification-methodology/SKILL.md - warning
missing-refreference to a missing file: ../secure-software-engineering/SKILL.md
Process rating: all ten parameters 39/100
- 0Tools and files. 6 referenced file(s) missing: ../release-engineering/SKILL.md, ../system-one/SKILL.md, ../supabase/references/agent-evals.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 85Steps. 11 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1529 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- medium 11 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 508: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 11 items
- +4Reference files are cited in the instructions (14 of 14)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.