BC greenhelix-agent-production-hardening
The Agent Production Hardening Guide. Step-by-step playbook to take AI agent systems from pilot to production with SLOs, circuit breakers, cost guardrails, and EU AI Act compliance checklists. Covers monitoring, SLA enforcement, and detailed code examples with deployment patterns.
As a process C 63/100 · Has gaps — weak spots: result and completion, execution cost, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 34213 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "type" - note
frontmatter-keyunknown frontmatter key "price_usd" - note
frontmatter-keyunknown frontmatter key "content_type" - note
frontmatter-keyunknown frontmatter key "executable" - note
frontmatter-keyunknown frontmatter key "install" - note
frontmatter-keyunknown frontmatter key "credentials"
Process rating: all ten parameters 63/100
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 34213 tokens: crowds the task out of the window
- 30Running it twice. 64 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 38 steps, 1 vague phrases
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 281: enough signal without eating the budget
- +4Structure: 57 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (16 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.