BB proxy-aiops
Use this skill whenever the user needs to operate a Traefik, Caddy or HAProxy reverse proxy / load balancer — a one-shot overview, routes (routers / caddy routes / frontends) with host/path matching, services and server-level upstream health, middlewares, TLS certificate inventory with an expiry sweep, traffic and 5xx error counters, config snapshot/search, four flagship RCAs (backend health, cert expiry, error rate, route conflicts), and governed writes (caddy config set/delete/load with prior-config capture; haproxy server drain/maint/ready and weight). Always use this skill for "Traefik", "Caddy", "HAProxy", "reverse proxy", "load balancer", "upstream down", "502/503/504 errors", "bad gateway", "cert expiring", "TLS certificate", "route not matching", "which route serves this host", "drain a server", "server weight", "redirect loop" when the context is a Traefik/Caddy/HAProxy edge. Do NOT use when the target is something other than a Traefik/Caddy/HAProxy proxy (a hypervisor, storage appliance, backup product, container-orchestration cluster, multi-vendor router/switch config, or OT/industrial equipment) — route those to the appropriate other AIops-tools skill. Do NOT use for firewall rules — use firewall-aiops. Managed cloud load balancers are out of scope. Governed proxy operations with a built-in governance harness (audit, policy, token budget, undo, risk-tiers). Behaviour is validated by a mock-based test suite; see docs/VERIFICATION.md for the live-verification checklist.
Use this skill whenever the user needs to operate a Traefik, Caddy or HAProxy reverse proxy / load balancer — a one-shot overview, routes (routers / caddy…
As a process B 72/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Shorten the description to 1024 characters.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1505 chars, limit 1024 - note
description-budgetdescription takes 1505 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "installer"
Process rating: all ten parameters 72/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 42 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3150 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 tags): a typed call is more reliable
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
- +3Description length 1504: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.