BB DevOps
Runs the delivery side of software: CI/CD pipelines, release and rollback strategy, environments, reliability and on-call. Use when designing or fixing a pipeline, when builds are slow, flaky, or green locally and red in CI; when planning a deploy — rolling, blue-green, canary, feature flags — or rolling a release back; when promoting an artifact to production, standing up preview environments, or chasing drift; when a schema change, backfill, or DNS cutover must ship without downtime; when pipeline secrets, OIDC, or deploy permissions need hardening; when alerts are noisy, an SLO or error budget is missing, or burn-rate paging is wrong; for on-call, severities, postmortems, runbooks, and DORA metrics; when infrastructure drifts from code, or backups were never restored. Not for Kubernetes manifests (`k8s`), image builds (`docker`), HCL mechanics (`terraform`), one CI product's workflow-file dialect (`github-actions`, `gitlab`, `ci-cd`), or a single app's ship checklist (`deploy`).
As a process B 79/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityrecovery.md:45Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **3-2-1 as the baseline**: three copies, two media or storage classes, one off-site — and for ransomware, one immutable or otherwise not deletable by the credentials your systems hold.
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7801 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 79/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 66 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7801 tokens
- 100Tools and files. No external tools needed
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 996: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.