CD childhood
Babysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.
Promises to monitor a release after merge or deployment: verify packages, production behavior, plugins, and late-breaking bugs. Sounds like a post-ship checklist.
One instruction file at 1443 tokens. Quality score 71—middling, process score 38—low. No critical errors found, but broken_references flag signals missing or dead links. No model runs, no sandbox testing. Supports many platforms from Claude to DeepSeek.
Don't install: the instruction set is incomplete (broken links, weak process score), and nobody actually tested it in the field. For real post-deployment monitoring, you need something that works.
Babysit a shipped release after merge, publication, or deployment.
As a process D 38/100 · Unfinished process — References files that are not bundled: ../babysit/SKILL.md, ../version-bump/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../babysit/SKILL.md - warning
missing-refreference to a missing file: ../version-bump/SKILL.md
Process rating: all ten parameters 38/100
- 0Tools and files. 2 referenced file(s) missing: ../babysit/SKILL.md, ../version-bump/SKILL.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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1443 tokens
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 245: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 9 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.