SKILLEMALL.ai

AB release-readiness

Validate release readiness with evidence-based go/no-go decisions. Covers go/no-go checklists, smoke test suite design, staged rollout validation, rollback criteria and procedures, and post-deployment verification. Ensures release confidence comes from data, not feelings. Use when: "release ready," "go/no-go," "smoke test," "release checklist," "rollback plan," "staged rollout," "canary deploy." Not for: safe-release techniques (flags, canary, dark launch) applied during the rollout itself — use testing-in-production; scheduled probes that run continuously after release — use synthetic-monitoring; designing new tests from prod telemetry — use observability-driven-testing. Related: testing-in-production, qa-metrics, ci-cd-integration, ai-system-testing.

petrkindlmann/qa-skills Agent Skills author: petrkindlmann MIT 3 files body ≈ 6 439 tokens Open the sourcegithub.com analyzed 2 d ago

Validate release readiness with evidence-based go/no-go decisions.

As a process B 71/100 · Nearly there — weak spots: result and completion

AnalyzerInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
88
Run on models
none yet
Process rating
B
71/100
Nearly there
Result and completion w 14
40
When it triggers w 12
50
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6439 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 264): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 71/100

  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6439 tokens
  • 85Steps. 141 steps, 2 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 12 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

  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +4Description says when NOT to use the skill
  • +3Description length 762: enough signal without eating the budget
  • +4Structure: 48 headings
  • +3Step-by-step instructions: 141 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.