CC experimentation-platform-orchestrator
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which experimentation platform, choose Statsig vs PostHog, evaluate experimentation tools, switch experimentation platform, migrate from Optimizely, consolidate experimentation tools, multi-platform experimentation, experimentation platform decision, ab test platform selection, feature flag platform vs experiment platform, warehouse-native experiments, vendor lock-in experimentation. Also triggers when a team is asking about cost, governance, or migration cost across experimentation tools, or when an evaluation is starting.
A platform decision framework for experimentation.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6360 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "catalog_summary" - note
frontmatter-keyunknown frontmatter key "display_order"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 70Execution cost. Instruction body is 6360 tokens
- 100Tools and files. No external tools needed
- 100Steps. 51 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- low 20 top-level sections: this looks like several domains in one skill
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)
- +3Description length 843: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 51 items
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.