AF llm-provider-forensics
Forensically verify what model family or routing layer may actually sit behind a claimed LLM endpoint or model ID. Use when an agent must investigate whether a provider is genuine, proxied, aliased, aggregated, wrapped, or currently unusable across OpenAI-compatible protocol layers, GPT/OpenAI, Anthropic/Claude, Google Gemini, GLM/Zhipu, Qwen/Tongyi, Kimi/Moonshot, MiniMax, DeepSeek, and mixed compatibility gateways. Supports deeper family-fingerprint analysis, long-context tests, structured-output stress, refusal and variance profiling, streaming/error clues, repeated stability checks, and cross-provider comparison reports.
As a process F 38/100 · Will not run — References files that are not bundled: references/fingerprint-*.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: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/fingerprint-*.md
Process rating: all ten parameters 38/100
- 0Tools and files. 1 referenced file(s) missing: references/fingerprint-*.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
- 50Failures and branches. 0 branches, has a failure section
- 85Steps. 64 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 913 tokens
- 100Running it twice. No mutating operations
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
- +1No license
- +2Single-language instructions
- +3Description length 632: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 64 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (9 of 16)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.