BF attribution-engine
Use whenever a creator, manager, or label is preparing credits, attribution, disclosures, or AI-content labels before publishing, or asks how to credit collaborators, disclose brand relationships, label AI involvement, or format credits for a specific platform. Tier 1 (native-tool platforms): YouTube, TikTok, Instagram. Tier 2 (distributor-metadata pipeline): Spotify, SoundCloud, and other music services, where credits flow through the distributor, not captions. Any other platform: route to its current official documentation. Do NOT use for: determining legal compliance, validating licenses or ownership, drafting contracts, or any request to conceal required disclosures.
As a process F 58/100 · Will not run — References files that are not bundled: references/links.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7411 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/links.md - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "ecosystem" - note
frontmatter-keyunknown frontmatter key "status" - note
frontmatter-keyunknown frontmatter key "last_verified"
Process rating: all ten parameters 58/100
- 0Tools and files. 1 referenced file(s) missing: references/links.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 26 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Execution cost. Instruction body is 7411 tokens
- 100Steps. 33 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 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 13 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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 679: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 33 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.