BC content-claim-navigator
Use whenever a creator mentions receiving a Content ID claim, copyright claim, copyright strike, takedown, demonetization notice, muted audio, blocked upload, or rights-holder match on their own uploaded work, even if they don't name the system involved. Explains the procedural flow of automated content claims and organizes the creator's existing documentation into an evidence organizer with a deadline timeline. Tier 1 (full procedural coverage): YouTube Content ID, Meta Rights Manager (Facebook and Instagram), TikTok. Tier 2 (general guidance plus pointer to official docs): Twitch, SoundCloud. All other platforms: explain the shared DMCA layer only and direct to that platform's help center. Do NOT use for: trademark disputes, defamation, community-guideline actions unrelated to copyright, claims the user wants to file against someone else (label and distributor operators defending their own roster's uploads ARE in scope; enforcement against others is not), or any request to evade, defeat, or probe matching systems.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Shorten the description to 1024 characters.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityreferences/eval-plan.md:47Offensive-security / dual-use content (legitimate for authorised testing; review intended use)3. **Red team (release candidate):** the ten extraction trajectories
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1032 chars, limit 1024 - warning
body-longSKILL.md body ≈ 14757 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "status" - note
frontmatter-keyunknown frontmatter key "ecosystem" - note
frontmatter-keyunknown frontmatter key "last_verified"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 21 mutating operations with no state check
- 40Consistency. Frontmatter name (content-claim-navigator) differs from the folder (content-id-guide)
- 40Execution cost. Instruction body is 14757 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 67 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 19 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Description length 1031: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 18 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (12 of 16)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.