BC video-recommendation
Recommend videos with precision, not addiction. Use when a user asks what to watch, wants video recommendations, wants a curated watchlist, wants direct video links, or wants suggestions based on recent chat instead of generic platform algorithms. Best for context-aware, taste-driven, non-feed-based video discovery. Supports: direct links, themed watchlists, project-aligned recommendations, mood-based picks, and bilingual curation.
As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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
-
high Instruction override
en-ignore-previousskill-card.md:21Instruction-override phrase ("ignore previous instructions")Mitigation: Avoid sharing private details unless they should influence recommendations, and ask the skill to ignore prior context when neutral recommendations are desired. <br>
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Recommend videos with precision, not addiction. Use when a user as… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Steps. 82 steps, 4 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 7 branches
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1493 tokens
- low 11 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)
- +1No license
- +2Single-language instructions
- +3Description length 435: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 82 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.