SKILLEMALL.ai

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.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: fischerlam v0.1.0 MIT-0 13 files body ≈ 1 493 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting

ProcedureMedia and videotype and topics are labelled automatically from the skill text
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
82
Quality 40%
84
Run on models
none yet
Process rating
C
59/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

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.

Instruction override
If you install

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.

For the author

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

  1. 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.
For the model run — optional
  • 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-previous skill-card.md:21
    Instruction-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-yaml SKILL.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.

External checks

ClawHub: clean
This appears to be a video recommendation skill whose personalization behavior is expected for its purpose, with some privacy and routing caveats but no evidence of harmful behavior.
LLM: benign (medium) · VirusTotal: · 29 May 2026