SKILLEMALL.ai

BF resource-2-nas

Use when a user asks to search for movie, TV, animation, or other media resources; provides a Quark/Baidu share link to save; wants to verify saved resources through OpenList; wants to view/cancel OpenList transfer task progress; or wants to copy saved resources to NAS/SMB storage.

ClawHub Agent Skills author: Leochens v0.1.0 MIT-0 22 files body ≈ 7 579 tokens Open the sourceclawhub.ai analyzed 28 h ago

provides a Quark/Baidu share link to save; wants to verify saved resources through OpenList; wants to view/cancel OpenList transfer task progress; or wants to…

As a process F 52/100 · Will not run — References files that are not bundled: url, scripts/quark-save.mjs, scripts/baidu-save.mjs

ProcedureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
97
Quality 40%
60
Run on models
none yet
Process rating
F
52/100
Will not run
References files that are not bundled: url, scripts/quark-save.mjs, scripts/baidu-save.mjs
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Secrets in code secret-password-literal baidu-save.test.mjs:16
    Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
    assert.deepEqual(parseBaiduShareUrl("https://pan.baidu.com/s/1abcDEF?pwd=…"), {
    fixturequoted
  • low Secrets in code secret-password-literal quark-save.test.mjs:28
    Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
    "https://pan.quark.cn/s/abc123?pwd=…"
    fixturequoted
  • low Exfiltration read-dotenv README.md:30
    Reads a .env file
    cp .env.example .env

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7579 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: url
  • warning missing-ref reference to a missing file: scripts/quark-save.mjs
  • warning missing-ref reference to a missing file: scripts/baidu-save.mjs
  • warning missing-ref reference to a missing file: scripts/check-env.mjs

Process rating: all ten parameters 52/100

Will not run. References files that are not bundled: url, scripts/quark-save.mjs, scripts/baidu-save.mjs
  • 0Tools and files. 4 referenced file(s) missing: url, scripts/quark-save.mjs, scripts/baidu-save.mjs
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 7579 tokens
  • 100Steps. 170 steps
  • 100Failures and branches. 18 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 282: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 170 items
  • +4Has examples (19 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: clean
This skill appears purpose-aligned, but it requires powerful cloud-drive and NAS credentials and should only be used with accounts and storage you trust it to manage.
LLM: benign (medium) · VirusTotal: · 7 Jun 2026