SKILLEMALL.ai

BF probe_first_research

Probe-first deep research — low-cost snippet reconnaissance before committing to full searches

ClawHub Agent Skills author: lkm123 v1.0.0 MIT-0 4 files body ≈ 5 216 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 46/100 · Will not run — References files that are not bundled: URL

ReferenceInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
95
Quality 40%
52
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: URL
Tools and files w 18
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: WebSearch WebFetch Read Write Edit Bash AskUserQuestion

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5216 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: URL

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: URL
  • 0Tools and files. 1 referenced file(s) missing: URL
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (probe_first_research) differs from the folder (probe-first-research)
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 5216 tokens
  • 100Steps. 137 steps
  • 100Failures and branches. 28 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
  • low 14 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)
  • +3Description length 94: 120–800 characters recommended
  • +2Single-language instructions
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 137 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.

External checks

ClawHub: clean
This is a coherent web-research workflow skill; its local note-writing behavior is worth noticing but matches long research sessions and is disclosed in the artifact.
LLM: benign (high) · VirusTotal: · 29 May 2026