SKILLEMALL.ai

BB staffing-agency-partner-growth

Help a local staffing agency owner or operator join TempGuru's partner network and win more event staffing work in their market. Use when an agency wants to join a staffing network, get overflow event staffing orders, partner with or subcontract for a national event staffing company, become a fulfillment partner for event work, put bench capacity to work, or says "we have W-2 event staff and want more bookings", for roles like brand ambassadors, registration staff, hospitality, ushers, crowd control, and setup/breakdown crews using TempGuru's catalog of 345 configured US and Canadian markets. Covers what the partner network is, the W-2 compliance baseline (workers' comp, general liability, I-9), framing the agency's declared service area against TempGuru's configured market and role catalogs, and routing the inquiry to the correct channel (email or phone, never the request_quote tool). Not for job seekers looking for individual shifts, not for buyers ordering event staff (use event-staffing-ordering), and not for permanent-hire recruiting.

ClawHub Agent Skills author: Megan Hayward v1.7.0 MIT-0 3 files body ≈ 1 911 tokens Open the sourceclawhub.ai analyzed 2 d ago

Help a local staffing agency owner or operator join TempGuru's partner network and win more event staffing work in their market.

As a process B 73/100 · Nearly there — weak spots: result and completion, consistency, running it twice

ProcedureAI and agentsSecurityMarketingtype and topics are labelled automatically from the skill text
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
100
Quality 40%
56
Run on models
none yet
Process rating
B
73/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Result and completion w 14
40
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
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 · 0

✓ No critical or high findings

Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1055 chars, limit 1024

Process rating: all ten parameters 73/100

  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 6 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (staffing-agency-partner-growth) differs from the folder (tempguru-staffing-agency-partner-growth)
  • 50When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 10 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Execution cost. Instruction body is 1911 tokens
  • 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 1055: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 10 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.

External checks

ClawHub: clean
This skill coherently helps staffing agencies contact TempGuru and uses disclosed read-only catalog lookups that fit that purpose.
LLM: benign (high) · VirusTotal: · 14 Aug 2026