SKILLEMALL.ai

BB CRM

Runs a CRM: contacts, companies, deals, pipeline stages, follow-ups, and the data hygiene that keeps it usable. Use when setting up, rescuing, or operating a CRM (personal, freelance, sales, donor, or job-search); when the pipeline needs review, a deal has gone quiet, a forecast has to be defended, or who has not been contacted in months; when contacts are duplicated, bouncing, or out of date; when importing/exporting a CSV of leads, or migrating between plain files, Notion, HubSpot, or Salesforce; when choosing which CRM to use, or why nobody updates the current one; when defining stages, fields, tags, lead scoring, or win/loss reasons; when logging a call or email for later; and when a deletion, unsubscribe, or do-not-contact request has to be honored. Not for address-book upkeep and birthdays (`people`), delivering the client work itself (`clients`), outreach campaigns (`outreach`), sourcing candidates (`recruiter`), or support tickets (`customer-support`).

ClawHub Agent Skills author: Iván v1.0.2 MIT-0 17 files body ≈ 6 041 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 74/100 · Nearly there — weak spots: inputs and preconditions

ProcedureNotionSalesforceHubSpotSales and CRMtype and topics are labelled automatically from the skill text
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
66
Run on models
none yet
Process rating
B
74/100
Nearly there
Inputs and preconditions w 11
0
Tools and files w 18
60
Result and completion w 14
60
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.
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: 17. 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 body-long SKILL.md body ≈ 6041 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "changelog"

Process rating: all ten parameters 74/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 6041 tokens
  • 100Steps. 40 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 4 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 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (6 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
  • +3Description length 974: 120–800 characters recommended
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 40 items
  • +3Output format is stated explicitly

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
The CRM skill is coherent and local-only, but it gives an agent broad authority to change and sometimes delete shared CRM/contact records without consistently requiring explicit confirmation.
LLM: suspicious (high) · 27 Jul 2026