SKILLEMALL.ai
GitHub ↗ RU Sign in

AC crm-data-cleaner

Deduplicate, normalize, and enrich CRM contacts and companies. Use when a user needs to clean CRM data, find duplicate contacts, standardize phone numbers or emails, merge duplicate records, audit data quality, or enrich contacts with external sources like Clearbit or Apollo. Works with HubSpot, Salesforce, Pipedrive, or any CRM with CSV export. Instruction-only skill — no scripts or code execution. All operations are performed via CRM platform APIs or CSV export/import workflows.

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 2 files body ≈ 7 084 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Deduplicate, normalize, and enrich CRM contacts and companies.

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureHubSpotSalesforceGmailSales and CRMtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
74
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7084 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Execution cost. Instruction body is 7084 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 400 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 485: enough signal without eating the budget
  • +4Structure: 87 headings
  • +3Step-by-step instructions: 400 items
  • +4Has examples (34 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.