BC crm-deduplication
Keep CRM accounts and contacts duplicate-free: audit company and person identity, run recurring deduplication plays directly on CRM models, merge safe exact matches, and route uncertain clusters to manual review. Triggers: "deduplicate our CRM accounts", "deduplicate CRM contacts", "our CRM has duplicate people", "merge duplicate contacts in HubSpot", "we keep creating duplicate account records", "merge duplicate companies in HubSpot", "set up recurring CRM deduplication", "review ambiguous duplicates". HubSpot, Salesforce, Attio, Slack, LinkedIn profiles, phone numbers, Cargo CDK, findRecords, Scoring, Human Review, mergeRecords. Skip when: the request is to add or refresh CRM data rather than merge duplicate records; use crm-enrichment.
Keep CRM accounts and contacts duplicate-free: audit company and person identity, run recurring deduplication plays directly on CRM models, merge safe exact…
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5078 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 51/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 18 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5078 tokens
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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
- +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
- +5Description quotes 8 example trigger phrases
- +3Description length 748: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.