AD crm
Personal CRM for managing contacts, relationships, and follow-ups using markdown files. Use when the user wants to add contacts, track relationships, set follow-up reminders, query contacts by tag/company/location, import/export contacts, or manage networking leads. Supports natural language input for adding contacts.
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (crm) differs from the folder (clawdbot-crm-skill)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 8 steps
- 100Execution cost. Instruction body is 1332 tokens
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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 319: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (11 code blocks)
- +3All 8 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.