AB dex-skill
Manage your Dex personal CRM — search, filter, create, archive, and update contacts; log notes; manage follow-ups, tags, groups, and custom fields; search connected email; and read or manage connected calendars. Use this skill to: (1) Find, add, or update contacts, (2) Log meetings and notes, (3) Manage reminders and keep-in-touch cadence, (4) Organize tags, groups, and custom fields, (5) Merge or archive contacts, (6) Review relationships or prepare meetings, (7) Search correspondence, (8) Manage calendar events, (9) Categorize, audit, or clean a network, (10) Turn notetaker output or transcripts into notes and follow-ups, (11) Prepare multiple meetings or event follow-up, (12) Research a contact on the public web, (13) See what is coming up — upcoming birthdays, due reminders, and who to reach out to, (14) Authenticate via /dex-login, or handle another personal CRM task involving the user's professional network.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5635 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5635 tokens
- 100Steps. 125 steps
- 100Failures and branches. 7 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
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)
- +3Description length 927: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 28 headings
- +3Step-by-step instructions: 125 items
- +3Output format is stated explicitly
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.