SKILLEMALL.ai

BC Contacts

Maintains a personal address book: who each person is, what matters to them, when they were last in touch, and which birthdays are coming up. Use when someone is mentioned by name with context worth keeping — met, called, or ran into them; when a birthday, anniversary, or death anniversary is approaching; when the question is what do I know about X, who do I know at Acme, who lives in Berlin, or who have I not spoken to in months; before a meeting, to surface what happened last time; when reconnecting after a long silence, or drafting a congratulations, a condolence, or a message about a job change or a bereavement; when making or chasing an introduction; when duplicates, name changes, or an export have to be merged into one address book; and when deciding what should never be written down about someone else. Not for sales pipelines and forecasts (`crm`), friendship depth (`friends`), family logistics (`family`), gift ideas (`gifts`), or reminders unrelated to people (`remind`).

ClawHub Agent Skills author: Iván v1.0.3 MIT-0 17 files body ≈ 6 142 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, consistency

GeneratorInfrastructuretype 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
C
61/100
Has gaps
Inputs and preconditions w 11
0
Consistency w 8
40
When it triggers w 12
50
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 ≈ 6142 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 61/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (Contacts) differs from the folder (people)
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (read) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Failures and branches. 7 branches
  • 70Execution cost. Instruction body is 6142 tokens
  • 100Steps. 40 steps
  • 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 13 top-level sections: this looks like several domains in one skill
  • 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Description length 993: 120–800 characters recommended
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 13 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: clean
This is a local contacts-memory skill that clearly discloses persistent address-book writes and does not show exfiltration, hidden execution, or credential handling.
LLM: benign (high) · VirusTotal: · 27 Jul 2026