SKILLEMALL.ai

BC create-teammate

Distill a teammate into an AI Skill. Auto-collect Slack/Teams/GitHub data, generate Work Skill + 5-layer Persona, with continuous evolution. Use when: user wants to capture a colleague's knowledge before they leave, create an AI version of a teammate, distill tribal knowledge into a reusable skill, or says /create-teammate.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: MyClaw.ai v2.0.0 MIT-0 37 files body ≈ 4 245 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

GeneratorSlackGitHubInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
82
Quality 40%
87
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Running it twice w 4
30
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Instruction override
If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 1

  • high Instruction override en-ignore-previous SKILL.md:306
    Instruction-override phrase ("ignore previous instructions")
    5. Correction Log entries override earlier rules

Files scanned: 37. 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 63/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 14 mutating operations with no state check
  • 40Consistency. Frontmatter name (create-teammate) differs from the folder (teammate-skill)
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 4245 tokens
  • 100Steps. 33 steps
  • 100Failures and branches. 16 branches, has a failure section
  • 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 325: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 33 items
  • +3Output format is stated explicitly
  • +4Has examples (21 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

External checks

ClawHub: suspicious
This skill is not overtly malicious, but it can collect, persist, export, and impersonate sensitive coworker communications without enough consent, scoping, or review safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026