BF working-with-emm
Stores and retrieves personal preferences, decisions, and context across conversations using Emm AI via MCP, and (when enabled) runs Emm AI's standing instructions, output wiki, and recurring-task cycle on top. Activates when the user mentions remembering, recalling decisions, saving info for later, personalized recommendations, shared context with others, controlling connected devices, or anything benefiting from long-term memory. Also activates when personal context would improve the response (trip planning, meeting prep, purchases, diet, health, or any request where knowing user history matters), AND when the user asks for an "agent run", "run the cycle", "what's on my dashboard", "drain my tasks", or equivalent phrasing tied to Emm AI's mission-control surface.
As a process F 50/100 · Will not run — References files that are not bundled: <actor_url>/app/memory, …, <actor_url>/app/memory
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-usescripts/manual-oauth.sh:95Credential used in a network call (verify the destination is the intended service)TOKEN_RESPONSE=$(curl -sf -X POST "$TOKEN_URL" \
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 12662 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: <actor_url>/app/memory - warning
missing-refreference to a missing file: … - warning
missing-refreference to a missing file: <actor_url>/app/memory - warning
missing-refreference to a missing file: url - warning
missing-refreference to a missing file: <actor_url>/app/outputs?category=<c>&id=<id> - warning
missing-refreference to a missing file: <host>/<actor_id>/app/outputs?category=email&id=42 - warning
missing-refreference to a missing file: <actor_url>/app/memory - warning
missing-refreference to a missing file: <host>/<actor_id>/app/memory
Process rating: all ten parameters 50/100
- 0Tools and files. 8 referenced file(s) missing: <actor_url>/app/memory, …, <actor_url>/app/memory
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 12662 tokens: crowds the task out of the window
- 70When it triggers. States when to use, but not when not to
- 100Steps. 74 steps
- 100Failures and branches. 25 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
- low 23 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (24 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
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 775: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.