AB pushman
Safely send, inspect, and diagnose personal iPhone notifications through Pushman MCP tools or the installed Pushman CLI. Use when a request names Pushman, asks to notify the user from an agent or terminal workflow, targets Pushman devices, history, usage, login, pairing, authorization, or delivery diagnostics, or needs help configuring the local Pushman MCP server; do not use for implementing generic APNs/FCM push systems or operating unrelated notification services.
Safely send, inspect, and diagnose personal iPhone notifications through Pushman MCP tools or the installed Pushman CLI.
As a process B 69/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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: 4. 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 69/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 58 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 26 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1607 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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 471: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 26 items
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.