AB cc-sticky-notify
Install, configure, or fix cc-sticky-notify — a notification system that displays a pinned yellow sticky note in the Mac top-right corner for key Claude Code events (task completed, permission required, command failed, etc.). No third-party dependencies; uses a native Swift floating window + macOS display notification dual-layer approach, fully self-contained within the skill directory. Use this skill when the user says "install sticky notify", "configure Mac task notifications", "set up Claude Code completion alerts", "sticky notify not working", "reinstall notification hook", etc. Also used for updating scripts or troubleshooting notification failures.
As a process B 73/100 · Nearly there — weak spots: result and completion, progress reporting
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-shell-rcSKILL.md:139Writes to a shell startup fileecho 'export CC_STICKY_NOTIFY_CLOSE_TIMEOUT=300' >> ~/.zshrc
-
low Dangerous commands
cmd-background-processscripts/notify.sh:131Starts a background / autostarted processdisown $!
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 73/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 21 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1403 tokens
- 100Running it twice. Mutating operations check current state
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
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 662: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.