CD ocas-spot
Use when checking appointment availability, booking services, monitoring for openings, or discovering venues at salons, spas, and restaurants. spot.discover finds and compares venues via Yelp before booking. Supports Acuity Scheduling, Square Appointments, Resy, Tock, SevenRooms, OpenTable, Meevo, Vagaro, Mindbody, Fresha, StyleSeat, Calendly, Yelp Reservations, Booksy, GlossGenius, SimplyBook.me, Boulevard, Mangomint, DaySmart, ResDiary, and Eat App. Integrates with ocas-vpn for bot block bypass. NOT for general travel planning (use ocas-voyage), calendar sync (use ocas-sands), restaurant reservations on unsupported platforms. Trigger phrases: 'book an appointment at', 'check availability at', 'when can I get a [service]', 'find me a slot at', 'is [venue] available', 'watch [venue] for openings', 'alert me when [venue] has availability', 'monitor [venue]', 'find a restaurant in', 'compare salons near', 'discover [type] near'.
spot.discover finds and compares venues via Yelp before booking. Supports Acuity Scheduling, Square Appointments, Resy, Tock, SevenRooms, OpenTable, Meevo…
As a process D 46/100 · Unfinished process — References files that are not bundled: references/platforms/<platform>.md
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
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The text references files that are not there: add them or drop the references.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 5
✓ No critical or high findings
Medium and low: 5
-
medium Dangerous commands
cmd-privilegereferences/virtualperson-patches/vpn-socks5-bridge.sh:54Privilege escalation / world-writable permissionscd "$TMPDIR/microsocks" && make 2>/dev/null && sudo cp microsocks /usr/local/bin/
-
low Dangerous commands
cmd-privilegereferences/platforms/square_booking_pattern.md:59Privilege escalation / world-writable permissions (detector / deny-list definition)args: ['--no-sandbox', '--disable-setuid-sandbox']
detector -
low Dangerous commands
cmd-privilegereferences/stealth-config.md:52Privilege escalation / world-writable permissions (quoted — discussed, not commanded)'--disable-setuid-sandbox',
quoted -
low Dangerous commands
cmd-privilegescripts/reservation_toolkit.py:348Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)'--no-sandbox', '--disable-setuid-sandbox',
detectorcode literal -
low Dangerous commands
cmd-privilegescripts/square.js:14Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)args: ['--no-sandbox', '--disable-setuid-sandbox'],
detectorcode literal
Files scanned: 79. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 940 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
missing-refreference to a missing file: references/platforms/<platform>.md - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "includes"
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: references/platforms/<platform>.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Consistency. The Hermes dialect needs category and tags
- 70Execution cost. Instruction body is 4516 tokens
- 100Steps. 48 steps
- 100Failures and branches. 1 branches, has a failure section
- 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 22 top-level sections: this looks like several domains in one skill
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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 940: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -2localhost URLs: will not work for another user
- -32 of 5 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 29 headings
- +3Step-by-step instructions: 48 items
- +4Reference files are cited in the instructions (16 of 25)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.