CD review-reply
Automatically monitors your App Store reviews and drafts warm, on-brand replies for 1–3 star reviews — so unhappy users hear back fast. Connects to App Store Connect API, detects repeat complaint patterns as bug signals, and delivers a daily approval queue to Telegram at 8am. You approve, it sends. Supports multiple apps simultaneously.
As a process D 47/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- 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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 6
-
high Dangerous commands
cmd-persistenceREADME.md:425Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load /Library/LaunchAgents/com.talos.reviewreply.monitor.plist
Medium and low: 5
-
medium Dangerous commands
cmd-persistenceREADME.md:382Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)Create `/Library/LaunchAgents/com.talos.reviewreply.monitor.plist`:
quoted -
medium Instruction override
en-ignore-previousscripts/draft_reply.py:122Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)"ignore previous instructions",
detector -
low Dangerous commands
cmd-cron-mentionREADME.md:82Mentions editing / listing crontabcrontab -e
-
low Exfiltration
exfil-webhook-urlscripts/pattern_detector.py:328Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"placeholder -
low Exfiltration
exfil-webhook-urlscripts/queue_manager.py:464Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"placeholder
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 338 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill
Process rating: all ten parameters 47/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (review-reply) differs from the folder (nicholasrae-review-reply)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 30 steps
- 100Execution cost. Instruction body is 2261 tokens
- low 10 top-level sections: this looks like several domains in one skill
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)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -33 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 338: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.