CF clawdate
Detailed SOP for ClawDate lobster operators. Use when installing or re-binding one owner account, validating whoami/sync/browse, collecting missing owner intake, submitting the owner profile JSON, and keeping a 5-minute cron sync running.
As a process F 45/100 · Will not run — References files that are not bundled: assets/profile-sync.sh.template
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.
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.
- 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 · 9
-
high Dangerous commands
cmd-persistencescripts/init_owner.sh:184Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v -F "${PROFILE}-sync.sh"; echo "$CRON_ENTRY" ) | crontab - -
high Dangerous commands
cmd-persistenceSKILL.md:242Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v -F "__PROFILE__-sync.sh"; echo "$CRON_ENTRY" ) | crontab -
Medium and low: 7
-
medium Dangerous commands
cmd-persistenceassets/cron.example.txt:2Persistence mechanism (cron / launchd / scheduled task / autorun registry) (test fixture / example file)( crontab -l 2>/dev/null | grep -v -F "__PROFILE__-sync.sh"; echo "$CRON_ENTRY" ) | crontab -
fixture -
low Dangerous commands
cmd-cron-mentionassets/cron.example.txt:2Mentions editing / listing crontab (test fixture / example file)( crontab -l 2>/dev/null | grep -v -F "__PROFILE__-sync.sh"; echo "$CRON_ENTRY" ) | crontab -
fixture -
low Dangerous commands
cmd-cron-mentionassets/cron.example.txt:3Mentions editing / listing crontab (test fixture / example file)crontab -l | grep -F "__PROFILE__-sync.sh"
fixture -
low Dangerous commands
cmd-cron-mentionscripts/init_owner.sh:184Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v -F "${PROFILE}-sync.sh"; echo "$CRON_ENTRY" ) | crontab - -
low Dangerous commands
cmd-cron-mentionscripts/init_owner.sh:185Mentions editing / listing crontabcrontab -l | grep -F "${PROFILE}-sync.sh" || warn "Cron entry write verification did not echo back." -
low Dangerous commands
cmd-cron-mentionSKILL.md:242Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v -F "__PROFILE__-sync.sh"; echo "$CRON_ENTRY" ) | crontab -
-
low Dangerous commands
cmd-cron-mentionSKILL.md:243Mentions editing / listing crontabcrontab -l | grep -F "__PROFILE__-sync.sh"
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/profile-sync.sh.template
Process rating: all ten parameters 45/100
- 0Tools and files. 1 referenced file(s) missing: assets/profile-sync.sh.template
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Steps. 75 steps
- 100Failures and branches. 12 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2507 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 238: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 75 items
- +4Has examples (14 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.