BC new-agent-setup
Set up a new OpenClaw agent from scratch. Use when Tom asks to create, add, or onboard a new agent. Covers everything: gathering requirements, Discord bot setup, openclaw.json configuration, Mission Control registration, heartbeat, cron, OneDrive access, and final verification.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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.
- 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 · 4
-
high Dangerous commands
cmd-persistencereferences/checklist.md:158Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l; echo "<minute>,<minute+10>,... * * * * MC_AGENT=<agent-id> ~/.openclaw/skills/mission-control/mc checkin >> ~/.openclaw/logs/mc-checkin.log 2>&1") | crontab -
Medium and low: 3
-
low Dangerous commands
cmd-cron-mentionreferences/checklist.md:156Mentions editing / listing crontab (detector / deny-list definition)Nächsten freien Minuten-Slot wählen (bestehende Belegung prüfen mit `crontab -l`):
detector -
low Dangerous commands
cmd-cron-mentionreferences/checklist.md:158Mentions editing / listing crontab(crontab -l; echo "<minute>,<minute+10>,... * * * * MC_AGENT=<agent-id> ~/.openclaw/skills/mission-control/mc checkin >> ~/.openclaw/logs/mc-checkin.log 2>&1") | crontab -
-
low Dangerous commands
cmd-cron-mentionreferences/checklist.md:238Mentions editing / listing crontab (quoted — discussed, not commanded)- [ ] Crontab korrekt gestaffelt (`crontab -l`)
quoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Set up a new OpenClaw agent from scratch. Use when Tom asks to cre… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 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. 6 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 528 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 278: enough signal without eating the budget
- +4Structure: 3 headings
- +3Step-by-step instructions: 32 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.