BB task-runner
Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents. A heartbeat/cron dispatcher wakes periodically to check pending tasks, spawn workers, and report completions. The system never "finishes" — it always remains ready for the next task.
Persistent task queue system.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
✓ No critical or high findings
Medium and low: 6
-
low Dangerous commands
cmd-cron-mentionreferences/task-types.md:162Mentions editing / listing crontab (quoted — discussed, not commanded)**Verification:** Cron job registered (confirm with `crontab -l`); OR reminder file exists with correct content
quoted -
low Dangerous commands
cmd-cron-mentionreferences/verification-guide.md:168Mentions editing / listing crontab (documentation table row)| Cron job registered (if cron used) | `exec: crontab -l` | New cron entry appears with correct schedule |
table -
low Dangerous commands
cmd-cron-mentionreferences/verification-guide.md:177Mentions editing / listing crontabexec: crontab -l | grep "<task keyword>"
-
low Dangerous commands
cmd-cron-mentionreferences/verification-guide.md:191Mentions editing / listing crontab (quoted — discussed, not commanded)- `crontab -l` doesn't show the new entry
quoted -
low Dangerous commands
cmd-cron-mentionreferences/verification-guide.md:194Mentions editing / listing crontab (detector / deny-list definition)- Crontab syntax error (check with `crontab -l 2>&1`)
detector -
low Dangerous commands
cmd-cron-mentionreferences/verification-guide.md:278Mentions editing / listing crontab (documentation table row)| reminder-scheduling | Cron entry or file exists | `exec: crontab -l` or `ls` |
table
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (task-runner) differs from the folder (autonomous-task-runner)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4058 tokens
- 85Steps. 40 steps, 2 vague phrases
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 3 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 12 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)
- +1No license
- +2Single-language instructions
- +3Description length 356: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 40 items
- +3Output format is stated explicitly
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.