BF tick-coord
Multi-agent task coordination via Git-backed Markdown (tick-md). Use when coordinating work across avatars or agents, managing tasks, tracking dependencies, or running multi-agent workflows with TICK.md files.
As a process F 61/100 · Will not run — References files that are not bundled: docs/tag-conventions.md
How to improve
- The text references files that are not there: add them or drop the references.
For the model run — optional
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-background-processSKILL.md:498Starts a background / autostarted process (quoted — discussed, not commanded)The dashboard dev server must run as a **detached background process** to avoid being killed by exec tool timeouts. The `tick-board.sh` script handles this automatically using `setsid` and a PID file,
quoted -
low Dangerous commands
cmd-background-processSKILL.md:503Starts a background / autostarted processsetsid pnpm dev --port 3000 --host 0.0.0.0 </dev/null > /tmp/tick-board.log 2>&1 &
-
low Dangerous commands
cmd-background-processSKILL.md:510Starts a background / autostarted process (detector / deny-list definition)Always use the script or the `setsid` pattern. Never run the dev server as a foreground exec command.
detector
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: docs/tag-conventions.md
Process rating: all ten parameters 61/100
Will not run. References files that are not bundled: docs/tag-conventions.md
- 0Tools and files. 1 referenced file(s) missing: docs/tag-conventions.md
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4835 tokens
- 100Steps. 73 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- -5TODO / placeholder text left in the skill
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +3Description length 209: enough signal without eating the budget
- +4Structure: 61 headings
- +3Step-by-step instructions: 73 items
- +4Has examples (41 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.
External checks
ClawHub: suspicious
This task coordination skill appears legitimate, but it can expose project task data through a network dashboard and remote sync that are not clearly disclosed up front.
LLM: suspicious (high) · VirusTotal: · 29 May 2026