AA paperzilla-monitor
Monitor and discuss research papers from one Paperzilla project using the `pz` CLI inside OpenClaw. Use when users want recent papers, metadata, markdown-based summaries, why a paper matters for current work, a recurring weekday brief, or Paperzilla feed triage in chat.
As a process A 85/100 · Runs to the end — weak spots: consistency, running it twice
How to improve
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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 85/100
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (paperzilla-monitor) differs from the folder (paperzilla-research-monitor)
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 105 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 5 branches, has a failure section
- 100Execution cost. Instruction body is 2094 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 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)
- +2Single-language instructions
- +3Description length 270: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 105 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
External checks
ClawHub: clean
This is a coherent Paperzilla research-brief helper that uses an existing authenticated CLI and optional Telegram delivery, with limited disclosed state for recurring briefs.
LLM: benign (high) · VirusTotal: · 29 May 2026