AB feishu-openclaw-paper-manager
Design or implement a paper-management workflow built on a Feishu bot plus OpenClaw. Use when the user wants to ingest papers from Feishu messages, save PDFs or source links into a Feishu cloud-docs paper folder, maintain a searchable multi-dimensional table of paper metadata and reusable tags, or evolve the tag taxonomy after every 50 newly added papers.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, consistency
How to improve
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (feishu-openclaw-paper-manager) differs from the folder (feishu-paper-manager)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 137 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 2620 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 17 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 357: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 137 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.