AB kb_eval_repo
Evaluate whether a GitHub/open-source repository is useful for the user's selected Research KB context. Use for query-page tasks asking to assess a repo's relevance, usefulness, reproducibility, setup effort, risks, or whether it is worth studying; accepts Java backend research_kb_agent_task JSON with taskType kb_query or kb_eval_repo and returns query-compatible answer/citations.
Evaluate whether a GitHub/open-source repository is useful for the user's selected Research KB context.
As a process B 67/100 · Nearly there — weak spots: failures and branches, consistency, progress reporting
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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 67/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (kb_eval_repo) differs from the folder (kb-eval-repo)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 36 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 683 tokens
- 100Running it twice. No mutating operations
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 383: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.