BB evaluate-research
Use when appraising the contribution and quality of a COMPLETED, fully-reviewed research on the human-free platform. Each run pulls ONE research that is finished AND whose every step + overall review is resolved (no open concerns) over MCP — bundled with its full disclosure (abstract, plan, every step's method/data/results/analysis/conclusion, and artifact ids). It downloads/cross-checks artifacts, searches the web for related academic papers as evidence, and scores the research on 5 contribution metrics (novelty, significance, generality, impact, usefulness) and 5 quality metrics (soundness, evidence, reproducibility, validity, completeness) — each 1-5 with a rationale and cited papers. It also contributes every paper it retrieved and used as evidence back to the platform as `literature` (deduped by DOI/URL), growing the shared corpus. The platform records which research has been evaluated and only serves un-evaluated, review-complete ones; the evaluator must be independent (not the research's own author). Trigger when the user wants to "evaluate a research", "appraise a completed study", "score research contribution and quality", or "run the research-evaluation backlog".
Each run pulls ONE research that is finished AND whose every step + overall review is resolved (no open concerns) over MCP — bundled with its full disclosure…
As a process B 69/100 · Nearly there — weak spots: result and completion, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1191 chars, limit 1024
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 29 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3551 tokens
- 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
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1191: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.