AC literature-review-paper-screener
Literature Review Paper Screener V1.4.6. The local agent (internet-enabled, free) searches for literature, collects evidence, builds per-paper Evidence Records with Evidence Availability Levels A-D, submits ONE paper per workbook row to the private LoomLoom Cloud template (rows run as independent parallel tasks, so screening never exceeds the platform per-activity timeout), then audits and merges the returned screening results and renders Excel Paper Sheet + Reading List. Cloud has no internet access; you gather the evidence and it evaluates it. Use it for Literature Review tasks in the Medical Science focus only; do not use it as a general citation manager, for other task types, or for disciplines it is not configured for. The bundled files are local helpers only — a pre-flight checker, a result validator, and an Excel renderer. All searching, downloading, and cloud submission is performed by the agent through the loomloom CLI, which this skill requires.
Literature Review Paper Screener V1.4.6. The local agent (internet-enabled, free) searches for literature, collects evidence, builds per-paper Evidence…
As a process C 63/100 · Has gaps — weak spots: result and completion, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5717 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 16 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5717 tokens
- 85Steps. 66 steps, 2 vague phrases
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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
- +3Description length 969: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 20 headings
- +3Step-by-step instructions: 66 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.