AC literature-review-paper-screener
Literature Review Paper Screener V1.1. 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. Literature Review task type only; Medical Science focus.
Literature Review Paper Screener V1.1. The local agent (internet-enabled, free) searches for literature, collects evidence, builds per-paper Evidence Records…
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 11 mutating operations with no state check
- 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 4559 tokens
- 85Steps. 61 steps, 2 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 606: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 61 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: 80.