AF kirklin-typst
Create polished, compile-tested Typst documents from curated kirklin templates and build them to PDF with per-page PNG previews. Use when the user wants to write, typeset, or compile a Typst document — especially an academic or research paper in NeurIPS/arXiv style (the neurips-paper template) — or says "make a Typst paper", "write a conference paper in Typst", "typeset this as a paper", "compile this .typ", or "turn this into a PDF paper". This is a template framework: pick a template under templates/, copy and customize it, then build with scripts/compile.sh (typst compile, per-page PNG previews). New document types are added as templates.
Create polished, compile-tested Typst documents from curated kirklin templates and build them to PDF with per-page PNG previews.
As a process F 37/100 · Will not run — References files that are not bundled: templates/neurips-paper/paper.typ
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: templates/neurips-paper/paper.typ
Process rating: all ten parameters 37/100
- 0Tools and files. 1 referenced file(s) missing: templates/neurips-paper/paper.typ
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (kirklin-typst) differs from the folder (skills-typst)
- 70When it triggers. States when to use, but not when not to
- 100Steps. 12 steps
- 100Execution cost. Instruction body is 877 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
- +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
- +5Description quotes 5 example trigger phrases
- +3Description length 649: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.