willoscar/survey-visuals
| Draft non-prose visuals artifacts (timeline, figure specs) for a survey, grounded in evidence and using citation keys from `citations/ref.bib`.
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill survey-visuals
This skill creates non-prose artifacts that make the writing stage less template-y:
Always read:
references/overview.mdreferences/figure_archetypes.mdRead by task:
references/timeline_patterns.md when building timeline milestonesMachine-readable assets:
assets/figure_templates.yaml — figure archetype specifications (extensible without code changes)Use scripts/run.py only for:
assets/figure_templates.yamlDo not treat run.py as the place for:
Tables are handled by dedicated table skills:
table-schema -> outline/table_schema.mdtable-filler -> outline/tables_index.md (internal index)appendix-table-writer -> outline/tables_appendix.md (reader-facing Appendix tables)outline/outline.ymloutline/claim_evidence_matrix.mdpapers/paper_notes.jsonlcitations/ref.biboutline/timeline.mdoutline/figures.mdoutline/outline.yml + outline/claim_evidence_matrix.md to decide what to visualize.papers/paper_notes.jsonl for year/milestone candidates.citations/ref.bib.1) Read the outline + claim-evidence matrix and pick recurring comparison axes.
2) Timeline (outline/timeline.md):
3) Figures (outline/figures.md):
4) Use only citation keys present in citations/ref.bib.
TODO and no <!-- SCAFFOLD ... --> markers remain in the outputs.outline/timeline.md contains >=8 year bullets and each bullet has >=1 citation marker [@...].outline/figures.md contains >=2 figure specs and each mentions at least one supporting citation.uv run python .codex/skills/survey-visuals/scripts/run.py --helpuv run python .codex/skills/survey-visuals/scripts/run.py --workspace <workspace>--workspace <workspace> (required)--unit-id <id> (optional; used only for runner bookkeeping)--inputs <a;b;c> (optional; defaults to the four Inputs listed above)--outputs <timeline_rel;figures_rel> (optional; defaults to outline/timeline.md;outline/figures.md)--checkpoint <C#> (optional; ignored by the helper)uv run python .codex/skills/survey-visuals/scripts/run.py --workspace <workspace>
uv run python .codex/skills/survey-visuals/scripts/run.py --workspace <workspace> --outputs outline/timeline.md;outline/figures.md
Fix:
[@...].paper-notes / evidence-draft rather than padding.Fix:
Take willoscar/survey-visuals from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.