design media by tsinghua-fib-lab
Scientific Visualization (bundled support) tsinghua-fib-lab/scientific-visualization
Publication-quality chart patterns for agentsociety-analysis Stage 4 refine — Okabe-Ito palettes, seaborn CI bands, small multiples, error bars, grayscale-safe encoding.
What it changes View full report → Passed 18 of 22 test cases with the skill, and 15 of 22 without it.
Without skill 68%
With skill 82%
Checks it passed that the model alone missed and 4 more in the full report
4 fixed14 passed either way3 still failing1 broke
Pass-rate lift +14 pp
Tokens -3%
Agent turns 0%
Response time -14% Model gemini-3.6-flashMeasured 8/15/2026 v1 18 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/tsinghua-fib-lab-scientific-visualization/SKILL.md https://app.decimal.ai/s/tsinghua-fib-lab-scientific-visualization/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add tsinghua-fib-lab-scientific-visualization, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/tsinghua-fib-lab-scientific-visualization/ and pins it in .decimal/skills.lock
$ decimalai skills add tsinghua-fib-lab-scientific-visualizationCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/tsinghua-fib-lab-scientific-visualization/SKILL.md https://app.decimal.ai/s/tsinghua-fib-lab-scientific-visualization/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt I am tasked with creating `charts/chart_11_ablation.py`. What workspace workflow reference documents should be inspected before writing code?
What was checked, without and with the skill Checked Without skill With skill The workflow specifies checking `references/charts.md` or `assets/chart_scaffold.reference.py` before code implementation.
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 38 lines single file
Scientific Visualization (bundled support)
Active only during agentsociety-analysis explore/refine/produce. Does not replace figure contracts or harness gates.
When to read
Writing charts/chart_NN_*.py via run-code
Chart failed squint test or validate-chart
User asks for better-looking or clearer plots
Read order
references/charts.mdreferences/chart-recipes.mdassets/chart_scaffold.reference.pyreferences/api.md
Absorbed sources (patterns only — no external deps required)
AgentSociety overrides
English-only legend text
matplotlib Agg required
Simulation caveats — no overstated significance
Semantic palette locked per condition across report
PNG in assets/ required; interactive HTML optional
Quick invoke
Copy scaffold → pick recipe letter (A–G) → fill SQL/pandas → save_chart_bundle → rubric → compose-figure if needed.
When it activates Automatically, when a task matches.
Use when writing run-code chart scripts or reviewing chart QA failures.
Track record Benchmark 18 / 22
test cases passed, vs 15 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported tsinghua-fib-lab / agentsociety
extension/skills/agentsociety-analysis/v1.0.0/support/scientific-visualization/SKILL.md
View on GitHub ↗ License Apache-2.0Imported 8/3/2026Version v1