GitHub issue/PR counter on K-Dense-AI/claude-scientific-skills is at 49.
Renumbered all tracking docs to #50 (next available):
- issue-00000050-markdown-mermaid-skill.md (renamed from 00000001)
- pr-00000050-markdown-mermaid-skill.md (renamed from 00000001)
- kanban/feat-00000050-markdown-mermaid-skill.md (new)
Cross-references updated throughout. PR record now links to kanban board.
Upstream PR URL set to https://github.com/K-Dense-AI/claude-scientific-skills/pull/50
All 40 references to borealBytes/opencode updated to the correct source:
https://github.com/SuperiorByteWorks-LLC/agent-project
Affected files: SKILL.md, all 24 diagram guides, 9 templates, issue and PR
docs, plus assets/examples/example-research-report.md (new file).
The example report demonstrates full skill usage: flowchart, sequence,
timeline, xychart, radar diagrams — all with accTitle/accDescr and
classDef colors, no %%{init}. Covers HEK293T CRISPR editing efficiency
as a realistic scientific context.
New skill establishing markdown + Mermaid diagrams as the default and
canonical documentation format for all scientific skill outputs.
Core principle (from K-Dense Discord, 2026-02-19): Mermaid in markdown
is the source of truth — text-based, version-controlled, token-efficient,
universally renderable. Python/AI images are downstream conversions only.
SKILL.md includes:
- Full 'source format' philosophy with three-phase workflow diagram
- 24-entry diagram type selection table with links to each guide
- 9-entry document template index
- Per-skill integration guides (scientific-schematics, scientific-writing,
literature-review, and any other output-producing skill)
- Quality checklist for finalizing documents from any skill
- Full attribution for ported Apache-2.0 content
Originated from conversation between Clayton Young (Boreal Bytes) and the
K-Dense team regarding documentation standards for shared scientific skills.
All content ported from borealBytes/opencode under Apache-2.0 license with
attribution headers prepended to each file.
- references/markdown_style_guide.md (~733 lines): full markdown formatting,
citation, collapsible sections, emoji, Mermaid integration, and template
selection guide
- references/mermaid_style_guide.md (~458 lines): full Mermaid standards —
emoji set, classDef color palette, accessibility (accTitle/accDescr),
theme neutrality (no %%{init}), and diagram type selection table
- references/diagrams/ (24 files): per-type exemplars, tips, and templates
for all Mermaid diagram types
- templates/ (9 files): PR, issue, kanban, ADR, presentation, how-to,
status report, research paper, project docs
Source: https://github.com/borealBytes/opencode
Documents the feature request to add a skill establishing markdown+Mermaid
as the canonical source format for scientific documentation. Includes the
originating K-Dense Discord conversation, three-phase workflow diagram
(Mermaid → Python → AI images), acceptance criteria, and technical spec
for the skill directory structure.
Files touched: docs/project/issues/issue-00000001-markdown-mermaid-skill.md
New skill for generating scientific infographics including:
- SKILL.md with comprehensive guidelines for infographic creation
- Design principles and color palette references
- Scripts for AI-powered infographic generation
- Support for various infographic types (statistical, process, comparison, etc.)
Co-authored-by: Cursor <cursoragent@cursor.com>
- Added criteria for identifying high-quality literature, emphasizing the importance of Tier-1 journals and citation counts.
- Updated guidelines for citation finding to prioritize influential papers and reputable authors.
- Revised abstract writing instructions to reflect the preference for flowing paragraphs over structured formats.
- Included best practices for generating AI schematics, specifically regarding figure numbering and content clarity.
- Replace direct calls to AllChem, Pairs, and Torsions with rdFingerprintGenerator in similarity_search.py
- Update example code in SKILL.md to reflect the new API usage
- Maintain existing functionality while adopting the modern fingerprint generation interface recommended by RDKit
