treatment-plans agent skill by K-Dense-AI

At a glance

Before you install

Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.

• Bundled scripts: 8 script files (8 Python). Your agent may run them, so read them first.
• License: MIT, an open-source or open-content license.

Install treatment-plans

The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.

npx skills add https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/skills/treatment-plans

tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/K-Dense-AI/claude-scientific-skills.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/treatment-plans .claude/skills/
rm -rf "$tmp"

python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
    --repo K-Dense-AI/claude-scientific-skills \
    --path skills/treatment-plans

K-Dense-AI/claude-scientific-skills is third-party code. Read SKILL.md and any bundled scripts before you install it.

How the author describes it

Formats and structurally validates local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and release gates—not for clinical decision-making.

From the description field of SKILL.md. Agents read this line to decide when to load the skill.

Compatibility, from SKILL.md

Sections in SKILL.md

• Hard safety boundary
• Required visible notice
• Data gate
• Allowed inputs
• Workflow
• 1. Establish authority and intended use
• 2. Generate a generic package
• 3. Transcribe supplied decisions without inference
• 4. Run deterministic local checks
• 5. Human review and release
• Source boundaries
• Verification
• Reference map
• Citing Scientific Agent Skills

Files in the skill folder

• SKILL.md
• assets/clinician_authored_intervention_template.json
• assets/goals_monitoring_checkpoint_template.json
• assets/informed_preference_shared_decision_template.json
• assets/intended_use_handoff_template.json
• assets/source_fact_manifest_template.json
• assets/transition_reconciliation_template.json
• references/README.md
• references/documentation_workflow.md
• references/privacy_governance.md
• references/safety_scope.md
• references/security_validation.md
• references/shared_decision_handoff.md
• references/source_boundaries.md
• references/source_ledger.md
• scripts/_common.py
• scripts/check_completeness.py
• scripts/check_consistency.py
• scripts/generate_template.py
• scripts/privacy_process_check.py
• scripts/timeline_generator.py
• scripts/validate_traceability.py
• scripts/validate_treatment_plan.py

Suede Skill Check: 91/100 · A

treatment-plans passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.

Where this skill is cited

K-Dense-AI/claude-scientific-skills appears in 2 curated lists: BehiSecc/awesome-claude-skills, travisvn/awesome-claude-skills.

More science and research skills

All science and research skills

More from K-Dense-AI/claude-scientific-skills

All 177 skills in K-Dense-AI/claude-scientific-skills