Treatment-Plan Documentation Formatter
Formats and structurally checks local treatment-plan records that clinicians have already decided and signed off.
- Repository
- K-Dense-AI/scientific-agent-skills
- Stars
- 55,780
- Licence
- MIT
- Files
- 15 files
What it does
This skill helps an AI agent organize and check documentation of clinical decisions that a licensed clinician has already made and verified. It generates JSON template packages, guides the agent to copy clinician-authored facts with their source references, and runs local validation scripts for structure, traceability, completeness, and privacy process. It explicitly does not diagnose, recommend treatments, choose doses, check interactions, triage, or provide clinical advice, and every output must carry a draft, not-medical-advice, sign-off-required notice.
Great for
- Clinical documentation or quality teams in an authorized local environment who need structured, traceable records of decisions already made by clinicians
- Developers building local, synthetic-data tooling that validates JSON treatment-plan templates before clinician review
Skip it if
- Patients or caregivers seeking treatment advice, because the skill is designed to refuse clinical decisions and will not recommend therapies, doses, or urgency levels
- Any use with real patient data outside an approved local environment, because the skill itself warns against sending patient-derived content to models or external tools and requires institutional privacy review first
Try asking
- “Generate a synthetic treatment-plan template package in a local folder for a documentation workflow test”
- “Check a locally stored clinician-authored intervention JSON file for missing fields and traceability gaps”
- “Build a timeline of explicitly dated checkpoints from a verified local plan package”
- “Review a shared-decision record template for unresolved required fields before clinician sign-off”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 15 original files, the MIT licence and an attribution note.
treatment-plans.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip treatment-plans.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip treatment-plans.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Start with the synthetic classification and SYNTHETIC-style subject references so no real patient data enters the workflow while you learn the structure
- Keep the release gate blocked and rely on the authorized clinician and local policies to approve any release; the scripts only check structure
- Read references/safety_scope.md and references/privacy_governance.md before working with any patient-derived material
What's inside
- 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/documentation_workflow.md
- references/privacy_governance.md
- references/README.md
- references/safety_scope.md
- references/security_validation.md
- references/shared_decision_handoff.md
- references/source_boundaries.md
- references/source_ledger.md
- SKILL.md
Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.