Pharmax Skills is a portable Agent Skill and chat-starter collection that interviews pharmaceutical professionals to build reusable, human-governed work-context files so AI tools begin from explicit role, sources, constraints, and review boundaries rather than guessing.

Stars

3

7-day growth

No data

Forks

0

Open issues

6

License

MIT

Last updated

2026-07-30

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It addresses the missing context layer before task-specific pharma AI skills, turning professional working knowledge into a transparent working pack with safety and human-review boundaries, and includes a reproducible benchmark and synthetic demonstration.

Who it is for

  • Pharmaceutical and biotech professionals in clinical pharmacology, pharmacometrics, biostatistics, clinical development, regulatory, medical affairs, and related functions
  • AI/ML engineers and platform teams building portable agent skills for life sciences
  • Clinical operations and data science teams wanting reusable AI work contexts
  • Compliance and quality reviewers assessing human-governed AI use in pharma

Use cases

  • Create an initial professional work context by attaching the Word or Markdown starter and answering a short interview
  • Refresh or reconcile an existing context and project capsule using permitted project sources
  • Export a combined AI working pack before applying task-specific pharma skills
  • Evaluate AI context quality using the included benchmark protocol and scoring rubric

Strengths

  • Portable: works as an Agent Skill or as a Word/Markdown starter for ordinary ChatGPT, Claude, or Copilot
  • Human-governed: emphasizes data boundaries, safety kernel, and human-review rules
  • Transparent: produces change summaries and keeps missing details as UNKNOWN
  • Reproducible evaluation: includes benchmark protocol, scoring rubric, and a dated Codex result

Considerations

  • Not clinical decision support, medical advice, a validated GxP system, or a replacement for qualified scientific and regulatory judgment
  • Compatibility varies by host; Copilot's authenticated web-chat test rejected DOCX and required the Markdown starter
  • Benchmark evidence is narrow: one dated Codex runtime with the backend model identifier unavailable, not a cross-model performance claim

README quick start

Pharmax Skills

Portable Agent Skills that teach AI how pharmaceutical professionals work.

Pharmax Skills interviews a pharmaceutical professional and turns their answers into a reusable work-context file. Attach that file before future approved work so a general-purpose AI begins with the professional's role, responsibilities, evidence rules, constraints, and human-review boundaries instead of guessing.

The first flagship skill is pharma-context-builder. It creates and refreshes:

  • a reusable professional work context;
  • a project-specific context capsule;
  • a combined AI working pack; and
  • a transparent change summary.

It works as an open Agent Skill for compatible tools and as a single attachable Word or Markdown starter for ordinary ChatGPT, Claude, or Copilot conversations.

[!IMPORTANT] Use only information permitted in your current AI environment. Never upload patient-level data, credentials, sponsor-confidential material, regulatory submission drafts, or employer-proprietary content to an unapproved service.

Start in 60 seconds

Option 1: ordinary chat

  1. Download Pharmax-Skills-Start.docx.
  2. Attach it to a new AI conversation.
  3. Say: "Start my pharma work context. Interview me."
  4. Answer only what you are comfortable sharing.
  5. Save the generated My-Pharma-Work-Context file and attach it before future work.

The Markdown version is Pharmax-Skills-Start.md. GitHub Copilot's authenticated web-chat test rejected DOCX but accepted the Markdown starter; see docs/COMPATIBILITY.md.

Option 2: project or workspace

Attach your existing work-context file plus permitted project sources and say:

Update my context, create a project capsule, and export one AI working pack. Show conflicts and assumptions before finalizing.

Option 3: Agent Skill

Install or copy the pharma-context-builder directory into a skills location supported by your AI host, then ask:

Use pharma-context-builder to create or update my pharma work context.

Host installation paths differ. Review [`

Description

Portable Agent Skills that teach AI how pharmaceutical professionals work.

Related repositories

Similar projects matched by category, topics, and programming language.

yetone
Featured
yetone GitHub avatar

kill-ai-slop

Kill AI Slop is a multilingual field guide and agent skill that catalogues 33 common AI-generated design tells with interactive before-after demos, and provides a tool to scan and fix web projects.

AI & Machine LearningAI Agents
805
gnipbao
Featured
gnipbao GitHub avatar

story-to-handdrawn-video

A Remotion-based tool that converts Chinese story text or ordered hand-drawn images into vertical hand-drawn diary-comic animation with handwritten captions, left-to-right reveals, optional page-curl transitions, and silent H.264 output for post-production dubbing.

AI & Machine LearningAI Agents
683
lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390