malekokour/clinpharm-pmx-skills / skills/build-work-context
build-work-context
VerifiedBuilds, updates, refreshes, and exports portable work context for pharmaceutical and biotech professionals. Use this skill whenever someone wants AI to understand their pharma role, department, responsibilities, projects, sources, terminology, constraints, approval rules, or preferred deliverables; asks to be interviewed; mentions a work profile, professional constitution, project instructions, reusable context, Copilot or ChatGPT context, or wants to combine an existing context file with new project documents. Produces a professional context, project capsule, working pack, and change summary without inventing facts. Do not use for patient-specific clinical decisions or as a substitute for qualified scientific, regulatory, or medical judgment.
| File | Kind | Size |
|---|---|---|
| PASTE.md | markdown | 8.2 KB |
| README.md | markdown | 936 B |
| SKILL.md | skill md | 8.4 KB |
| assets/AI-Working-Pack.template.md | markdown | 774 B |
| assets/Context-Change-Summary.template.md | markdown | 494 B |
| assets/My-Pharma-Work-Context.template.md | markdown | 1.7 KB |
| assets/Project-Context.template.md | markdown | 808 B |
| references/context-contract.md | markdown | 3.8 KB |
| references/department-prompts.md | markdown | 3.3 KB |
| references/evidence-hierarchy.md | markdown | 2.7 KB |
| references/human-review.md | markdown | 2.4 KB |
| references/interview-and-modes.md | markdown | 3.8 KB |
| references/output-states.md | markdown | 2.5 KB |
| references/safety-and-evidence.md | markdown | 3.0 KB |
| references/source-preflight.md | markdown | 2.8 KB |
| scripts/context_validation.pyexecutable | script | 6.4 KB |
| scripts/findings.py | script | 4.7 KB |
| scripts/validate_context.pyexecutable | script | 1.7 KB |
references/context-contract.md
View on GitHub# ClinPharm PMx Skills context contract
Schema version: `1.0`
Use these headings and field meanings so a context file can be updated
reliably across AI hosts.
## Professional context
```markdown
---
clinpharm_context_schema: "1.0"
document_type: professional-context
version: "1.0"
updated_at: "YYYY-MM-DD"
status: draft | confirmed
owner_label: "<user-selected label or unknown>"
data_classification: PUBLIC_OR_SYNTHETIC | INTERNAL_APPROVED | RESTRICTED_DO_NOT_PROCESS | UNKNOWN
approved_environment: "<confirmed environment or unknown>"
review_due: "YYYY-MM-DD or unknown"
---
# My Pharma Work Context
## How to use this file
## Safety Kernel
### Data boundary
### Permitted tools and actions
### Human review and approval gates
### Stop conditions
## Professional Constitution
### Professional scope
### Responsibilities and outcomes
### Decision rights and escalation
### Recurring workflows and deliverables
### Terminology and definitions
### Source and evidence hierarchy
### Quality expectations
### Tools and constraints
### Output and communication preferences
## Active project index
## Known unknowns and conflicts
## Maintenance
### Review triggers
### Change history
```
Rules:
- Use `unknown` rather than an inferred value.
- Blank templates default to `UNKNOWN`; only a confirmed synthetic example may
default to `PUBLIC_OR_SYNTHETIC`.
- Keep project detail in a project capsule; the index contains only safe names,
status, and capsule references.
- Put mutable facts with an effective date when known.
- Include the data boundary in every exported derivative.
## Project capsule
```markdown
---
clinpharm_context_schema: "1.0"
document_type: project-capsule
project_slug: "<lowercase-safe-slug>"
version: "1.0"
updated_at: "YYYY-MM-DD"
status: proposed | active | on-hold | completed | unknown
data_classification: PUBLIC_OR_SYNTHETIC | INTERNAL_APPROVED | RESTRICTED_DO_NOT_PROCESS | UNKNOWN
---
# Project Context: <Project>
## How to use this capsule
## Purpose and current status
## Deliverables and success criteria
## Stakeholders and required reviewers
## Source manifest and authority order
## Decisions already made
## Constraints and non-goals
## Risks and contradictions
## Open questions
## Next action and review point
```
## Working pack
```markdown
---
clinpharm_context_schema: "1.0"
document_type: ai-working-pack
project_slug: "<project-slug>"
generated_from:
professional_context_version: "<version>"
project_capsule_version: "<version>"
generated_at: "YYYY-MM-DD"
data_classification: PUBLIC_OR_SYNTHETIC | INTERNAL_APPROVED | RESTRICTED_DO_NOT_PROCESS | UNKNOWN
---
# AI Working Pack: <Project>
## How to use this file
## Task for this session
## Safety Kernel
## Relevant Professional Constitution
## Project Capsule
## Required output
## Sources and authority
## Unknowns, conflicts, and assumptions
## Human review before external use
```
## Change summary
```markdown
---
clinpharm_context_schema: "1.0"
document_type: context-change-summary
previous_version: "<version>"
new_version: "<version>"
updated_at: "YYYY-MM-DD"
---
# Context Change Summary
## Why this update was requested
## Added
## Updated
## Removed
## Conflicts requiring confirmation
## Stale items
## Unchanged critical controls
## Source and user confirmations
## Next review
```
## Version behavior
- Increment the minor version for confirmed additions or corrections.
- Increment the major version when the role, function, or Safety Kernel changes
materially.
- Do not increment for a REFRESH report that makes no accepted change.
- Record the previous version and reason in the embedded change history.
## Filenames
- `My-Pharma-Work-Context.md`
- `Project-Context-<project-slug>.md`
- `AI-Working-Pack-<project-slug>.md`
- `Context-Change-Summary.md`
If DOCX versions are created, use the same stem.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |