archived/skills/hdr/SKILL.md
HDR (Higher Degree Research) student task conventions, reference letter workflows, and document access patterns.
npx skillsauth add nicsuzor/academicops hdrInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Taxonomy note: This skill provides domain expertise (HOW) for HDR student task conventions and reference letter workflows. See [[TAXONOMY.md]] for the skill/workflow distinction.
Manage HDR (Higher Degree Research) student-related tasks including supervision, reference letters, reviews, and document handling.
CRITICAL: This skill requires the $ACA_DATA environment variable to be set.
$ACA_DATA points to the user's data directoryHDR data location: $ACA_DATA/hdr/
MANDATORY: All HDR student tasks MUST use project=hdr.
mcp__pkb__create_task(
task_title="Review Sadia's dissertation chapter",
type="task",
project="hdr", # NOT "supervision", NOT "academic"
tags=["sadia", "dissertation", "review"],
assignee="nic" # HDR tasks typically assigned to human
)
Why: HDR tasks are stored at $ACA_DATA/hdr/tasks/ and use hdr- prefix for task IDs. Using the wrong project breaks routing and organization.
Task ID format: hdr-{hash}-{title-slug}
hdr/{student}/Student-specific files are organized by student name:
$ACA_DATA/hdr/
├── tasks/ # HDR-related tasks
│ ├── hdr-abc123-review-sadias-chapter.md
│ └── hdr-def456-write-lucinda-reference.md
├── sadia/ # Sadia Sharmin's files
│ ├── oii-reference-2026.md
│ └── rental-reference-2024.md
├── tegan/ # Tegan's files
│ └── annual-planning.md
└── lucinda/ # Lucinda's files
└── (student-specific docs)
When to create student directory:
{student}/reference-{purpose}-{year}.md)Naming convention: Use lowercase first name only (e.g., sadia/, not sadia-sharmin/).
When HDR tasks involve Google Docs (common for shared drafts and feedback):
In task body, include the link clearly:
**Link**: https://docs.google.com/document/d/1q-5VhWcNnWwtYjL5v-SWjT8rEUse6MkOHi9TMkAH-M4/edit
Accessing Google Docs content:
For review/feedback tasks: The human must access the Google Doc directly in browser. The agent cannot read Google Docs content automatically.
If content needs to be in the repo: Ask the user to:
.docx and download/convert-to-md skill to convert to markdownhdr/{student}/ directoryFor collaborative editing: Keep work in Google Doc until finalized, then archive to repo.
Current limitation: No automated Google Docs MCP integration. Future enhancement may add mcp__gdocs__read_document capability.
See [[workflows/reference-letter]] for the complete workflow.
Quick reference:
project=hdr, tags=["reference", "{student}"]$ACA_DATA/hdr/{student}/{purpose}-reference-{year}.md| Task Type | Description | Typical Assignee | | ------------------- | -------------------------------- | ---------------- | | Reference letter | Write recommendation for student | nic | | Dissertation review | Review chapter/draft | nic | | Supervision inquiry | Respond to prospective student | nic | | Final seminar | Schedule and attend | nic | | Annual planning | Review annual plan with student | nic |
Note: Most HDR tasks are assignee=nic because they require human judgment and relationship management.
$ACA_DATA/projects/hdr/current-students.md$ACA_DATA/projects/hdr/hdr.md[[workflows/reference-letter]]Wrong project used:
project=supervision or project=academic: Update to project=hdrStudent directory missing:
$ACA_DATA/hdr/{student}/ on first useGoogle Doc inaccessible:
tools
Streamlit implementation of the analyst presentation layer. Use when building or updating a Streamlit dashboard that displays pre-computed research data. This is the Streamlit-specific HOW for the tech-agnostic principles in the aops-tools analyst skill — display only, never transform.
tools
Python plotting and statistical-modelling libraries (matplotlib, seaborn, statsmodels) for the analyst presentation and statistical-methodology layers. Use when producing publication-quality figures or fitting statistical models in Python. Library-specific HOW for the tech-agnostic principles in the aops-tools analyst skill.
tools
dbt (data build tool) implementation of the analyst transformation layer. Use when a project has a dbt/ directory or you need to build, test, or document SQL transformations as version-controlled, reproducible dbt models. This is the dbt-specific HOW for the tech-agnostic principles in the aops-tools analyst skill.
development
Core academicOps skill — institutional memory, strategic coordination, workflow routing, and framework governance. Merges butler (chief-of-staff) with framework development conventions.