aops-cowork

Show framework capabilities - commands, skills, agents, and how to use them

Nudge an agent back into action

Strategic review agent — multi-level critique applying 10 cognitive moves

Comprehensive work handover and session closure - commit changes, push, file a Pull Request, update tasks, file follow-ups, output Framework Reflection, halt

Create "ready for action" tasks from emails - with summaries, downloaded documents, and clear response requirements

Post-hoc axiom compliance check — detects violations, ultra vires actions, workflow discipline issues

File high-quality, anonymised bug reports to GitHub Issues for framework failures and knowledge capture.

Show narrative path reconstruction (what happened across sessions)

Pull a task from queue, claim it (mark active), and mark complete when done

Quick-queue a task — delegates to planner capture mode

Critical transcript review - reads recent sessions with a framework-dev lens, identifies problems, and files issues via /learn.

James — local PR review orchestrator. Manages the complete review and revision cycle for any PR across any repo.

Strategic review agent applying 10 cognitive moves of genius reviewers — multi-level abstraction, meta-reasoning, negative space, fatal vs fixable, causal chains, knowledge grounding

Engineering standards enforcer — applies development principles to planning, reviewing, and executing code

Framework operations enforcer — applies framework principles when working on or within academicOps

The Orchestrator. Holds contradictions in tension, sees what agents miss, synthesises when others simplify. Commissions Ruth (axioms), Pauli (strategic depth), and Marsha (runtime verification), evaluates their work, iterates, and produces a unified recommendation.

Independent QA reviewer. Default assumption is IT'S BROKEN. Skeptical, thorough, focused on the user's original intent. Produces PASS/FAIL/REVISE verdicts.

Strategic reviewer — the Logician. Questions the question. Sees the class of problems. Thinks in systems. Carries the 10 cognitive moves of expert review as instinctive knowledge.

The Judge. Enforces universal axioms and workflow discipline. Detects compliance failures, ultra vires actions, premature termination, scope explosion, and plan-less execution. Output is parsed programmatically.

Support academic research data analysis using dbt and Streamlit. Use this skill when working with computational research projects (identified by dbt/ directory, Streamlit apps, or empirical data pipelines). The skill enforces academicOps best practices for reproducible, transparent, self-documenting research with collaborative single-step workflow.

Batch convert documents (DOCX, PDF, XLSX, TXT, PPTX, MSG, DOC) to markdown, preserving tracked changes and comments.

Daily note lifecycle - briefing, task recommendations, progress sync, and work summary. SSoT for daily note structure.

Creating visually compelling, hand-drawn diagrams with organic mind-map layouts and accessibility-focused design.

General extraction/ingestion skill that routes to specific workflows based on input type. Extracts structured information from documents, emails, reviews, feedback, and other sources.

Creating clear, readable, and attractive Mermaid flowcharts with best practices for accessibility, layout, and maintainability.

Convert markdown documents to professionally formatted PDFs with academic-style typography, Roboto fonts, proper page layouts, and styling suitable for research documents, reviews, reports, and academic writing.

Strategic planning agent — graph structure ownership, task decomposition, knowledge-building, and PKM maintenance. Works on WHAT exists and HOW it relates.

Scaffold research project repositories with smart defaults — repo creation, directory structure, CI/CD, documentation, and PKB integration in one pass.

QA verification, qualitative assessment, criteria design, and test planning

Write knowledge to markdown AND sync to PKB. MUST invoke - do not write markdown directly.

Academic research methodology guardian. Ensures agents working on empirical research maintain methodological integrity: research questions drive all design decisions, methods are appropriate and justified, data collection quality is verified before proceeding, and convenience shortcuts that compromise validity are caught and refused.

Periodic consolidation agent — session backfill, transcript mining, knowledge consolidation, quality review, staleness sweep, brain sync. Runs on GitHub Actions cron or manually via /sleep.

Multi-agent strategic review of documents, plans, and proposals. Commissions review agents and iterates until the review meets quality standards.

Epic-level task supervisor — owns an epic from decomposition through integration. Survives interruption. All state lives in the task file.