Theorist — Productivity skill for Claude Code
You maintain a per-repo narrative document at THEORY.MD that captures the operating theory of the work being done.
How to install Theorist
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open blader/theorist and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Theorist does
You maintain a per-repo narrative document at `THEORY.MD` that captures the operating theory of the work being done. This is not a plan, not a log, not a task list. It is a living essay that describes
Alternatives in Productivity
- 🤝 Contributing To Agent Skills — First of all, thank you for taking the time to contribute 1.7k ★
- Jobs — Create, list, edit, or delete cron jobs 1.3k ★
- MCP Tree-sitter Server Roadmap — This document outlines the planned improvements and future features for the MCP Tree-sitter Server project 288 ★
README
name: theorist description: | Maintain a per-repo THEORY.MD as a continuously updated narrative of the operating theory behind the current work. Activates EVERY session and stays active throughout the session. Requires frequent in-session rewrites as new learnings land (major result, verification outcome, or strategy pivot). Not a log, not a plan, not a todo list — a cohesive document describing the higher-level thinking, systematic strategy, and motivation behind the work as it evolves. Updated end-to-end (rewritten, not appended) as understanding deepens. author: blader version: 1.3.0 date: 2026-02-28
Theorist
You maintain a per-repo narrative document at `THEORY.MD` that captures the operating theory of the work being done. This is not a plan, not a log, not a task list. It is a living essay that describes *why* the work exists, *what* the systematic strategy is, and *how* the current approach connects to the larger picture.
**This skill is always active during every session. No trigger required.** **Once active in a session, it stays active for the full session.**
What THEORY.MD Is
A cohesive narrative document — typically 1-3 pages — that a thoughtful collaborator could read to understand:
- The problem thesis: What problem is being solved and why it matters. Not "fix bug X" but "the export pipeline assumes Y, which breaks under Z."
- The operating theory: The current mental model of how the system works and where the leverage points are. What has been tried, what was learned, and what that implies about the shape of the solution.
- The systematic strategy: Not task-by-task steps, but the higher-order approach. Why this sequence of work? What principle connects the changes?
- Key discoveries and pivots: Moments where understanding shifted. What was the old theory, what broke it, and what replaced it.
- Open questions and uncertainties: What is still unknown. Where the current theory might be wrong. What would change the approach.
What THEORY.MD Is Not
- Not a changelog or log: Never append timestamped entries. The document is rewritten holistically as understanding evolves.
- Not a plan or todo list: No task items, checkboxes, or step-by-step instructions. A plan says "do X then Y." A theory says "X matters because of Y, and the right lever is Z."
- Not a postmortem: Written in the present tense of ongoing work, not retrospectively about completed work.
- Not a status report: No "today I did X." Instead: "The current approach is X because the evidence shows Y."
Session Behavior
Starting a Session
At session start, if `THEORY.MD` exists, read it. Use it to orient yourself to the work. Do not announce that you read it.
If meaningful work begins and no THEORY.MD exists yet, create one once you have enough context to write a meaningful narrative (not before — don't create an empty skeleton).
During Work
Update THEORY.MD when underst
Related Skills
Report Worklog
Summarize the work done so far this session and log it to your worklog (time reporting)
Plan Execute Verify Repair
Run the autonomous-engineering operating loop on a task (plan→implement→verify→repair→report)
Generate Tasks
Generate a detailed, step-by-step task list from a Requirements Document (PRD or ERD)
Task Log
Keep a log of the work you complete in this project, in .claude/tasks.json
Ai4cela
CELA — how work gets done at Microsoft CELA Engineering (AI4CELA), the entry point that routes a task to the r
Agent Afk
The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own
Related Agents
Work Recorder
Use to maintain the session work record under docs/workrecords/. Appends a first-person narrative of what was
Theorist Critic
Theory critic. Reviews formal theoretical content -- assumptions, definitions, lemmas, theorems, proofs -- for
Documentation Curator
Maintain living documentation, generate API docs, and ensure doc-code synchronization.