project-philosophy

Maintain a canonical project philosophy document at .thrum/philosophy.md.

28|5|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/leonletto/thrum --skill project-philosophy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: project-philosophy
Source: https://github.com/leonletto/thrum/tree/main/opencode-plugin/assets/skills/project-philosophy
Command: npx skills add https://github.com/leonletto/thrum --skill project-philosophy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams establish and maintain a canonical project philosophy document that agents read at task start to enforce project-specific rules, anti-patterns, and governance, using a single source of truth at .thrum/philosophy.md.

Core Features & Use Cases

  • Canonical document path at .thrum/philosophy.md serves as the single authoritative location for project rules and guidelines.
  • Mode-driven workflow (First-run, Fallback migration, Re-run-unchanged, Re-run-evolved) ensures idempotent generation and safe evolution.
  • Interactive prompts collect team anti-patterns, red flags, and governance requirements; supports drift detection and diff proposals.
  • Guidance for implementation agents to read and apply project-specific rules at task-start.

Quick Start

Invoke the project-philosophy skill to generate or reconcile the canonical philosophy document at .thrum/philosophy.md.

Frequently Asked Questions about project-philosophy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a canonical project philosophy document for AI agents to read?

Create a project philosophy document by invoking the skill to initialize a canonical file at .thrum/philosophy.md, which serves as the single source of truth for project rules and anti-patterns.

What is the best way to maintain project-specific anti-patterns and governance rules over time?

Maintain anti-patterns and governance rules by running the skill in re-run-evolved mode, which detects drift over time and proposes diffs to keep the canonical philosophy document current.

How does drift detection work when evolving project documentation?

Drift detection works by comparing the current project state against the existing .thrum/philosophy.md, proposing targeted diffs to reconcile any changes in team red flags and governance requirements.

Can I safely re-run project philosophy generation without duplicating or overwriting existing rules?

Yes, you can safely re-run generation because the workflow is idempotent, featuring first-run, fallback migration, re-run-unchanged, and re-run-evolved modes to ensure safe evolution without data loss.

How do I collect team anti-patterns and red flags for a new software project?

Collect anti-patterns and red flags through interactive prompts that guide the team during initialization, capturing project-specific rules directly into the canonical philosophy document.

When do I need a fallback migration for my project rules document?

You need a fallback migration when the existing .thrum/philosophy.md is missing or corrupted, allowing the skill to recover and rebuild the canonical project philosophy from project inspection.