# Evolve

Research-driven multi-cycle improvement director.

- Repository: https://github.com/SethGammon/Citadel (927 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-30
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add SethGammon/Citadel --skill evolve -g -a claude-code -y`
Codex: `npx skills add SethGammon/Citadel --skill evolve -g -a codex -y`
Cursor: `npx skills add SethGammon/Citadel --skill evolve -g -a cursor -y`
Gemini CLI: `npx skills add SethGammon/Citadel --skill evolve -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add SethGammon/Citadel`

## Description

Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and pattern library across sessions.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# /evolve, Improvement Director

## Orientation

**Use when:** You want sustained autonomous quality advancement, the director
forms hypotheses, scouts before attacking, and builds a belief model that
compounds across cycles. Runs until a natural ceiling, budget exhaustion, or you
say stop.

**Don't use when:** You want a single scored loop (`/improve`), a known axis
attacked directly (`/improve --axis`), or a one-time audit (`/improve --score-only`).

**Key difference from `/improve`:** `/improve` follows the rubric mechanically.
`/evolve` asks *why* scores are where they are, validates those theories before
spending fleet budget, and extracts cross-skill patterns that propagate to skills
never directly attacked.

## Invocation

```
/evolve {target}                  # run until ceiling, velocity drop, or budget
/evolve {target} --n={N}          # exactly N director cycles then stop
/evolve {target} --budget=${X}    # run until cumulative spend reaches $X
/evolve {target} --continue       # resume from saved director state
/evolve {target} --status         # show belief model, velocity, spend, no attack
/evolve {target} --axis={name}    # focus director on one axis (scout + attack only)
```

`target` maps to `.planning/rubrics/{target}.md`.
If no rubric exists, run `/improve {target}` Phase 0 first, `/evolve` requires
an approved rubric and will not auto-generate one.

## Campaign Artifacts

All findings are externalized incrementally, written after every phase, not
only at cycle end. A crashed or compacted session resumes with full context.

The rest: https://github.com/SethGammon/Citadel/blob/HEAD/skills/evolve/SKILL.md