# alchaincyf/darwin-skill architecture

> Architecture diagram of the GitHub repository alchaincyf/darwin-skill, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/alchaincyf/darwin-skill
- Repository: https://github.com/alchaincyf/darwin-skill

## Overview

Darwin Skill is an agent skill for iteratively improving other SKILL.md files. Its principal workflow evaluates a baseline, edits one dimension, independently validates the change, keeps improvements or reverts regressions, and pauses for human review. README documentation supplies the workflow and capabilities; the only sampled source is a peripheral screenshot script, so stage-level implementation details are attributed to SKILL.md without claiming its contents were inspected.

Main entry points: [`SKILL.md`](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md) (Darwin Skill), [`templates/result-card.html`](https://github.com/alchaincyf/darwin-skill/blob/master/templates/result-card.html) (Result Card), [`test-prompts.json`](https://github.com/alchaincyf/darwin-skill/blob/master/test-prompts.json) (Test Prompts)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_orchestration["Skill Workflow"]
  node_darwin["Darwin Skill<br/>[SKILL.md]"]
  node_target["Target Skill"]
  node_checkpoint["Human Checkpoint<br/>[SKILL.md]"]
  node_resultcard["Result Card<br/>[result-card.html]"]
end

subgraph group_evaluation["Evaluation"]
  node_baseline["Baseline Review<br/>[SKILL.md]"]
  node_rubric["Nine-Dimension Rubric<br/>[SKILL.md]"]
  node_static["Structural Scoring<br/>[SKILL.md]"]
  node_effect["Effectiveness Testing<br/>[SKILL.md]"]
end

subgraph group_validation["Validation"]
  node_testprompts["Test Prompts<br/>[test-prompts.json]"]
  node_reviewers["Independent Reviewers<br/>[SKILL.md]"]
  node_regression["Regression Review<br/>[SKILL.md]"]
end

subgraph group_iteration["Iteration"]
  node_edit["Single-Dimension Edit<br/>[SKILL.md]"]
  node_ratchet["Keep or Revert<br/>[SKILL.md]"]
end

node_user(("User"))

node_user -->|"requests optimization"| node_darwin
node_darwin -->|"optimizes"| node_target
node_darwin -->|"starts with"| node_baseline
node_baseline -->|"scores against"| node_rubric
node_baseline -->|"assesses structure"| node_static
node_baseline -->|"assesses results"| node_effect
node_darwin -->|"proposes change"| node_edit
node_edit -->|"requests validation"| node_reviewers
node_reviewers -->|"provides scores"| node_ratchet
node_ratchet -->|"keeps or reverts"| node_target
node_darwin -->|"pauses for approval"| node_checkpoint
node_darwin -->|"uses for testing"| node_testprompts
node_darwin -->|"runs regression tests"| node_regression
node_darwin -.->|"presents results"| node_resultcard

click node_darwin "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_baseline "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_rubric "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_static "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_effect "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_testprompts "https://github.com/alchaincyf/darwin-skill/blob/master/test-prompts.json"
click node_edit "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_reviewers "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_ratchet "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_checkpoint "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_regression "https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md"
click node_resultcard "https://github.com/alchaincyf/darwin-skill/blob/master/templates/result-card.html"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_darwin,node_target,node_checkpoint,node_resultcard,node_user toneBlue
class node_baseline,node_rubric,node_static,node_effect toneAmber
class node_testprompts,node_reviewers,node_regression toneMint
class node_edit,node_ratchet toneRose
```

## Components

### Skill Workflow

- [Darwin Skill](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`
- **Target Skill**
- [Human Checkpoint](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`
- [Result Card](https://github.com/alchaincyf/darwin-skill/blob/master/templates/result-card.html): `templates/result-card.html`

### Evaluation

- [Baseline Review](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`
- [Nine-Dimension Rubric](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`
- [Structural Scoring](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`
- [Effectiveness Testing](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`

### Validation

- [Test Prompts](https://github.com/alchaincyf/darwin-skill/blob/master/test-prompts.json): `test-prompts.json`
- [Independent Reviewers](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`
- [Regression Review](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`

### Iteration

- [Single-Dimension Edit](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`
- [Keep or Revert](https://github.com/alchaincyf/darwin-skill/blob/master/SKILL.md): `SKILL.md`

### Other components

- **User**

## Connections

- User → Darwin Skill: requests optimization (evidence: `README.md`)
- Darwin Skill → Target Skill: optimizes (evidence: `README.md`)
- Darwin Skill → Baseline Review: starts with (evidence: `README.md`)
- Baseline Review → Nine-Dimension Rubric: scores against (evidence: `README.md`)
- Baseline Review → Structural Scoring: assesses structure (evidence: `README.md`)
- Baseline Review → Effectiveness Testing: assesses results (evidence: `README.md`)
- Darwin Skill → Single-Dimension Edit: proposes change (evidence: `README.md`)
- Single-Dimension Edit → Independent Reviewers: requests validation (evidence: `README.md`)
- Independent Reviewers → Keep or Revert: provides scores (evidence: `README.md`)
- Keep or Revert → Target Skill: keeps or reverts (evidence: `README.md`)
- Darwin Skill → Human Checkpoint: pauses for approval (evidence: `README.md`)
- Darwin Skill → Test Prompts: uses for testing (evidence: `README.md`)
- Darwin Skill → Regression Review: runs regression tests (evidence: `README.md`)
- Darwin Skill → Result Card: presents results
