experiment SKILL.md skillA

experiment from sethgammon/citadel is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sethgammon/citadel/experiment@git:20261015.e7c2e78

Pins git:20261015.e7c2e78 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sethgammon/citadel
Path
skills/experiment/SKILL.md
Versions recorded
7
Latest version
git:20261015.28501a5, committed Oct 15, 2026
First version recorded
Mar 29, 2026
Size
11,979 bytes
Repository stars
929
License
MIT

Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures against a fixed baseline, and retains verified candidates locally. Supports convergence detection and diminishing returns.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# /experiment — Metric-Driven Optimization Loop

## Identity

Coordinate bounded metric-driven experiments in isolated checkouts, retaining
candidates locally until the declared verification and independent review pass.

## Orientation

### When to Use

- When you want to optimize a measurable metric (bundle size, error count, test coverage, FPS)
- When you have a clear hypothesis but aren't sure which of several approaches wins
- When manual A/B testing would be too slow or error-prone
- NOT when the goal is subjective ("make it feel better") — the metric must be a number

### Inputs

The user provides three things:
1. **scope**: Files to modify (glob pattern, e.g., "src/api/**/*.ts")
2. **metric**: Project command that outputs a single number (e.g., `node tools/bundle-bytes.cjs`)
3. **budget**: Iteration cap (default: 5) or time cap (e.g., "10 minutes")

Ask only for missing inputs that cannot be resolved from the request or project.
The metric MUST exit successfully and output a single finite number to stdout.

## Protocol

### Step 1: BASELINE

1. Read project instructions and inspect the checkout, index, untracked files,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sethgammon/citadel/experiment@sha256:28ecdff5a9c0ae75

The line at the top of this page pins the label git:20261015.e7c2e78, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_p7cjbdarrm6b6yba.svg)](https://markdownregistry.com/a/art_p7cjbdarrm6b6yba)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Mar 29, 2026 and Oct 15, 2026, about one every 33 days.

versioncommittedcommitsizeaudit
git:20261015.28501a5 latest2026-10-15 28501a5 11,979 BA view · diff
git:20261015.e7c2e782026-10-15 e7c2e78 12,368 BA view · diff
git:20261015.502e3e92026-10-15 502e3e9 11,789 BA view · diff
git:20260611.0f3f8e72026-06-11 0f3f8e7 6,138 BA view · diff
git:20260611.a6479532026-06-11 a647953 6,125 BA view · diff
git:20260503.631b94d2026-05-03 631b94d 6,051 BA view · diff
git:20260329.6c378a22026-03-29 6c378a2 5,835 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11979 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

sethgammon/citadel · 929 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_p7cjbdarrm6b6yba
GET https://markdownregistry.com/api/v1/resolve?ref=sethgammon/citadel/experiment
GET https://markdownregistry.com/api/v1/blob/28ecdff5a9c0ae753823310cf0e6d55727c9d14d6636bcf52d0b496e577f888a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from sethgammon/citadel

AGENTS.md AGENTS.md file
sethgammon/citadel · AGENTS.md
git:20260911.5005453 · audit A · 929 stars
CLAUDE.md CLAUDE.md file
sethgammon/citadel · CLAUDE.md
git:20260911.5005453 · audit A · 929 stars
AGENTS.md@examples/berman-agents-md-only AGENTS.md file
sethgammon/citadel · examples/berman-agents-md-only/AGENTS.md
git:20260701.7169885 · audit A · 929 stars
AGENTS.md@examples/berman-deploy-steward AGENTS.md file
sethgammon/citadel · examples/berman-deploy-steward/AGENTS.md
git:20260701.7169885 · audit A · 929 stars
template-skill SKILL.md skill
sethgammon/citadel · scripts/fixtures/ecosystem/anthropics-template-skill/SKILL.md · Replace with description of the skill and when Claude should use it.
git:20260711.59dbe65 · audit B · 929 stars
architect SKILL.md skill
sethgammon/citadel · skills/architect/SKILL.md · Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build…
git:20260611.0f3f8e7 · audit A · 929 stars
archon SKILL.md skill
sethgammon/citadel · skills/archon/SKILL.md · Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output…
git:20261021.eead012 · audit A · 929 stars
ascii-diagram SKILL.md skill
sethgammon/citadel · skills/ascii-diagram/SKILL.md · Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic…
git:20260611.0f3f8e7 · audit A · 929 stars
autopilot SKILL.md skill
sethgammon/citadel · skills/autopilot/SKILL.md · Intake-to-delivery pipeline. Processes pending items from .planning/intake/: briefs new ideas, executes approved work…
git:20261009.7a64c3f · audit A · 929 stars
cost SKILL.md skill
sethgammon/citadel · skills/cost/SKILL.md · Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model…
git:20260611.0f3f8e7 · audit A · 929 stars
create-app SKILL.md skill
sethgammon/citadel · skills/create-app/SKILL.md · End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or…
git:20260611.0f3f8e7 · audit A · 929 stars
create-skill SKILL.md skill
sethgammon/citadel · skills/create-skill/SKILL.md · Creates new skills from the user's repeating patterns. Interview-driven: discovers the task, analyzes failure modes…
git:20260922.465c020 · audit A · 929 stars

Every file in sethgammon/citadel

Other files named experiment

experiment SKILL.md skill
ai-analyst-lab/ai-analyst · .claude/skills/experiment/SKILL.md · The analysis and lifecycle owner for experiments. Full experiment lifecycle: design, power analysis, statistical…
git:20260902.b370de6 · audit A · 320 stars
experiment SKILL.md skill
simota/agent-skills · experiment/SKILL.md · Designing A/B tests: hypothesis docs, sample size, feature flags, significance analysis, CUPED, SRM detection…
git:20261014.350ad2b · audit A · 98 stars
experiment SKILL.md skill
ariaxhan/kernel-claude · skills/experiment/SKILL.md · Rules as hypotheses: falsifiable tests, confidence updates, graduate or kill. Triggers: experiment, hypothesis, prove…
git:20260910.20bff72 · audit A · 14 stars
experiment SKILL.md skill
ohm41321/luciazero · skills/experiment/SKILL.md · Measure performance or tuning changes with a baseline, controlled comparison, correctness check, and recorded verdict…
git:20260820.35b5e3e · audit A · 6 stars
experiment SKILL.md skill
lusona/ai-skills · plugins/lusona/skills/experiment/SKILL.md · Test an intervention or compare alternatives through a bounded empirical trial with declared evaluation criteria and…
git:20261030.ebca32b · audit A · 3 stars

Browse by kind, by grade A, or by owner.