create-experiment SKILL.md skillA

create-experiment from harness/harness-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add harness/harness-skills/create-experiment@v1.0.1

Pins v1.0.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
harness/harness-skills
Path
skills/fme/create-experiment/SKILL.md
Versions recorded
1
Latest version
v1.0.1, committed Oct 14, 2026
Size
3,998 bytes
Repository stars
122
License
Apache-2.0

Thin compatibility entrypoint for creating a new Harness FME experiment. Invokes manage-experiments' Create experiment flow directly - same scope, parent/environment resolution, hypothesis, metrics, treatments, window, and rule - and returns the created experiment id plus verification. Use when asked to create an experiment, set up an A/B test, or design a new experiment. Do NOT use for updating, pausing, resuming, completing, archiving, or deleting an experiment (manage-experiments), or for…

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

# Create Experiment

Compatibility entrypoint kept for direct `/create-experiment` invocation. This
skill does not duplicate any workflow - it hands the entire creation flow to
[manage-experiments](../manage-experiments/SKILL.md)'s **Create experiment**
section and returns once that flow completes.

## Tools

Performs no operations of its own; it uses the operations of manage-experiments'
Create experiment flow, named in [tool-map.md](../../../references/fme/tool-map.md).

## Instructions

### Step 1: Delegate

Read [manage-experiments/SKILL.md](../manage-experiments/SKILL.md) and follow
its **Phase 1: Establish scope** and **Create experiment** section (Steps 1-8)
exactly as written, using the current request's scope (org/project), parent
flag + environment, hypothesis, metrics, treatments, window
(`startAt`/`endAt`), and `rule`. Do not re-derive or re-interpret any of that
section's logic here - this skill has no independent instructions for
resolving treatments, choosing metrics, or drafting the payload; it only
exists so `/create-experiment` remains a valid invocation.

If the tool interface you're running under can't follow a markdown link to
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add harness/harness-skills/create-experiment@sha256:46eca634ff98fc64

The line at the top of this page pins the label v1.0.1, 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_e24kaiznwc7bffwf.svg)](https://markdownregistry.com/a/art_e24kaiznwc7bffwf)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 14, 2026.

versioncommittedcommitsizeaudit
v1.0.1 latest2026-10-14 bc2236d 3,998 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 (3998 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

harness/harness-skills · 122 stars · license Apache-2.0 · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_e24kaiznwc7bffwf
GET https://markdownregistry.com/api/v1/resolve?ref=harness/harness-skills/create-experiment
GET https://markdownregistry.com/api/v1/blob/46eca634ff98fc64093724108e0ab4fda9c0f98eece30936e72033413bfdacd8

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 harness/harness-skills

harness Cursor rule
harness/harness-skills · .cursor/rules/harness.mdc
git:20261014.bc2236d · audit A · 122 stars
AGENTS.md AGENTS.md file
harness/harness-skills · AGENTS.md
git:20261014.bc2236d · audit A · 122 stars
CLAUDE.md CLAUDE.md file
harness/harness-skills · CLAUDE.md
git:20260704.b481a60 · audit B · 122 stars
manage-roles SKILL.md skill
harness/harness-skills · skills/access-control/manage-roles/SKILL.md · Manage Harness RBAC roles, role assignments, permissions, and resource groups via MCP v2 tools. List, create, update…
v1.0.0 · audit A · 122 stars
manage-users SKILL.md skill
harness/harness-skills · skills/access-control/manage-users/SKILL.md · Manage Harness users, user groups, and service accounts via MCP. List and search users, create and manage user groups…
v1.0.0 · audit A · 122 stars
create-agent-template SKILL.md skill
harness/harness-skills · skills/agents/create-agent-template/SKILL.md · Generate Harness Agent Template files for AI-powered automation agents. Produces metadata.json, pipeline.yaml (v1…
v1.0.0 · audit A · 122 stars
create-agent SKILL.md skill
harness/harness-skills · skills/agents/create-agent/SKILL.md · Create and update Harness AI agent instances - standalone templates for agentic workflows in pipelines. Use when asked…
v1.0.0 · audit A · 122 stars
dbops-changeset SKILL.md skill
harness/harness-skills · skills/database/dbops-changeset/SKILL.md · Generates Liquibase database changesets via a structured workflow: resolve schema+instance (from context or via API…
v2.1.1 · audit A · 122 stars
choose-metric SKILL.md skill
harness/harness-skills · skills/fme/choose-metric/SKILL.md · Recommend primary/guardrail metrics for an experiment or rollout, judged against a good-metric checklist. Checks…
v1.3.2 · audit A · 122 stars
cleanup-feature-flags SKILL.md skill
harness/harness-skills · skills/fme/cleanup-feature-flags/SKILL.md · Remove a launched Harness FME feature flag from application code, keeping the treatment FME serves today, and open a…
v1.2.2 · audit A · 122 stars
create-feature-flag SKILL.md skill
harness/harness-skills · skills/fme/create-feature-flag/SKILL.md · Create a new Harness FME feature flag and its per-environment definitions with a safe default, following the project's…
v1.2.2 · audit A · 122 stars
create-metric SKILL.md skill
harness/harness-skills · skills/fme/create-metric/SKILL.md · Create a Harness FME metric: helps decide what to measure, suggests candidate metrics from application code, resolves…
v1.4.2 · audit A · 122 stars

Every file in harness/harness-skills

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