experiment-design SKILL.md skillA

experiment-design from dragonked2/alphacode is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dragonked2/alphacode/experiment-design@git:20261104.824f63f

Pins git:20261104.824f63f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dragonked2/alphacode
Path
src/alphacode_base/bundled_skills/bugbounty/experiment-design/SKILL.md
Versions recorded
2
Latest version
git:20261104.824f63f, committed Nov 4, 2026
First version recorded
Nov 3, 2026
Size
6,417 bytes
Repository stars
626
License
MIT

Turn observed clues into discriminating experiments, novel boundary comparisons and compatible impact chains within authorized scope.

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

# Design the next decisive experiment

Use with investigation-control and real-world-validation. Read supplied program
rules first. These are reasoning methods, not evidence that any target is
vulnerable. Never promise a finding, acceptance, a particular severity or better
performance than expert humans.

## Keep a small working set

For the current feature, keep at most three leading explanations, including the
strongest ordinary explanation. Store other clues in the register rather than
discarding them or keeping the entire inventory in every model prompt.

For each live hypothesis write one compact experiment card:

```text
Clue/evidence locator; protected invariant; actor and owned fixtures:
Observed facts / inference / missing prerequisite:
Leading explanation / competing ordinary explanation:
Single changed variable; baseline; negative control:
Predicted observation under each explanation:
Authoritative readback/oracle; asynchronous settling rule:
Request/time budget; cleanup; stop condition:
Result; conclusion limited to tested conditions; next discriminating action:
```

Choose the experiment whose possible outcomes most change the next decision.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ccmg4kem5jwbydpt/08115e372bfdc00ee926199cef1c50546b50a772a3c23be453078461208db0f9.json

Then /plugin install experiment-design@markdownregistry-ccmg4kem5jwbydpt in Claude Code. It installs git:20261104.824f63f, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add dragonked2/alphacode/experiment-design@sha256:08115e372bfdc00e

The line at the top of this page pins the label git:20261104.824f63f, 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_ccmg4kem5jwbydpt.svg)](https://markdownregistry.com/a/art_ccmg4kem5jwbydpt)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in dragonked2/alphacode/experiment-design since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of experiment-design from somewhere else? Ask it: where did my experiment-design come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, between Nov 3, 2026 and Nov 4, 2026, more than one a day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261104.824f63f latest2026-11-04 824f63f 6,417 BA view · diff
git:20261103.b72aef92026-11-03 b72aef9 5,619 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (6417 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

dragonked2/alphacode · 626 stars · license MIT · pushed 2026-11-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ccmg4kem5jwbydpt
GET https://markdownregistry.com/api/v1/resolve?ref=dragonked2/alphacode/experiment-design
GET https://markdownregistry.com/api/v1/blob/08115e372bfdc00ee926199cef1c50546b50a772a3c23be453078461208db0f9

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 dragonked2/alphacode

AGENTS.md AGENTS.md file
dragonked2/alphacode · AGENTS.md
git:20261111.5b671c4 · audit A · 626 stars
api-builder SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/api-builder/SKILL.md · Expert REST API design and implementation — endpoint design, authentication, error handling, rate limiting, versioning…
git:20260923.ffaa29c · audit A · 626 stars
api-design SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/api-design/SKILL.md · RESTful and GraphQL API design: OpenAPI specs, pagination, rate limiting, error schemas, versioning, and backwards…
git:20260923.ffaa29c · audit A · 626 stars
api-security SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/api-security/SKILL.md · API security testing: authentication bypass, authorization flaws, rate limiting, input validation, GraphQL…
git:20260923.ffaa29c · audit A · 626 stars
architecture-review SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/architecture-review/SKILL.md · Review system architecture: module boundaries, dependency direction, coupling analysis, and scalability assessment.
git:20260923.ffaa29c · audit A · 626 stars
backend-dev SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/backend-dev/SKILL.md · Comprehensive backend development methodology covering API design, authentication, database design, caching, testing…
git:20260923.ffaa29c · audit A · 626 stars
backend-dev/auth SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/backend-dev/auth/SKILL.md · Authentication and authorization — JWT access/refresh token rotation, OAuth2 PKCE/client credentials, session…
git:20260923.82a4143 · audit A · 626 stars
backend-dev/caching SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/backend-dev/caching/SKILL.md · Caching strategies — HTTP caching, CDN, application-level caching (Redis, Memcached), cache invalidation patterns…
git:20260923.82a4143 · audit A · 626 stars
backend-dev/database SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/backend-dev/database/SKILL.md · Database patterns — schema design, indexing strategies, query optimization, connection pooling, migration management…
git:20260923.82a4143 · audit A · 626 stars
backend-dev/nodejs SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/backend-dev/nodejs/SKILL.md · Node.js/Express/Fastify backend development — project structure, middleware patterns, route design, validation…
git:20260923.82a4143 · audit A · 626 stars
backend-dev/python SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/backend-dev/python/SKILL.md · Python/FastAPI/Django backend development — async patterns, Pydantic models, dependency injection, middleware…
git:20260923.82a4143 · audit A · 626 stars
backend-dev/rust SKILL.md skill
dragonked2/alphacode · src/alphacode_base/bundled_skills/backend-dev/rust/SKILL.md · Rust/Axum/Actix-web backend development — handler patterns, extractors, middleware, error handling, state management…
git:20260923.82a4143 · audit A · 626 stars

Every file in dragonked2/alphacode

Other files named experiment-design

experiment-design SKILL.md skill
rampstackco/claude-skills · skills/experiment-design/SKILL.md · A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question…
git:20260810.e5bc675 · audit A · 1,100 stars
experiment-design SKILL.md skill
fcakyon/labrat · plugin/skills/experiment-design/SKILL.md · Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental…
git:20260312.ea277c2 · audit A · 464 stars
experiment-design SKILL.md skill
suifei/dsh-ai-team · talents/experiment-designer/skills/experiment-design/SKILL.md · 实验设计:
git:20261117.01181a3 · audit A · 34 stars
experiment-design SKILL.md skill
qa-aman/claude-skills · skills/by-role/pm/experiment-design/SKILL.md · Design product experiments to test hypotheses. Use when the user says "run an experiment", "A/B test this"…
git:20261019.be4abcc · audit A · 27 stars
experiment-design SKILL.md skill
uchicago-dsi/ai-sci-skills · skills/experiment-design/SKILL.md · Design the smallest useful experiment matrix that separates important hypotheses and changes a decision. Use when the…
git:20261013.2f47de7 · audit A · 20 stars
experiment-design SKILL.md skill
kendrick-stein/mcislab_deepread · skills/3-experiment/experiment-design/SKILL.md · 当 Supervisor 说"设计个实验""怎么验证这个 idea", 或 autoresearch 判断某个 developing/validated idea 需要实验验证时, 为 idea 设计完整实验方案
git:20260428.bf023ec · audit A · 12 stars
experiment-design SKILL.md skill
vandanaajaydubey111/great-pm · skills/experiment-design/SKILL.md · Playbook for trustworthy experiments — hypothesis framing, test types, sample size and power, statistical vs practical…
git:20260721.86de099 · audit A · 3 stars
experiment-design SKILL.md skill
vandanaajaydubey111/great-pm · plugins/great-pm/skills/experiment-design/SKILL.md · Playbook for trustworthy experiments — hypothesis framing, test types, sample size and power, statistical vs practical…
git:20260920.2cbc56d · audit A · 3 stars

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