auto-research SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.

auto-research from transitive-bullshit/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add transitive-bullshit/skills/auto-research@git:20261011.ef64499

Pins git:20261011.ef64499 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
transitive-bullshit/skills
Path
provenance/upstream/auto-research/skill/SKILL.md
Versions recorded
1
Latest version
git:20261011.ef64499, committed Oct 11, 2026
Size
10,825 bytes
Repository stars
4
License
MIT

Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.

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

# Auto Research

Optimize **learning per unit of time**. Start with one fast, revealing task,
plan competing hypotheses, test them separately, combine verified winners, then
expand coverage. The durable result is a **parameter-effect map** plus the best
verified artifact. An experiment is a checkpoint, not a stopping point.

## Workflow

1. **Recover the research state.** Read the objective, user feedback, project
   instructions, and existing research records. Reconcile the handoff with actual
   artifacts and running jobs; collect a pending attempt before launching another.
   Identify the best verified artifact (the incumbent), active task, regression
   set, hypothesis queue, and remaining budget. Reuse existing record locations.

2. **Clarify success before experimenting.** Recover any already agreed criteria;
   do not ask the user to repeat them. If the evaluator, metric, comparison
   baseline, or required improvement is unclear, ask focused questions and wait
   for answers before editing candidates or launching evaluations. Inspect
   existing artifacts and propose concrete options to make answering easier;
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add transitive-bullshit/skills/auto-research@sha256:73da6a4e28275666

The line at the top of this page pins the label git:20261011.ef64499, 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_phmzlwy2tgx5ebv5.svg)](https://markdownregistry.com/a/art_phmzlwy2tgx5ebv5)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 11, 2026.

versioncommittedcommitsizeaudit
git:20261011.ef64499 latest2026-10-11 ef64499 10,825 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 (10825 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

transitive-bullshit/skills · 4 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_phmzlwy2tgx5ebv5
GET https://markdownregistry.com/api/v1/resolve?ref=transitive-bullshit/skills/auto-research
GET https://markdownregistry.com/api/v1/blob/73da6a4e28275666816dbdd37f52c7bd3324b9b90a298c061b3335604cef3dbd

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 transitive-bullshit/skills

AGENTS.md AGENTS.md file
transitive-bullshit/skills · AGENTS.md
git:20261012.cfd478c · audit A · 4 stars
resolving-merge-conflicts SKILL.md skill
transitive-bullshit/skills · provenance/history/2026-10-11-removed/resolving-merge-conflicts/SKILL.md · Use when you need to resolve an in-progress git merge/rebase conflict.
git:20261011.ef64499 · audit A · 4 stars
testing-strategy SKILL.md skill
transitive-bullshit/skills · provenance/history/testing-strategy/recipe-1/SKILL.md · Choose proportionate verification and maintain useful tests when implementing changes, fixing bugs, or reviewing test…
git:20261011.ef64499 · audit A · 4 stars
better-accessibility SKILL.md skill
transitive-bullshit/skills · provenance/upstream/better-accessibility/SKILL.md · Reviews and fixes keyboard and focus behavior, ARIA, accessible names, forms, screen-reader announcements, motion and…
git:20261011.ef64499 · audit A · 4 stars
better-colors SKILL.md skill
transitive-bullshit/skills · provenance/upstream/better-colors/SKILL.md · Helps you build and check a color system for your project. It generates palettes, names semantic tokens, converts…
git:20261011.ef64499 · audit A · 4 stars
better-layout SKILL.md skill
transitive-bullshit/skills · provenance/upstream/better-layout/SKILL.md · Helps with grouping, alignment, reading order, responsive structure and room for translated text, so a layout holds up…
git:20261011.ef64499 · audit A · 4 stars
better-typography SKILL.md skill
transitive-bullshit/skills · provenance/upstream/better-typography/SKILL.md · Sets and reviews how text renders in your product, from the type scale and spacing to font features, wrapping…
git:20261011.ef64499 · audit A · 4 stars
better-ui SKILL.md skill
transitive-bullshit/skills · provenance/upstream/better-ui/SKILL.md · Polishes the surfaces, icons and motion in your project with exact values for border radius, optical alignment…
git:20261011.ef64499 · audit A · 4 stars
better-writing SKILL.md skill
transitive-bullshit/skills · provenance/upstream/better-writing/SKILL.md · Writes and reviews your interface copy, from labels and errors to empty states and confirmations, so it matches your…
git:20261011.ef64499 · audit A · 4 stars
claude SKILL.md skill
transitive-bullshit/skills · provenance/upstream/claude/skill/SKILL.md · Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent…
git:20261018.0333997 · audit A · 4 stars
codebase-design SKILL.md skill
transitive-bullshit/skills · provenance/upstream/codebase-design/skill/SKILL.md · Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
git:20261011.ef64499 · audit A · 4 stars
codex SKILL.md skill
transitive-bullshit/skills · provenance/upstream/codex/skill/SKILL.md · Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second…
git:20261018.0333997 · audit A · 4 stars

Every file in transitive-bullshit/skills

Other files named auto-research

auto-research SKILL.md skill
sickn33/agentic-awesome-skills · plugins/agentic-awesome-skills-claude/skills/auto-research/SKILL.md · Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options…
git:20260714.e3d12ce · audit A · 48,329 stars
auto-research SKILL.md skill
dzhng/skills · skills/engineering/auto-research/SKILL.md · Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts…
git:20260925.120cae1 · audit A · 1,377 stars
auto-research SKILL.md skill
huytieu/cog-second-brain · skills/auto-research/SKILL.md · Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and…
git:20260807.b852369 · audit A · 1,305 stars
auto-research SKILL.md skill
huytieu/cog-second-brain · .agents/skills/auto-research/SKILL.md · Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and…
git:20260730.acf9b42 · audit A · 1,305 stars
auto-research SKILL.md skill
huytieu/cog-second-brain · .claude/skills/auto-research/SKILL.md · Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and…
git:20260312.39ccbee · audit A · 1,305 stars
auto-research SKILL.md skill
transitive-bullshit/skills · skills/auto-research/SKILL.md · Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts…
git:20261002.164a2bc · audit A · 4 stars

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