round SKILL.md skillA

round from emaballarin/ccplugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add emaballarin/ccplugins/round@git:20261003.6ee5419

Pins git:20261003.6ee5419 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
emaballarin/ccplugins
Path
plugins/tuneml/skills/round/SKILL.md
Versions recorded
3
Latest version
git:20261003.6ee5419, committed Oct 3, 2026
First version recorded
Jul 30, 2026
Size
5,990 bytes
Repository stars
4
License
MIT

Design the next round of experiments — scope one goal, classify every hyperparameter as scientific, nuisance or fixed, build the studies, choose search spaces and a sampler, and allocate the trial budget. Use for `/tml:round`, "what experiment should I run next", "how do I test whether X helps", "design a sweep for this", "is this comparison fair", "set up a hyperparameter search", or after `/tml:plan`. Emits a self-contained study bundle under ./.tml/rounds/NNN/ — config matrix, launch stub…

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

# /tml:round — design the next experiment

Turn a question into a study whose answer will actually mean something. The whole
value is in two things: **one goal**, and an honest **scientific / nuisance /
fixed** split. Everything else is bookkeeping.

## First action, always

```bash
ls -la ./.tml/rounds/ 2>/dev/null | tail -5; cat ./.tml/frontier.md 2>/dev/null | head -40
```

Number this round after the highest existing one. If earlier rounds exist, read
the most recent spec and its verdict — a round that repeats a settled question is
wasted budget, and a round that ignores the previous round's caveats inherits
them silently.

## Hard rules

1. **One goal per round.** If the goal needs an "and", it is two rounds. Two
   simultaneous questions cannot be disentangled afterwards.
2. **Write the role assignment down.** A round whose scientific / nuisance / fixed
   split was never recorded cannot be checked for fairness later — and it will
   be, by `/tml:analyze`, possibly in a different session.
3. **Every fixed hyperparameter is a caveat on the conclusion.** Record it as
   one, in those words.
4. **Never put `max_train_steps` in the search space.** Fixed per study.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add emaballarin/ccplugins/round@sha256:f43819498a60f314

The line at the top of this page pins the label git:20261003.6ee5419, 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_pn4kcnnr7emejqas.svg)](https://markdownregistry.com/a/art_pn4kcnnr7emejqas)

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

Versions

The registry has recorded 3 versions of this file, between Jul 30, 2026 and Oct 3, 2026, about one every 32 days.

versioncommittedcommitsizeaudit
git:20261003.6ee5419 latest2026-10-03 6ee5419 5,990 BA view · diff
git:20260730.ff37a732026-07-30 ff37a73 5,792 BA view · diff
git:20260730.b9ce9012026-07-30 b9ce901 5,769 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 (5990 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

emaballarin/ccplugins · 4 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pn4kcnnr7emejqas
GET https://markdownregistry.com/api/v1/resolve?ref=emaballarin/ccplugins/round
GET https://markdownregistry.com/api/v1/blob/f43819498a60f3143e3bc0ed0f8ea77d738b62e4f02aa3406ae59e39aaf7571d

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 emaballarin/ccplugins

AGENTS.md AGENTS.md file
emaballarin/ccplugins · AGENTS.md
git:20260424.d7fe13b · audit A · 4 stars
CLAUDE.md CLAUDE.md file
emaballarin/ccplugins · CLAUDE.md
git:20260424.d7fe13b · audit B · 4 stars
report SKILL.md skill
emaballarin/ccplugins · plugins/autoresearch/skills/report/SKILL.md · Write the final summary of an autoresearch run to `./.ar/final_report.md` — trajectory, best commit and its diff, what…
git:20261003.36f24d0 · audit A · 4 stars
resume SKILL.md skill
emaballarin/ccplugins · plugins/autoresearch/skills/resume/SKILL.md · Run the autoresearch experiment loop — propose one change, measure it, keep it only if it beats the noise floor…
git:20261003.36f24d0 · audit A · 4 stars
start SKILL.md skill
emaballarin/ccplugins · plugins/autoresearch/skills/start/SKILL.md · Open a new autoresearch experiment loop — dedicated `ar/…` git branch, `./.ar/` state, and a measured baseline noise…
git:20261003.36f24d0 · audit A · 4 stars
status SKILL.md skill
emaballarin/ccplugins · plugins/autoresearch/skills/status/SKILL.md · Print the current autoresearch run's state — goal, baseline, noise floor, best-so-far, run tallies, budget, branch, and…
git:20261003.36f24d0 · audit A · 4 stars
stop SKILL.md skill
emaballarin/ccplugins · plugins/autoresearch/skills/stop/SKILL.md · End the current autoresearch run — append a `status:stopped` sentinel to `./.ar/ar.jsonl`, which is also what halts the…
git:20261003.36f24d0 · audit A · 4 stars
bib-audit SKILL.md skill
emaballarin/ccplugins · plugins/ccscience/skills/bib-audit/SKILL.md · Audit an existing BibTeX bibliography end to end — verify every entry against Crossref, arXiv (via DataCite), DBLP…
git:20261003.faedaf3 · audit A · 4 stars
figure-composer SKILL.md skill
emaballarin/ccplugins · plugins/ccscience/skills/figure-composer/SKILL.md · Compose one publication-grade multi-panel figure. Entry from a one-line claim + data refs, OR from an existing figure…
git:20261003.faedaf3 · audit A · 4 stars
figure-style SKILL.md skill
emaballarin/ccplugins · plugins/ccscience/skills/figure-style/SKILL.md · Publication-grade figure correctness and legibility rules for final-deliverable figures — not every plot. Quick look or…
git:20261003.faedaf3 · audit A · 4 stars
literature-review SKILL.md skill
emaballarin/ccplugins · plugins/ccscience/skills/literature-review/SKILL.md · Find, verify, and synthesize STEM literature across every field — from "what's the seminal paper for X" through full…
git:20261003.faedaf3 · audit A · 4 stars
paper-narrative SKILL.md skill
emaballarin/ccplugins · plugins/ccscience/skills/paper-narrative/SKILL.md · Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck —…
git:20261003.faedaf3 · audit A · 4 stars

Every file in emaballarin/ccplugins

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