researchforge-validate SKILL.md skillA

researchforge-validate from forger-labs-hq/researchforge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add forger-labs-hq/researchforge/researchforge-validate@git:20260713.896358d

Pins git:20260713.896358d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
forger-labs-hq/researchforge
Path
src/researchforge/claude/skills/researchforge-validate/SKILL.md
Versions recorded
1
Latest version
git:20260713.896358d, committed Jul 13, 2026
Size
1,785 bytes
Repository stars
9
License
Apache-2.0

Run repeated validation benchmarks on a run's finalists so a result can honestly be called validated. Use after a run has a promising winner, or when the user asks to confirm/validate a result.

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

# Validate finalists

"Validated" is a structural claim in ResearchForge: it requires the full
benchmark **plus** the contract's configured number of repeated validation
runs. A one-off result can never be called validated — the engine enforces
this, and so should your language.

Validation repeats the full benchmark, so it costs real time. Tell the user
how many repeats the contract configures, get their go-ahead in chat, then:

```bash
researchforge validate <run-id> --json
```

(The command asks for a typed confirmation; only pass `--yes` if the user
explicitly approved validation in this conversation.)

Afterwards, report from the JSON:

- per-attempt measurements and their spread (mean/stdev) — repeated runs
  exist precisely to expose variance, so show it;
- whether hard constraints held on every attempt;
- the final status: an experiment that survives becomes `validated`; one
  that regresses stays honest too — report that as the finding it is.

Next: the researchforge-ship skill turns a validated winner into a clean
branch, report, and optional draft PR.

## Rules

- The Python engine is the boundary: never work around a validation error, a
…

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_wxls4zgon4weknh2/fecfd7e552571c395053ed67a1c935c8aa5f3b352241a8c61d87ad6733f9ae90.json

Then /plugin install researchforge-validate@markdownregistry-wxls4zgon4weknh2 in Claude Code. It installs git:20260713.896358d, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add forger-labs-hq/researchforge/researchforge-validate@sha256:fecfd7e552571c39

The line at the top of this page pins the label git:20260713.896358d, 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_wxls4zgon4weknh2.svg)](https://markdownregistry.com/a/art_wxls4zgon4weknh2)

1 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 forger-labs-hq/researchforge/researchforge-validate 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 researchforge-validate from somewhere else? Ask it: where did my researchforge-validate 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 1 version of this file, committed on Jul 13, 2026.

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

versioncommittedcommitsizeaudit
git:20260713.896358d latest2026-07-13 896358d 1,785 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 (1785 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

forger-labs-hq/researchforge · 9 stars · license Apache-2.0 · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wxls4zgon4weknh2
GET https://markdownregistry.com/api/v1/resolve?ref=forger-labs-hq/researchforge/researchforge-validate
GET https://markdownregistry.com/api/v1/blob/fecfd7e552571c395053ed67a1c935c8aa5f3b352241a8c61d87ad6733f9ae90

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 forger-labs-hq/researchforge

overnight SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/overnight/SKILL.md · Improve a Kaggle score overnight. Use when the user says /overnight, gives a Kaggle competition URL or slug, or wants…
git:20261115.6378c2b · audit A · 9 stars
researchforge-autorun SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-autorun/SKILL.md · Drive the autonomous research loop round after round — ask the engine which node to expand, plan there, run, read the…
git:20261115.6378c2b · audit A · 9 stars
researchforge-baseline SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-baseline/SKILL.md · Set up the experiment contract and run the frozen baseline benchmark. Use when an improve-repository project needs its…
git:20260713.896358d · audit A · 9 stars
researchforge-doctor SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-doctor/SKILL.md · Check that ResearchForge's dependencies (git, Python, optionally Docker) are available and explain any failures. Use…
git:20260713.896358d · audit A · 9 stars
researchforge-hypotheses SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-hypotheses/SKILL.md · Generate testable, evidence-linked hypotheses from the research landscape and import them for validation. Use after the…
git:20260713.896358d · audit A · 9 stars
researchforge-landscape SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-landscape/SKILL.md · Synthesize stored papers into a research landscape — grouped directions with evidence claims — and import it for…
git:20260713.896358d · audit A · 9 stars
researchforge-paper SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-paper/SKILL.md · Build the research package — BibTeX citations, related work, evidence matrix, paper outline, reproducibility bundle…
git:20260713.896358d · audit A · 9 stars
researchforge-papers SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-papers/SKILL.md · Search arXiv for papers relevant to the project objective and review what was stored. Use when the user wants…
git:20260713.896358d · audit A · 9 stars
researchforge-plan SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-plan/SKILL.md · Design experiment variants for a hypothesis — write patches, import the plan for validation, and get it approved. Use…
git:20260720.c0c9164 · audit A · 9 stars
researchforge-results SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-results/SKILL.md · Summarize a run's results — ranking, Pareto trade-offs, constraint violations, and rejected experiments — grounded…
git:20260718.99c2d52 · audit A · 9 stars
researchforge-run SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-run/SKILL.md · Execute an approved experiment plan through the screening → full benchmark funnel, or resume an interrupted run. Use…
git:20260720.7aca8e5 · audit A · 9 stars
researchforge-ship SKILL.md skill
forger-labs-hq/researchforge · src/researchforge/claude/skills/researchforge-ship/SKILL.md · Ship a validated experiment — clean local branch reconstructed from the baseline, engineering report, and optional…
git:20260721.ac757f3 · audit A · 9 stars

Every file in forger-labs-hq/researchforge

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