learning-loop skillA
learning-loop is agent-read markdown (skill) from robium-ai/robium: Turn captured Robium experience into small, evidence-backed skill improvements..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Learning loop Capture is a lead, not knowledge. Promote it only when the evidence can improve a future decision without injecting old conversations into new work. ## Capture without recall - Hooks may queue corrections, failures, and transcript windows silently. - Findings live in one store, `learnings/observations/<skill>.md`. Capture is a `tentative` entry there — status and signal are the only required fields. - Never insert queue items, observations, memories, or reminders into a new prompt. Read them only during an explicit consolidate, absorb, refine, or status task. - Batch bookkeeping at a natural milestone. A command error or clean skill run is not automatically a reusable lesson. - Keep project-specific facts in the application that owns them. ## Promote evidence - Read the source transcript before turning a flag into an observation. - Preserve what was expected, what actually happened, the evidence for the fix, and any dead ends that prevent repeating the mistake. - Absorb only observations marked `ready`; uncertain material stays tentative. - Deduplicate the finding before carrying it forward. …
Read the whole file at its exact version.
How to install
mdr add robium-ai/robium/learning-loop@git:20260922.d17aa3emdr add robium-ai/robium/learning-loop@sha256:3eef4b9c680b5b3bPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_3agqbcmqa5y2r2ho)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260922.d17aa3e latest | 2026-09-22 | d17aa3e | 3,275 B | A | view · diff |
| git:20260907.863840e | 2026-09-07 | 863840e | 3,061 B | A | view · diff |
| v1.2.0 | 2026-08-28 | 371219b | 11,293 B | A | view · diff |
| v1.1.0 | 2026-08-28 | a7a0334 | 11,151 B | A | view · diff |
| v1.0.1 | 2026-08-28 | 32770d5 | 10,676 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3275 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
robium-ai/robium · 14 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3agqbcmqa5y2r2ho GET https://markdownregistry.com/api/v1/resolve?ref=robium-ai/robium/learning-loop GET https://markdownregistry.com/api/v1/blob/3eef4b9c680b5b3b13b787219d04496016e4aa918d756254697c71d22c7c177a
Your agent 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.
More from robium-ai/robium
Every file in robium-ai/robium