agent-improvement SKILL.md skillA
agent-improvement from devantler-tech/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add devantler-tech/agent-skills/agent-improvement@git:20261024.422a282Pins git:20261024.422a282 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- devantler-tech/agent-skills
- Path
agent-improvement/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261024.422a282, committed Oct 24, 2026
- First version recorded
- Aug 31, 2026
- Size
- 19,997 bytes
- Repository stars
- 3
- License
- Apache-2.0
How a meta-engineer improves an autonomous AI engineer from the OUTSIDE — mining the agent's own operational telemetry across many runs and, where a deployment runs more than one instance, across all of them. Scores the agent on reliability, safety, efficiency, outcome throughput, quality, coordination, currency, and prioritization/flow, diagnoses root causes from measured patterns, ships the highest-value fix with its evidence and a reversible audit trail, then verifies the targeted metric…
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
# Agent-improvement loop An autonomous AI engineer improves the products it owns. This skill is how something improves **the engineer itself**, from the outside, on evidence the agent generated by running. **It complements a `self-improvement` skill rather than replacing it.** Self-improvement is a single run reflecting on its own memory, on a slow distil cadence. This is an **external observer** across the whole session corpus — and, in a deployment running more than one instance, across all of them at once. The observer's own Agent Improver sessions are part of that corpus too: it improves the Engineer's execution plane and its own observation plane as separately measured subjects. That vantage point is what makes it see things no single run can: - failures that recur across hundreds of runs but look like one-offs from inside any single run; - waste that feels normal from inside a run (a wait, a retry, a re-read) and is obvious in aggregate; - **divergence between sibling instances** of the same brain; - **drift between what the agent's bootstrap/loader says and what its contract says** — the loaders are …
Read the whole file at its exact version.
How to install
mdr add devantler-tech/agent-skills/agent-improvement@sha256:865e6e98d9c41a8aThe line at the top of this page pins the label git:20261024.422a282, 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.
[](https://markdownregistry.com/a/art_inh5uyhe2wbohvor)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Aug 31, 2026 and Oct 24, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261024.422a282 latest | 2026-10-24 | 422a282 | 19,997 B | A | view · diff |
| git:20261009.698dbfc | 2026-10-09 | 698dbfc | 41,417 B | A | view · diff |
| git:20261008.533fb01 | 2026-10-08 | 533fb01 | 40,837 B | A | view · diff |
| git:20261008.bb2aa6b | 2026-10-08 | bb2aa6b | 40,542 B | A | view · diff |
| git:20260924.2edcf23 | 2026-09-24 | 2edcf23 | 40,007 B | A | view · diff |
| git:20260912.9d434db | 2026-09-12 | 9d434db | 38,192 B | A | view · diff |
| git:20260908.cfeec83 | 2026-09-08 | cfeec83 | 37,473 B | A | view · diff |
| git:20260903.0974484 | 2026-09-03 | 0974484 | 36,066 B | A | view · diff |
| git:20260831.9258038 | 2026-08-31 | 9258038 | 34,979 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 (19997 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
devantler-tech/agent-skills · 3 stars · license Apache-2.0 · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_inh5uyhe2wbohvor GET https://markdownregistry.com/api/v1/resolve?ref=devantler-tech/agent-skills/agent-improvement GET https://markdownregistry.com/api/v1/blob/865e6e98d9c41a8ae8b3e5f49538fb55bff57d374bd773431fb2f30771d71c10
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 devantler-tech/agent-skills
Every file in devantler-tech/agent-skills