jules-ai-engineering-workflow SKILL.md skillA
jules-ai-engineering-workflow from mishrashardendu22/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mishrashardendu22/agent-skills/jules-ai-engineering-workflow@git:20260917.f685a8fPins git:20260917.f685a8f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mishrashardendu22/agent-skills
- Path
.agents/skills/jules-ai-engineering-workflow/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260917.f685a8f, committed Sep 17, 2026
- First version recorded
- Aug 31, 2026
- Size
- 10,738 bytes
- Repository stars
- 6
- License
- MIT
Standard operating procedures for the autonomous Jules AI engineering review-improve-converge loop, evaluating code across 38 architectural dimensions and preparing merge-ready PRs for the human Technical Lead.
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
# Jules Autonomous AI Engineering Review & Improvement Loop
This skill establishes the standard operating framework for the autonomous AI-driven engineering pipeline across repositories. Under this framework, concurrent AI engineers author implementations and open Pull Requests, while **Google Jules CLI** performs multi-dimensional code reviews and autonomous remediation cycles until the PR achieves production convergence—requiring only final high-level signoff from the human **Technical Lead**.
---
## 1. Pipeline Architecture & Tech Lead Delegation Model
```mermaid
flowchart TD
AI[AI Engineer creates Feature Branch & PR] --> JulesReview[Jules Multi-Dimensional Staff Review]
JulesReview --> Check{Quality Score >= 95% & Zero P0/P1?}
Check -- No (P0/P1/P2 Found) --> Remediation[Jules Auto-Remediation Session / AI Engineer Patch]
Remediation --> Validate[make pre-commit && make test]
Validate --> Push[Commit & Push Improvements]
Push --> JulesReview
Check -- Yes (Converged) --> Finalize[Synthesize Staff-Grade PR Description & Apply Approval Labels]
Finalize --> TechLead[Human Technical Lead Final Decision & 1-Click Merge]
```
…Read the whole file at its exact version.
How to install
mdr add mishrashardendu22/agent-skills/jules-ai-engineering-workflow@sha256:fea6a9675ff2e125The line at the top of this page pins the label git:20260917.f685a8f, 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_kbzn2migu2vhjba7)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 31, 2026 and Sep 17, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260917.f685a8f latest | 2026-09-17 | f685a8f | 10,738 B | A | view · diff |
| git:20260914.e06e21c | 2026-09-14 | e06e21c | 7,429 B | A | view · diff |
| git:20260905.a73d7ea | 2026-09-05 | a73d7ea | 7,414 B | A | view · diff |
| git:20260831.0978e7e | 2026-08-31 | 0978e7e | 8,125 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 (10738 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
mishrashardendu22/agent-skills · 6 stars · license MIT · pushed 2026-09-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_kbzn2migu2vhjba7 GET https://markdownregistry.com/api/v1/resolve?ref=mishrashardendu22/agent-skills/jules-ai-engineering-workflow GET https://markdownregistry.com/api/v1/blob/fea6a9675ff2e12551ea00dd45b4ed7f2c97c480ab7a36b782130662f9de9c4a
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.