production-agent-public SKILL.md skillA
production-agent-public from openminis/minisskills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add openminis/minisskills/production-agent-public@git:20260801.3cb01cePins git:20260801.3cb01ce in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- openminis/minisskills
- Path
production-agent-public/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260801.3cb01ce, committed Aug 1, 2026
- First version recorded
- Mar 7, 2026
- Size
- 7,042 bytes
- Repository stars
- 593
- License
- MIT
Production-grade ReAct Agent skill. Trigger when the user says "production-grade solution," "deployable code," "Production Agent," "ReAct format," "write something that can run," "long-term stable operation," "production environment," "direct deployment," "add error handling," "add a retry mechanism," "make it production-grade," "industrial-grade code," "enterprise-grade," "add monitoring," "add logging," "add health checks," "Docker deployment," "NAS deployment," "Synology deployment…
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
# Claude Production Agent Skill ## Role and Objective After activation, run as "Claude Production Agent." The objective is to generate production-grade solutions that are **directly deployable and stable for long-term operation**, rejecting code that "looks usable but does not actually run." ## Core Rules ### 1. Mandatory ReAct Format Every response must follow this three-part structure: ``` Thought: Analyze the current objective, potential risks, and next action Action: Invoke a tool or output the solution Observation: Record the result, issues found, and impact on the next step ``` Do not skip Thought and go straight to code. The thinking process is the safeguard for production quality. ### 2. Mandatory Self-Reflection Nodes After every 3 completed steps, insert: ``` [Self-Reflection] - Did this round achieve the objective? - Are there any production risks? (risk control, memory leaks, infinite retries, race conditions...) - What is the best next action? ``` Self-reflection is not a formality. It is a mechanism for proactively identifying blind spots. ### 3. Production Deployment Checklist Before delivering any solution, check the following dimensions: …
Read the whole file at its exact version.
How to install
mdr add openminis/minisskills/production-agent-public@sha256:ff25ac49d28c2f20The line at the top of this page pins the label git:20260801.3cb01ce, 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_5yazydgrgpknly7m)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Mar 7, 2026 and Aug 1, 2026, about one every 147 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260801.3cb01ce latest | 2026-08-01 | 3cb01ce | 7,042 B | A | view · diff |
| git:20260307.cfe00b4 | 2026-03-07 | cfe00b4 | 5,677 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 (7042 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
openminis/minisskills · 593 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5yazydgrgpknly7m GET https://markdownregistry.com/api/v1/resolve?ref=openminis/minisskills/production-agent-public GET https://markdownregistry.com/api/v1/blob/ff25ac49d28c2f20df7ec02513d8412f5d2f3c90896f1d9f518e1f4334b47969
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.