Home / shinpr / agentic-code · GitHub

ai-development-guide SKILL.md skillA

ai-development-guide from shinpr/agentic-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add shinpr/agentic-code/ai-development-guide@git:20261103.998947c

Pins git:20261103.998947c in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: shinpr/agentic-code
Path: .agents/skills/ai-development-guide/SKILL.md
Versions recorded: 5
Latest version: git:20261103.998947c, committed Nov 3, 2026
First version recorded: Dec 30, 2025
Size: 3,403 bytes
Repository stars: 51
License: MIT

Applies root-cause analysis, impact inspection, and completeness checks without expanding the requested scope. Use when fixing bugs, refactoring, reviewing quality, or resolving unexpected implementation evidence.

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

# AI Development Guide

## Core Rule

Correct the invalid source before adding compensating layers. A workaround, fallback, abstraction, or new artifact is justified only when current evidence shows that removing or fixing the cause cannot satisfy the approved outcome.

## Investigation

Inspect the smallest relevant path that can establish:

- expected versus actual behavior;
- the first failing boundary;
- callers, contracts, and data or control flow affected;
- existing equivalent behavior and representative repository patterns;
- tests and checks that can reproduce or observe the issue;
- unknowns that could change the fix.

Mark findings as observed, inferred, or unknown. Expand inspection when new evidence points to another affected boundary, not to satisfy a fixed coverage checklist.

## Root-Cause Resolution

1. Reproduce or otherwise observe the failure.
2. Identify the earliest invalid assumption, state, or contract.
3. Determine whether existing code, configuration, or documentation already provides the correct mechanism.
4. Fix or remove the invalid source.
5. Add a focused regression proof when it protects the demonstrated failure from recurrence.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add shinpr/agentic-code/ai-development-guide@sha256:e0dc004cf1952286

The line at the top of this page pins the label git:20261103.998947c, 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](https://markdownregistry.com/badge/art_q5u6intmeb5f3z6o.svg)](https://markdownregistry.com/a/art_q5u6intmeb5f3z6o)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Dec 30, 2025 and Nov 3, 2026, about one every 77 days.

version	committed	commit	size	audit
git:20261103.998947c latest	2026-11-03	998947c	3,403 B	A	view · diff
git:20260829.876a214	2026-08-29	876a214	3,387 B	A	view · diff
git:20251231.cb53cf6	2025-12-31	cb53cf6	9,657 B	A	view · diff
git:20251230.9a88ee8	2025-12-30	9a88ee8	9,741 B	A	view · diff
git:20251230.7fa7e69	2025-12-30	7fa7e69	9,741 B	A	view

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 (3403 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

shinpr/agentic-code · 51 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_q5u6intmeb5f3z6o
GET https://markdownregistry.com/api/v1/resolve?ref=shinpr/agentic-code/ai-development-guide
GET https://markdownregistry.com/api/v1/blob/e0dc004cf1952286c699e54caec387231cc4e23de665249e56f031af6f91a649

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 shinpr/agentic-code

coding-rules SKILL.md skill

shinpr/agentic-code · .agents/skills/coding-rules/SKILL.md · Applies repository-aware rules for maintainable implementation, contracts, errors, and refactoring. Use when writing or…