rag-vs-finetune-decision SKILL.md skillA
rag-vs-finetune-decision from vandanaajaydubey111/great-pm is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vandanaajaydubey111/great-pm/rag-vs-finetune-decision@git:20260721.86de099Pins git:20260721.86de099 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vandanaajaydubey111/great-pm
- Path
skills/rag-vs-finetune-decision/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260721.86de099, committed Jul 21, 2026
- Size
- 17,102 bytes
- Repository stars
- 3
- License
- MIT
The model-capability decision tree — prompt-engineering first, then RAG for missing knowledge, then fine-tuning for missing behavior/format or cost/latency, climbing only as far as needed. Covers the cost/latency/maintenance tradeoffs of each rung and when each is the wrong choice (especially the premature-fine-tune trap). Gives the PM the framework to decide where an AI feature's knowledge and behavior should come from. Used by ai-prompt-architect and architect.
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
# RAG vs Fine-tune Decision — the model-capability ladder When an AI feature isn't good enough, teams reach for the most expensive, least reversible fix — fine-tuning — far too early. The discipline this skill enforces: **climb the capability ladder prompt → RAG → fine-tune only as far as the problem actually requires.** Roughly **99% of products never need fine-tuning.** The decision is not "which is most powerful" — it is *where the missing capability actually lives,* and the cheapest rung that closes that specific gap. The diagnosing question for every gap: **does the model lack instructions, knowledge, or behavior?** - Missing **instructions** (it *can* do it, but you asked badly) → **prompt engineering.** - Missing **knowledge** (it doesn't *know* your facts, or they go stale) → **RAG.** - Missing **behavior / format at scale**, or a **latency/cost** problem from huge repeated prompts → **fine-tuning** (only after prompt + RAG fail). ## 1. Rung 1 — Prompt engineering (always first) The cheapest, fastest, most reversible lever. Before anything else, exhaust the prompt. The seven components of a strong prompt: …
Read the whole file at its exact version.
How to install
mdr add vandanaajaydubey111/great-pm/rag-vs-finetune-decision@sha256:ed196df404508eb4The line at the top of this page pins the label git:20260721.86de099, 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_5ss5osahrc562slg)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 21, 2026.
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 (17102 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
vandanaajaydubey111/great-pm · 3 stars · license MIT · pushed 2026-09-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5ss5osahrc562slg GET https://markdownregistry.com/api/v1/resolve?ref=vandanaajaydubey111/great-pm/rag-vs-finetune-decision GET https://markdownregistry.com/api/v1/blob/ed196df404508eb428ef8f8e30705606c739f77600ebaaeb804379dd604d92ef
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 vandanaajaydubey111/great-pm
Every file in vandanaajaydubey111/great-pm