Skip to content
Skills Library
Programming · Building & coding

rag-code-gen

/rag-code-gen

RAG-grounded code generation with source citations. Triggers on: grounded code, ground this, cite sources, show me with sources, how do I with attune, reference attune docs, grounded against attune docs.

Repository
attune-ai ↗
Licence
Apache-2.0
Last repository change
24.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

RAG-grounded code generation with source citations. Triggers on: grounded code, ground this, cite sources, show me with sources, how do I with attune, reference attune docs, grounded against attune docs.

Original author description

RAG-grounded code generation with source citations. Triggers on: grounded code, ground this, cite sources, show me with sources, how do I with attune, reference attune docs, grounded against attune docs.

How it works

  1. Scoping
  2. Running
  3. Output shape
  4. When RAG doesn't help
  5. Alternative: MCP tool only (no LLM call)
  6. If the extra isn't installed
  7. See also
Original SKILL.md headings · 80 lines, 375 words
SKILL.md preview
---
name: rag-code-gen
description: "RAG-grounded code generation with source citations. Triggers on: grounded code, ground this, cite sources, show me with sources, how do I with attune, reference attune docs, grounded against attune docs."
---
# RAG-grounded code generation

attune-rag ships with attune-ai core (`pip install attune-ai`).
Grounds code generation in the attune-help template corpus
so outputs cite real APIs, workflow names, and patterns
instead of hallucinating them. Every output ends with a
`## Sources` block of clickable citations.

## Scoping

Before running, ask:

1. **What are you trying to produce?** Code, config,
   explanation, or a mix?
2. **Any specific attune surface?** e.g. "the
   security-audit workflow", "MCP tool pattern", "BaseWorkflow
   subclass". Helps retrieval hit the right concept file.
3. **Depth?** Default is `standard`. `quick` saves time
   and budget for simple asks; `deep` is for complex
   multi-file or architectural questions.

## Running

```
attune workflow run rag-code-gen \
  --input '{"query": "<the request>"}'
```

Optional inputs:

- `k` — max grounding docs to retrieve (default 3)
- `depth` — `quick` / `standard` / `deep`
- `feedback` — pass `good` or `bad` AFTER inspecting the
  output to record a verdict against every cited template
- `model` — override the generator model if you need to

## Output shape

`WorkflowResult.final_output` is a string with two parts:

1. The generated code / explanation
2. A `## Sources` section listing each cited
   `attune-help` template with its category, retrieval
   score, and a clickable link to the source on GitHub

`WorkflowResult.metadata` carries the full citation dict
(`query`, `retriever_name`, `retrieved_at`, `hits[]`) plus
`fallback_used` and `confidence` so callers can make
routing decisions.

## When RAG doesn't help

If the retriever can't find relevant templates, the
workflow still runs — it falls back to an unaugmented
prompt that explicitly tells the model there is NO
grounding context so it should say "I don't know about
attune X" rather than invent. `metadata.fallback_used` is
`True` in that case.

## Alternative: MCP tool only (no LLM call)

If you want just retrieval without generation, use the
`rag_knowledge_query` MCP tool directly. It returns hits +
an augmented prompt string without calling an LLM itself —
handy for routing decisions, agent planning, or feeding
another model.

## If the extra isn't installed

The workflow returns a structured error pointing at
`pip install attune-rag` (a core dep — missing means a broken
install). No exception propagates.

## See also

- [docs/rag/index.md](../../docs/rag/index.md) — full
  walkthrough including the standalone attune-rag usage
- [attune-rag on PyPI](https://pypi.org/project/attune-rag/)
- [Embeddings decision record](../../docs/rag/embeddings-decision-2026-04-17.md)

Versions

The database has no other skills named rag-code-gen.

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 57ddef972a19 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100attune-hub
    Developer workflow hub — routes to the right skill based on what you need. Triggers on: attune, what can attune do, what can you do, capabilities, where do I start, get started.
  • 95catalog
    Enumerate everything attune offers — every workflow, wizard, and tool, read live from the registries. Triggers on: catalog, list capabilities, browse, show all, what can attune do, list workflows, list wizards, what tools are there.
  • 100gen-docs
    文档生成器。自动分析模块结构,生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.