Skip to main content
skill CX Codex

fix · takagoto — Claude Code skill: what it does, how to install

Diagnoses and repairs broken RAG pipelines without lectures or theory. Useful when retrieval returns garbage or the model hallucinates.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add TakaGoto/rag-learning-academy --skill fix -a claude-code
Open on GitHub

What fix does

This skill focuses on repairing an existing RAG pipeline without walking through study material. It skips the curriculum and directly asks for the symptom, covering bad retrieval outputs, hallucinations, indexing misses, or query latency.

The agent inspects pipeline code files, checking chunking configuration, embedding model dimensions, vector database metric settings, retrieval top-k parameters, and prompt context injection. It then reports the root cause backed by evidence in your files and outputs a code diff.

The routine requires existing pipeline source files in your workspace; without actual implementation code, diagnosis cannot run. When progress/debug-log.md is present in your repository, the skill writes the resolution details there.

What it helps with

  • Fix poor retrieval precision caused by bad chunk size or overlap
  • Diagnose model hallucinations caused by missing context injection
  • Track down vector collection issues causing empty search outputs
  • Resolve throughput bottlenecks across embedding batches and database lookups

Example prompts for the agent

  • Our RAG pipeline returns irrelevant context on technical queries, diagnose it with fix
  • The model hallucinates answers despite having indexed docs, run fix on src/pipeline.py
  • Use fix to inspect our retrieval logic: queries only work half the time

How to install fix

1Skills CLI (Vercel)

npx skills add TakaGoto/rag-learning-academy --skill fix -a claude-code

2Manually: put the files in place

~/.claude/skills/fix/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/fix/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about fix

How do I install fix in Claude Code?

Run npx skills add TakaGoto/rag-learning-academy --skill fix -a claude-code in your terminal.

What does the fix skill do?

It identifies the failure symptom in your RAG setup, reads your source code, isolates the root cause, and provides a targeted code diff.

How is fix different from /debug-rag?

The /debug-rag command walks learners through failure modes step by step, whereas fix focuses on delivering an immediate patch without educational commentary.

Source text

SKILL.md · MIT
---
name: fix
description: "Diagnose and fix your RAG pipeline — skip the teaching, get to the answer"
---

# Fix: Fast-Track RAG Diagnosis

> **Scope:** This skill **diagnoses and fixes** an existing pipeline with no teaching. For guided debugging that explains common failure modes, use `/debug-rag`.

For learners who already have a RAG pipeline and just need help fixing it. No curriculum, no lessons — straight to diagnosis and solutions.

> **Language awareness:** See `.claude/LANGUAGE_AWARENESS.md`.

## Step 1: Get the Symptom

Ask one question: "What's going wrong?"

Common symptoms and what to probe for:

| Symptom | Follow-up |
|---------|-----------|
| "Bad retrieval results" | Ask for a sample query + what it returns vs what it should return |
| "Hallucinating" | Ask if context is being passed, and what the prompt looks like |
| "Slow" | Ask about data size, embedding model, vector DB, and whether they're batching |
| "No results" | Ask if data is indexed, and check the collection exists |
| "Works sometimes" | Ask for a working query and a failing query — compare them |

## Step 2: Read Their Code

Ask the learner to point you to their pipeline code. Read the files in `src/` or wherever they indicate. Look at:

1. **Chunking** — strategy, size, overlap
2. **Embedding** — model, dimensions, normalization
3. **Storage** — vector DB config, distance metric
4. **Retrieval** — top-k, filters, search type
5. **Generation** — prompt template, context injection, grounding instructions

## Step 3: Diagnose

Identify the likely root cause. Present it clearly:

```
Diagnosis: [one-line summary]
Root cause: [what's actually happening]
Evidence: [what in their code/output points to this]
```

If you're not certain, rank the top 2-3 most likely causes and explain how to verify each.

## Step 4: Fix It

Provide the specific code change needed. Show a before/after diff if possible. Explain *why* the fix works in 1-2 sentences — enough to understand, not a lecture.

If the fix requires multiple changes, prioritize: "Fix this first, then we'll check if the other issues resolve."

## Step 5: Verify

Help them test the fix:
1. Re-run the failing query
2. Compare the output to what they expected
3. If still broken, go back to Step 3 with the new information

## Step 6: Optional Learning

After the fix works, offer (don't push): "Want to understand why this happened? `/explain [relevant concept]` goes deeper on this."

Log the fix to `progress/debug-log.md` if the file exists.

Suggest next steps:
- `/lesson` on the concept behind the issue
- `/build` to implement the correct pattern from scratch
- `/roadmap` to see your overall progress

© TakaGoto · MIT · TakaGoto/rag-learning-academy

Similar skills

All skills for AI and ML →

fix by other authors comes first.

fix react The skill formats changed files and checks for remaining lint issues before a commit. Use it when code needs to pass CI checks. CX Codex +1 2,300installs fix Alireza Rezvani Sorts a failing or flaky Playwright test into a category, applies the matching fix, then proves it holds. Useful when a test fails in CI but passes locally. 1,638installs fix parcadei A meta-skill that picks a chain of skills for a bug and walks it from diagnosis to commit. Handy when you don't know where to start. CX Codex +1 484installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 350,300installs

From the same set16

recap Builds a brief recap of the previous lesson from progress files: what you covered, the main ideas, and what comes next. Handy when you come back to a course after a break. CX Codex +1 ★ 24repo stars quiz Generates interactive RAG quizzes with question-by-question scoring. Identifies knowledge gaps before you build retrieval pipelines. CX Codex +1 ★ 24repo stars paper-review Takes you through a RAG research paper section by section: background, method, results, and what to borrow for your own pipeline. Useful when a skim of the abstract is not enough. CX Codex +1 ★ 24repo stars journal The skill saves short notes about what you understood or got stuck on, appending them to progress/journal.md. Useful when you want a learning diary without the ceremony. CX Codex +1 ★ 24repo stars explain This skill teaches RAG concepts, from plain-language intuition to code and practical trade-offs. Use it to dig into topics such as embeddings, chunking, or hybrid search. CX Codex +1 ★ 24repo stars debug-rag Walks you from a symptom to the actual cause when retrieval or generation misbehaves. Useful once your RAG is built and the answers are still wrong. CX Codex +1 ★ 24repo stars build Interactive step-by-step guidance for constructing RAG components from scratch. CX Codex +1 ★ 24repo stars break-it A skill that plants bugs in RAG pipelines and asks you to find them. Debugging teaches architecture faster than building from scratch, since you have to understand why things work to spot why they fail. CX Codex +1 ★ 24repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor