Automated summary

Queries a RAG-indexed conversation history and synthesizes an answer citing the relevant sessions.

Strengths

Combines multiple search results into a coherent answer with sources and dates.
Reports confidence based on result scores and clearly flags insufficient context.
Uses a configurable backend endpoint and can include code snippets found in past sessions.

Limitations

Depends on an external RAG backend and on history that has already been indexed.
Does not replace checking the current codebase or general knowledge unless explicitly offered.
Requires network access and the curl tool.

When to use it

Use it when you need to recall and synthesize information already captured in indexed past conversations.

When not to use it

Avoid it for questions about the current codebase or when the relevant history has not been indexed in the RAG database.

Security analysis

Caution

Quality score82/100

The skill has no destructive or obfuscated actions, but it reads a local config file and transmits user-provided question text to an external endpoint. That is legitimate for a RAG search skill, but it warrants caution because the endpoint is configurable and not validated, and the tool permissions do not match the documented commands.

Findings

•Reads local plugin config at ~/.claude/plugins/claude-rag/config.json, which may contain credentials or endpoint details.
•Sends the user's question to a remote RAG endpoint, defaulting to https://api.clauderag.io, so sensitive query content could leave the local environment.
•Declared allowed-tools is only Bash(curl *), but step 1 invokes cat, creating a tool-permission mismatch.
•Does not validate or allowlist the endpoint read from config before curling it, so a modified config could redirect queries to an arbitrary host.

How this analysis is made

Examples

Past decisions

/ask What decisions did we make about the database migration last week?

Find a fix session

/ask Find the session in my history where we fixed the authentication token refresh.

Summarize recent work

/ask Summarize what I did yesterday on the payments module and cite the sessions involved.

name: ask description: Ask a question about past work and get a synthesized answer informed by conversation history from the RAG database disable-model-invocation: true allowed-tools: Bash(curl *) argument-hint: "[question]"

RAG Ask

Name: Ask about past work using RAG
Author: Skills Guide Bot

Answer the user's question using RAG context: "$ARGUMENTS"

Instructions

Read the plugin config to get the backend endpoint:

cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}'

Search the RAG database for relevant context:

curl -s -X POST <endpoint>/api/v1/search \
  -H "Content-Type: application/json" \
  -d '{"query": "<user_question>", "limit": 10, "threshold": 0.4}'

Synthesize an answer based on the search results:
- Combine information from multiple results to form a coherent answer
- Cite specific sessions, tools, and dates when referencing past work
- If the answer comes from code (tool_result from Read), include relevant code snippets
- If results are from sub-agents, mention which agent type found the information
- Be transparent about confidence: if results have low scores (<0.5), caveat accordingly
Structure the response:
- Start with the direct answer
- Follow with supporting evidence from RAG results
- End with "Sources" listing the sessions/events referenced
If insufficient context is found:
- Say clearly that the RAG database doesn't have enough context
- Suggest what the user could search for instead
- Offer to answer from general knowledge (without RAG)

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/ask-about-past-work-using-rag-mttmx72y/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/ask-about-past-work-using-rag-mttmx72y' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ask-about-past-work-using-rag-mttmx72y/download' --output '.skill-downloads/ask-about-past-work-using-rag-mttmx72y/SKILL.md.part' && mv '.skill-downloads/ask-about-past-work-using-rag-mttmx72y/SKILL.md.part' '.skill-downloads/ask-about-past-work-using-rag-mttmx72y/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash(curl *)

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/ask-about-past-work-using-rag-mttmx72y/SKILL.md' && test -s '.skill-downloads/ask-about-past-work-using-rag-mttmx72y/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ask' && cp -R '.skill-downloads/ask-about-past-work-using-rag-mttmx72y' '.claude/skills/ask'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/ask-about-past-work-using-rag-mttmx72y'

openskills read 'ask-about-past-work-using-rag-mttmx72y'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/ask-about-past-work-using-rag-mttmx72y/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995

Skills Guide Bot