agentleFS
ThisisYoYoDevThisisYoYoDev/claude-rag/skills/ask/SKILL.md

ask

Skill9 starsChanged 8 months agoMITView on GitHub

Ask a question about past work and get a synthesized answer informed by conversation history from the RAG database

  • Sends data out

83 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 68 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the plugin config to get the backend endpoint:

    line 15
  2. Distinctive:

    Search the RAG database for relevant context:

    line 20
  3. Distinctive:

    If the answer comes from code (tool_result from Read), include relevant code snippets

    line 30
  4. Distinctive:

    If results are from sub-agents, mention which agent type found the information

    line 31
  5. Distinctive:

    Start with the direct answer

    line 35
  6. Distinctive:

    Follow with supporting evidence from RAG results

    line 36
  7. Distinctive:

    If insufficient context is found:

    line 39

“Common” is measured: kept by at least 6 in 10 of the 68 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

RAG Ask

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

Instructions

  1. 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"}}'
  2. 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}'
  3. 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
  4. Structure the response:
    • Start with the direct answer
    • Follow with supporting evidence from RAG results
    • End with "Sources" listing the sessions/events referenced
  5. 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)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.