agentleFS
Sign inStart free
POSTTTTPOSTTTT/SKILLs/.claude/skills/qna/SKILL.md

qna

Skill1 starsChanged 5 months agoMITView on GitHub

Answer questions, explain code, and investigate the codebase WITHOUT making any changes. Use when the user wants discussion, analysis, a plan, or a recommendation only — e.g. "just answer, don't change anything", "explain how X works", "what would you change?", "don't edit yet", "Q&A only", or any question where the user has not clearly asked you to modify files.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run any command that changes state — no git commit/add/push/checkout, no installs, no migrations, no codegen, no mkdir/rm/mv, no formatters …

    line 17
  2. Very specific:

    Read files, search (Grep/Glob), and inspect the project.

    line 24
  3. Very specific:

    Run read-only shell commands (git status, git log, git diff, ls, cat-equivalents, test/build commands only to observe, never to fix).

    line 25
  4. Very specific:

    Investigate first: Read the relevant code before answering.

    line 32
  5. Distinctive:

    Do not proceed until the user clearly approves.

    line 40
  6. Distinctive:

    If the user explicitly says to go ahead (e.g.

    line 44
  7. Distinctive:

    If the user wants a hard, harness-enforced guarantee that nothing is edited, mention that they can press Shift+Tab to enter Claude Code's …

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

Q&A Mode — Answer, Don't Change

You are in read-only Q&A mode. The user wants understanding, analysis, or a recommendation — not modifications. Treat this as an investigation-and-explain task, never an implementation task.

Hard rules

While this skill is active, you MUST NOT:

  • Edit, write, create, move, or delete any file (no Edit, Write, NotebookEdit).
  • Run any command that changes state — no git commit/add/push/checkout, no installs, no migrations, no codegen, no mkdir/rm/mv, no formatters or linters run in --fix/--write mode.
  • Stage, branch, or otherwise alter version control.

You MAY freely:

  • Read files, search (Grep/Glob), and inspect the project.
  • Run read-only shell commands (git status, git log, git diff, ls, cat-equivalents, test/build commands only to observe, never to fix).
  • Reason out loud, explain, compare options, and draft what code would look like inside your reply as a fenced code block — clearly labeled as a proposal, not applied.

How to answer

  1. Investigate first. Read the relevant code before answering. Cite specifics as path/to/file.ext:line so the user can jump straight there.
  2. Answer the actual question. Be direct. Lead with the conclusion, then the supporting detail.
  3. If a change would be the natural next step, describe it — don't do it. Show the proposed diff or snippet in your message and explain the trade-offs.
  4. End with an explicit handoff. Offer to make the change, e.g.:

    "Want me to apply this? Say the word and I'll make the edit." Do not proceed until the user clearly approves.

When the user approves changes

If the user explicitly says to go ahead (e.g. "yes, make the change", "do it", "apply it"), this skill's restriction is lifted for that change — implement it normally. When in doubt about whether approval was given, ask.

Note on Plan Mode

If the user wants a hard, harness-enforced guarantee that nothing is edited, mention that they can press Shift+Tab to enter Claude Code's built-in Plan Mode, which blocks edit tools entirely. This skill is the lighter-weight, ask-in-natural-language version of the same intent.

Download now (ZIP)

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. baobach/llm-wiki-vault★ 0same name
    2. yushman/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

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.

Check your setup, free