agentleFS
Sign inStart free
ROCmROCm/rocprofiler-systems-skills/skills/ask/SKILL.md

ask

Skill5 starsChanged 17 days agoMITView on GitHub

Use when user asks a question that doesn't require any action - just explanation or information

72 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

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 9

    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:

    Use this skill when the user is asking a question that requires explanation only, not implementation.

    line 8
  2. Distinctive:

    Do NOT use this skill if the user wants you to:

    line 21
  3. Distinctive:

    Write or modify code

    line 22
  4. Distinctive:

    Create or update files

    line 23
  5. Distinctive:

    If action is needed, use the appropriate planning skill instead.

    line 30
  6. Distinctive:

    Read relevant code/files: if the question is about the codebase

    line 41
  7. Distinctive:

    Use code examples: when helpful (but don't create files)

    line 43
  8. Distinctive:

    Reference specific files/lines: when explaining existing code

    line 44
  9. Distinctive:

    Offer follow-up: if they want to take action based on the answer

    line 45

“Common” is measured: kept by at least 6 in 10 of the 60 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

Ask Skill

Use this skill when the user is asking a question that requires explanation only, not implementation.

When to Use

This skill applies when the user wants to:

  • Understand how something works
  • Get an explanation of code, concepts, or architecture
  • Learn about best practices
  • Compare options or approaches
  • Get clarification on something

When NOT to Use

Do NOT use this skill if the user wants you to:

  • Write or modify code
  • Create or update files
  • Fix bugs
  • Implement features
  • Create documentation files
  • Systematic code exploration with structured output (use exploration-explore-code skill)
  • Debugging rocprof-sys issues - crashes, hangs, incorrect output (use debugging-rocprof-sys skill)

If action is needed, use the appropriate planning skill instead.

Quick explanation vs. deep exploration:

User RequestSkill to Use
"How does auth work here?" (quick answer)ask
"Explore the auth system so I can extract it" (structured analysis)exploration-explore-code
"rocprof-sys crashes when profiling my MPI app" (debugging)debugging-rocprof-sys

How to Respond

  1. Read relevant code/files if the question is about the codebase
  2. Provide clear, concise explanation
  3. Use code examples when helpful (but don't create files)
  4. Reference specific files/lines when explaining existing code
  5. Offer follow-up if they want to take action based on the answer

Response Format

Structure your answer clearly:

  1. Direct answer - Answer the question first
  2. Explanation - Provide context and details
  3. Examples - Show code snippets if relevant
  4. References - Point to relevant files/documentation
  5. Next steps (optional) - Suggest actions if they want to proceed

Example

User: "How does the authentication work in this project?"

Response:

Authentication uses JWT tokens with refresh token rotation.

Flow:

  1. User logs in with credentials
  2. Server validates and returns access + refresh tokens
  3. Access token (15min) used for API calls
  4. Refresh token (7 days) used to get new access tokens

Key files:

  • src/auth/authService.ts - Main auth logic
  • src/middleware/authMiddleware.ts - Token validation
  • src/auth/tokenService.ts - Token generation/refresh

Would you like me to implement any changes to the auth system?

No Planning Required

This skill does not require:

  • Creating a plan file
  • Using TodoWrite
  • Updating changelog

Simply answer the question and move on.

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.

Check your setup, free