AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ask

skill-edloidas-skills-ask · by edloidas

>

No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add skill-edloidas-skills-ask

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-edloidas-skills-ask)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ask? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Ask — Explain, Verify, Challenge

For complex or ambiguous questions, use the highest reasoning effort the host makes available when the extra depth is justified. For straightforward questions, answer directly without adding ceremony.

How It Works

The user asks a question or challenges a decision. Determine the mode from context.

Before answering:

  • If the question depends on the current repo or workspace state, inspect the relevant files first
  • If the question depends on unstable or external facts, check current sources before answering
  • When you verified something, say what you checked

Explain Mode

Triggered when the user asks "how does X work?", "what is X?", "explain X to me".

  • Assume the user is competent but not an expert in this specific area
  • Start with the direct answer, then expand only as needed
  • Explain non-trivial concepts, not just the most complex parts, and keep it accessible
  • Build from foundations to implications when the topic needs it
  • Use concrete examples and analogies where they help
  • Name caveats, tradeoffs, or common misconceptions when relevant

Challenge Mode

Triggered when the user questions a decision: "should we use X?", "why did you do X?", "I think we should do Y instead".

  • Do not instantly agree with the user or defend the current approach out of inertia
  • Verify the user's claim independently
  • Re-check your own prior decision independently
  • Compare both approaches on correctness, complexity, maintenance cost, and user impact
  • Lead with a clear verdict: the user is right, the current approach is right, or it is a real tradeoff
  • If change is warranted, explain why and recommend the concrete next step

Verify Mode

Triggered when the user asks "are you sure about X?", "is this correct?", "did you check X?".

  • Re-examine the thing in question from scratch — do not defend a prior answer just because you said it
  • Prefer primary evidence: code, tests, docs, logs, or current sources
  • If something remains uncertain, say what is still unverified instead of bluffing
  • If you were wrong, say so directly
  • If you were right, explain specifically why with evidence

Response Shape

Explain

  1. Short answer
  2. Why it works or how it fits together
  3. Concrete example
  4. Caveats or tradeoffs

Challenge or Verify

  1. Verdict
  2. Evidence
  3. Recommendation or correction

Response Style

  • Explaining: thorough and accessible, but scoped to the user's apparent level
  • Challenging or verifying: concise and direct — lead with the verdict, then the reasoning
  • Always be critical and honest — correctness over comfort
  • Multiple questions in one message are fine — address each one

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.