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

Research

skill-kriscard-skills-research · by kriscard

>-

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

Install

$ agentstack add skill-kriscard-skills-research

✓ 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-kriscard-skills-research)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo 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 Research? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Research

Strategy (priority order)

Try these in order and stop at the first that returns useful results:

1. Context7 MCP — best for library/framework/SDK documentation

mcp__context7__resolve-library-id  →  mcp__context7__query-docs

Prefer this for npm packages, Python libraries, and popular frameworks. Training data goes stale; Context7 returns current docs.

2. GitHub CLI — for repos not indexed by Context7

gh repo view / --json description,readme
gh api repos///contents/docs

3. WebFetch → WebSearch — for everything else

  • WebFetch a specific URL if you have it
  • WebSearch when you need to find the right page first

Output Format

Deliver actionable implementation guidance — not a raw docs dump.

Key patterns — show working code examples for the most common use cases

Common pitfalls — what trips people up, especially on first use

Version notes — call out anything version-specific, especially for fast-moving ecosystems (Next.js App Router vs Pages, React 19 changes, Python 3.12+ features)

Authoritative sources — link to the official docs page you drew from so the user can verify

When to Search vs When to Answer From Memory

Search when:

  • The user is actively writing code that uses a library
  • The question involves specific API syntax, config options, or method signatures
  • The library had major changes in the past 12 months (anything in the JS/Python ecosystem)

Answer from memory when:

  • The question is about a fundamental concept (e.g., "what is a closure")
  • The user is asking for a high-level explanation, not implementation details
  • The library is very stable and the question is about basic usage (e.g., standard library functions)

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.