Skills Agent Development

📦

Agent Development

Name: Agent Development
Author: davila7

v0.1.0 Content revision r1 Safe 📁 Filesystem access⚙️ External commands

Build Claude Code Agents

Creating reliable plugin agents is difficult when triggers, tools, and prompts are unclear. This skill provides reusable patterns for agent structure, validation, and testing.

Supports: Claude Codex Code(CC)

🥇 83 Gold

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "Agent Development" from https://skillstore.io/skills/davila7-agent-development.md and its manifest at https://skillstore.io/api/skills/davila7-agent-development/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/davila7-agent-development.md Signed manifest GET /api/skills/davila7-agent-development/manifest Signed lockfile GET /api/skills/davila7-agent-development/lockfile

Test it

Using "Agent Development". Create an agent that reviews pull requests for code quality.

Expected outcome:

A reviewer agent plan with a clear identifier, trigger examples for pull requests, read-only tools, quality checks, and a structured report format.

Using "Agent Development". Improve this agent description so it triggers more reliably.

Expected outcome:

A revised trigger description with concrete examples, commentary for each example, exclusions, and wording that avoids broad activation.

Using "Agent Development". Check whether my testing agent has the right tool permissions.

Expected outcome:

A tool-scope recommendation that explains required read and search access, when shell access is useful, and which permissions are unnecessary.

Security Audit

Safe

v9 • 7/19/2026 Open versioned report

All 82 static findings are false positives caused by Markdown backticks, illustrative ellipses, ordinary prose, comments, or fixed local parsing commands in the validator. The reviewed files show no malicious command construction, path traversal, reconnaissance, data exfiltration, or prompt injection intent.

Files scanned

2,413

Lines analyzed

Review items

False positives ignored

Risk Factors

📁 Filesystem access (2)

examples/agent-creation-prompt.md:146 references/agent-creation-system-prompt.md:87

⚙️ External commands (50)

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/davila7-agent-development/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/davila7-agent-development/security.svg)](https://skillstore.io/skills/davila7-agent-development?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/davila7-agent-development?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-agent-development/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-agent-development.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

davila7. (2026). Agent Development security audit report (audit version 9) [Author version 0.1.0]. Skillstore. https://skillstore.io/skills/davila7-agent-development/audits/9

BibTeX citation

@techreport{davila7-davila7-agent-development-2026,
  author = {davila7},
  title = {Agent Development security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-agent-development/audits/9},
  note = {Author version 0.1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "Agent Development security audit report (audit version 9)"
version: "0.1.0"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-19"
url: "https://skillstore.io/skills/davila7-agent-development/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-agent-development:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

4 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

Dami-Randle Recommended

dami-randle-agent-development

Skillstore Score 85

Evidence Confidence High

Skillstore usage 25

Updated

2026-08-21

anthropics

agent-development

Skillstore Score 84

Evidence Confidence High

Skillstore usage 32

Updated

2026-08-21

anthropics

anthropics-agent-development

Skillstore Score 84

Evidence Confidence High

Skillstore usage 13

Updated

2026-08-21

davila7 Current

davila7-agent-development

Skillstore Score 83

Evidence Confidence High

Skillstore usage 11

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create a New Plugin Agent

Design an agent with a valid identifier, trigger examples, model choice, color, tools, and system prompt.

Improve Agent Triggering

Rewrite vague descriptions into precise trigger conditions with examples that show when the agent should run.

Review Agent Safety Boundaries

Check whether an agent uses least-privilege tools and has clear responsibilities, output format, and edge cases.

Try These Prompts

Create a Basic Agent

Create a Claude Code plugin agent for [task]. Include the identifier, trigger description, model, color, tool scope, and system prompt outline.

Refine Triggering Rules

Review this agent description for trigger quality: [description]. Make it specific, add examples, and explain when not to use the agent.

Design Least-Privilege Tools

For an agent that handles [responsibilities], recommend the minimum Claude Code tools it needs. Explain each tool choice and any tool to avoid.

Audit a Multi-Agent Plugin

Review these planned agents: [agent list]. Check naming, trigger overlap, tool scope, model choice, prompt structure, and validation gaps.

Best Practices

Write trigger descriptions with concrete user requests and clear commentary.
Give each agent only the tools required for its responsibilities.
Validate the agent file and test realistic triggering scenarios before publishing.