Skills agent-generation

📦

agent-generation

Name: agent-generation
Author: Cpicon

v1.0.0 Content revision r1 Medium Risk ⚙️ External commands📁 Filesystem access

Generate Project-Specific Claude Code Agents

Generic assistants miss project conventions. This skill helps create specialized Claude Code agents using real architecture, domain, and tech stack details.

Supports: Claude Codex Code(CC)

📊 70 Adequate

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-generation" from https://skillstore.io/skills/cpicon-agent-generation.md and its manifest at https://skillstore.io/api/skills/cpicon-agent-generation/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/cpicon-agent-generation.md Signed manifest GET /api/skills/cpicon-agent-generation/manifest Signed lockfile GET /api/skills/cpicon-agent-generation/lockfile

Test it

Using "agent-generation". A Next.js dashboard needs agents for frontend patterns, file placement, and business entities.

Expected outcome:

The skill would recommend a React expert, an architecture expert, and a domain expert with separate triggers and project-specific guidance.

Using "agent-generation". A monorepo has frontend, backend, shared packages, tests, and deployment files.

Expected outcome:

The skill would suggest a larger team with technology, architecture, testing, DevOps, and domain roles mapped to relevant project areas.

Using "agent-generation". A team wants reusable standards for generated Claude Code agents.

Expected outcome:

The skill would provide consistent agent fields, color conventions, role boundaries, and prompt sections for every generated agent.

Security Audit

Medium Risk

v8 • 7/5/2026 Open versioned report

The static backtick, reconnaissance, and device-file alerts are false positives from Markdown documentation and read-only analysis examples. No prompt injection or malicious exfiltration intent was found. The remaining concern is that generated agent templates grant broad write, shell, and network tools by default.

Files scanned

1,160

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Medium

SKILL.md:56 examples/tech-stack-expert.md:101 examples/architecture-expert.md:137 examples/domain-expert.md:129

Overbroad Generated Agent Tool Permissions

The skill template and examples assign generated agents broad tools including Edit, Write, Bash, WebFetch, and WebSearch. This can enable unnecessary file modification, shell execution, or network access if copied into agents without review.

The same broad tool list appears in the core template and all three example agents. The risk depends on downstream publication, but the evidence is direct.

Risk Factors

⚙️ External commands (115)

📁 Filesystem access (8)

references/analysis-patterns.md:115 references/analysis-patterns.md:118 references/analysis-patterns.md:121 references/analysis-patterns.md:124 references/analysis-patterns.md:134 references/analysis-patterns.md:166 references/analysis-patterns.md:173 references/analysis-patterns.md:180

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/cpicon-agent-generation/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/cpicon-agent-generation.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

Cpicon. (2026). agent-generation security audit report (audit version 8) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/cpicon-agent-generation/audits/8

BibTeX citation

@techreport{cpicon-cpicon-agent-generation-2026,
  author = {Cpicon},
  title = {agent-generation security audit report (audit version 8)},
  institution = {Skillstore},
  year = {2026},
  number = {8},
  url = {https://skillstore.io/skills/cpicon-agent-generation/audits/8},
  note = {Author version 1.0.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-generation security audit report (audit version 8)"
version: "1.0.0"
type: report
authors:
  - name: "Cpicon"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/cpicon-agent-generation/audits/8"
identifiers:
  - type: other
    value: "skillstore:cpicon-agent-generation:audit:8"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create an Agent Team for a New Repository

Turn project structure, frameworks, and conventions into focused Claude Code agents for daily engineering work.

Standardize Internal Agent Templates

Use consistent fields, trigger rules, colors, and role boundaries across generated coding agents.

Document Codebase Expertise Areas

Convert architecture, technology, and business-domain knowledge into reusable assistant roles for team onboarding.

Try These Prompts

Generate a Basic Agent Team

Use this skill to create a small Claude Code agent team for my repository. Focus on tech stack and architecture agents first.

Create Role-Specific Agents

Use this skill to generate separate agents for frontend, backend, architecture, and domain logic. Keep trigger conditions distinct.

Tailor Agents to Existing Conventions

Analyze the repository conventions and use this skill to draft agents that reference real directories, naming rules, and framework patterns.

Design a Large Project Agent Strategy

Use this skill to design an agent team for a large codebase. Balance coverage, avoid overlapping triggers, and recommend tool permissions per role.

Best Practices

Ground every generated agent in actual project files, frameworks, and conventions.
Keep trigger conditions specific so agents do not overlap unnecessarily.
Review tool permissions before publishing generated agents in shared environments.