Skills agent-tool-builder
📦

agent-tool-builder

Content revision r2 Safe ⚙️ External commands🌐 Network access

Build Reliable AI Agent Tools

Poorly defined tools cause invalid calls, silent failures, and wasted tokens. This skill guides schema design, validation, error handling, MCP integration, and parallel execution.

Supports: Claude Codex Code(CC)
🥉 77 Bronze

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-tool-builder" from https://skillstore.io/skills/sickn33-agent-tool-builder.md and its manifest at https://skillstore.io/api/skills/sickn33-agent-tool-builder/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/sickn33-agent-tool-builder.md Signed manifest GET /api/skills/sickn33-agent-tool-builder/manifest Signed lockfile GET /api/skills/sickn33-agent-tool-builder/lockfile

Test it

Using "agent-tool-builder". Design a customer lookup tool using an email address.

Expected outcome:

A focused lookup design with a validated email parameter, explicit not-found behavior, permission errors, and a concise customer summary.

Using "agent-tool-builder". Improve a vague weather tool that only says it gets weather.

Expected outcome:

A revised description states supported locations, units, current-weather scope, expected response details, and recovery guidance for invalid places.

Using "agent-tool-builder". Review four independent research tools for execution speed.

Expected outcome:

The review groups independent calls for parallel execution, preserves result identifiers, combines responses once, and isolates retries for failed services.

Security Audit

Safe
v5 • 7/23/2026 Open versioned report

All seven static findings are false positives caused by documentation syntax, illustrative API calls, or ordinary prose. The skill contains guidance and examples, with no executable scripts or prompt injection evidence.

1
Files scanned
715
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (3)
SKILL.md:410 SKILL.md:418 SKILL.md:695
🌐 Network access (1)
SKILL.md:314
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
Security Assessment

Copy report link

https://skillstore.io/skills/sickn33-agent-tool-builder/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-agent-tool-builder/security.svg)](https://skillstore.io/skills/sickn33-agent-tool-builder?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-agent-tool-builder?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-agent-tool-builder/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-agent-tool-builder.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

sickn33. (2026). agent-tool-builder security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-agent-tool-builder/audits/5

BibTeX citation

@techreport{sickn33-sickn33-agent-tool-builder-2026, author = {sickn33}, title = {agent-tool-builder security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/sickn33-agent-tool-builder/audits/5}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "agent-tool-builder security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "sickn33" date-released: "2026-07-23" url: "https://skillstore.io/skills/sickn33-agent-tool-builder/audits/5" identifiers: - type: other value: "skillstore:sickn33-agent-tool-builder:audit:5" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
74
Spec Compliance

What You Can Build

Define a First Agent Tool

Create a clear schema, parameter descriptions, and recoverable errors for a new function-calling integration.

Standardize an MCP Service

Review tool discovery, call handling, response formatting, and access controls before sharing an MCP server.

Improve Tool Reliability

Diagnose invalid calls, ambiguous descriptions, silent failures, and inefficient sequential execution in an existing agent.

Try These Prompts

Draft a Tool Schema 
Design a tool for [task]. Define its name, purpose, parameters, required fields, constraints, return text, and likely validation errors.
Improve an Existing Tool 
Review this tool definition: [definition]. Identify ambiguous descriptions, missing constraints, weak examples, and unrecoverable errors. Provide a revised design.
Plan an MCP Server 
Plan an MCP server for [system]. Define a small tool set, schemas, permissions, error behavior, transport, observability, and integration tests.
Audit a Production Tool Loop 
Audit this agent tool loop: [workflow]. Assess selection accuracy, validation, retries, timeouts, parallel calls, result ordering, access control, and test coverage.

Best Practices

  • Describe when each tool applies, what every parameter means, and what the result contains.
  • Validate all model-provided inputs before execution and return errors that support recovery.
  • Test tool selection and argument quality with the target model alongside conventional unit and integration tests.

Avoid

  • Do not expose many overlapping tools with vague names or descriptions.
  • Do not return silent failures, generic errors, or unstructured implementation details.
  • Do not concatenate user input into SQL, shell commands, URLs, or other executable contexts.

Frequently Asked Questions

What types of tools does this skill cover?
It covers function-calling tools, MCP tools, schema design, validation, error handling, tool runners, and parallel execution.
Does it implement the tool for me?
It guides design and implementation patterns. You still adapt the result to your SDK, services, permissions, and deployment environment.
Which assistants can use this skill?
The marketplace metadata lists Claude, Codex, and Claude Code as supported tools.
Can it improve an existing tool schema?
Yes. Provide the schema and expected behavior so it can identify ambiguity, missing constraints, weak errors, and testing gaps.
Does it support MCP servers?
Yes. It includes MCP tool discovery, call handling, response formatting, transport setup, access controls, and interoperability guidance.
How should generated designs be verified?
Run schema validation, unit tests, integration tests, model-based tool selection tests, permission checks, and failure-path tests before deployment.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/agent-tool-builder

Ref

ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006

Maintenance freshness

7/26/2026

Usage

5 downloads · 104 views

File structure

📄 SKILL.md