Skills add-backend-tool
📦

add-backend-tool

Content revision r2 Safe ⚙️ External commands

Add Backend Tools to OpenAI Function Calling

Adding backend agent tools requires coordinated changes across implementation, schemas, dispatch, and permissions. This skill provides a focused workflow for those changes.

Supports: Claude Codex Code(CC)
🥉 79 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 "add-backend-tool" from https://skillstore.io/skills/applelamps-add-backend-tool.md and its manifest at https://skillstore.io/api/skills/applelamps-add-backend-tool/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/applelamps-add-backend-tool.md Signed manifest GET /api/skills/applelamps-add-backend-tool/manifest Signed lockfile GET /api/skills/applelamps-add-backend-tool/lockfile

Test it

Using "add-backend-tool". Add a tool that lists files in a requested project directory.

Expected outcome:

  • A typed helper validates the requested directory and returns directory entries.
  • A function definition describes the path parameter and expected use.
  • The dispatch handler invokes the helper, with access limited to the appropriate mode.

Using "add-backend-tool". Create a tool that checks repository status.

Expected outcome:

  • A bounded helper reports repository status without changing files.
  • The tool definition documents the repository path and read-only behavior.
  • The handler includes clear failure reporting and a suitable timeout.

Using "add-backend-tool". Add a web data retrieval tool for a trusted service.

Expected outcome:

  • The helper validates inputs and handles service failures without exposing secrets.
  • The function description states when the agent should use the service.
  • Access restrictions reflect the tool's network and data exposure risks.

Security Audit

Safe
v9 • 7/23/2026 Open versioned report

All eight external-command alerts are Markdown formatting or fenced Python examples, not shell execution. The access-mode note contains no network probing behavior. No malicious intent, prompt injection, or data exfiltration instructions were found.

1
Files scanned
64
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (8)
SKILL.md:9 SKILL.md:10 SKILL.md:14-22 SKILL.md:22-24 SKILL.md:24-25 SKILL.md:25-41 SKILL.md:41-44 SKILL.md:44-47
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/applelamps-add-backend-tool/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/applelamps-add-backend-tool/security.svg)](https://skillstore.io/skills/applelamps-add-backend-tool?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/applelamps-add-backend-tool.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

AppleLamps. (2026). add-backend-tool security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/applelamps-add-backend-tool/audits/9

BibTeX citation

@techreport{applelamps-applelamps-add-backend-tool-2026, author = {AppleLamps}, title = {add-backend-tool security audit report (audit version 9)}, institution = {Skillstore}, year = {2026}, number = {9}, url = {https://skillstore.io/skills/applelamps-add-backend-tool/audits/9}, 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: "add-backend-tool security audit report (audit version 9)" version: "unspecified" type: report authors: - name: "AppleLamps" date-released: "2026-07-23" url: "https://skillstore.io/skills/applelamps-add-backend-tool/audits/9" identifiers: - type: other value: "skillstore:applelamps-add-backend-tool:audit:9" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
70
Community
91
Spec Compliance

What You Can Build

Add a Read-Only Utility

Create a backend tool that reads application data and expose it under appropriate mode restrictions.

Extend an Agent Workflow

Add a typed function that lets an agent perform a project-specific operation through existing dispatch logic.

Standardize Tool Contributions

Apply one implementation pattern when reviewing new helpers, schemas, handlers, and access rules.

Try These Prompts

Add a Simple Tool 
Add a backend tool named [name] that accepts [parameters] and returns [result]. Follow the existing patterns in backend/main.py.
Add a Read-Only Tool 
Create a read-only backend tool for [task]. Define its schema, connect dispatch, and assess whether chat mode access is appropriate.
Add a Mutating Tool 
Implement a backend tool that performs [operation]. Validate inputs, add a timeout, handle failures, and restrict access to the safest suitable mode.
Integrate a Complex Tool 
Add [tool] with typed parameters, bounded execution, structured errors, secret-safe configuration, dispatch integration, mode restrictions, and focused tests for success and failure paths.

Best Practices

  • Match existing helper, schema, and dispatch conventions before adding new behavior.
  • Validate every argument and apply timeouts to operations that can block.
  • Grant chat mode access only to tools with reviewed, limited, and safe behavior.

Avoid

  • Do not hardcode credentials, tokens, or private endpoints in helper functions.
  • Do not expose mutating or unrestricted tools to chat mode without authorization controls.
  • Do not define schema parameters that the helper ignores or interprets differently.

Frequently Asked Questions

Which backend architecture does this skill support?
It targets a Python backend where backend/main.py contains tool definitions, helper functions, and WebSocket dispatch logic.
Does the skill create the complete tool automatically?
It guides implementation using a generic pattern. The developer must supply domain logic, validation, and service-specific behavior.
Can a new tool be available in chat mode?
Yes, but only after confirming that the tool is read-only or otherwise safe under the application's access policy.
Does the workflow include error handling?
Yes. The helper pattern catches failures, and the guardrails require proper error handling and timeouts.
Does the workflow protect secrets?
It explicitly prohibits hardcoded API keys and secrets. The application must still provide secure configuration and runtime secret management.
Does the skill add automated tests?
No. Add focused tests for schema validation, dispatch behavior, authorization, timeouts, success responses, and failure responses.

Developer Details

Author

AppleLamps

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/AppleLamps/web-term/tree/main/.claude/skills/add-backend-tool

Ref

89edfdc710d0846129dcee6a929477b04f08052c

Maintenance freshness

7/24/2026

Usage

7 downloads · 209 views

File structure

📄 SKILL.md