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

Work Ai Custom Local Skill Draft

skill-jonayeon-claude-code-skills-work-ai-custom-local-skill-draft · by JoNaYeon

Use this skill to draft a new custom local skill tailored to a specific project workflow. Triggers on: 'create custom skill', 'write local skill', 'draft new skill', 'custom skill', '커스텀 스킬 만들기', '로컬 스킬 작성'.

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

Install

$ agentstack add skill-jonayeon-claude-code-skills-work-ai-custom-local-skill-draft

✓ 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-jonayeon-claude-code-skills-work-ai-custom-local-skill-draft)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo 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 Work Ai Custom Local Skill Draft? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Custom Local Skill Draft: {{title}}

1. Why This Skill Should Exist

  • Project / workflow:
  • Repeated task:
  • Current pain:
  • Why external skills are not enough:

2. Trigger

  • Use this skill when:
  • Do not use this skill when:
  • Typical user request examples:

3. Inputs The Skill Needs

  • Codebase / folder context:
  • Docs / design / ticket links:
  • Required files:
  • Required tools:
  • Required secrets or environment:

4. Expected Output

  • What a good result looks like:
  • Output format:
  • What decisions should be surfaced:
  • What should be left to the user:

5. Guardrails

  • Trust boundaries:
  • Risky actions to avoid:
  • What must be verified first:
  • What should require confirmation:

6. Preferred Workflow

  1. Gather context
  2. Inspect code or documents
  3. Propose the narrowest viable approach
  4. Execute
  5. Verify
  6. Summarize next steps

7. SKILL.md Skeleton

---
name: {{title}}
description: [What this skill does and when to use it]
---

# {{title}}

## When to Use
- [Trigger 1]
- [Trigger 2]

## Inputs
- [Input 1]
- [Input 2]

## Workflow
1. [Step 1]
2. [Step 2]
3. [Step 3]

## Output
- [Expected output]

## Safety Notes
- [Guardrail 1]
- [Guardrail 2]

8. Validation Cases

  • Happy path:
  • Edge case:
  • Failure mode:
  • What would make this skill clearly useful:

9. Decision

  • Build now / backlog / not worth it
  • If build now, first version scope:

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.