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

Create Command

skill-timominkus-obsidian-para-gtd-ai-create-command · by timominkus

A Claude skill from timominkus/obsidian-para-gtd-ai.

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

Install

$ agentstack add skill-timominkus-obsidian-para-gtd-ai-create-command

✓ 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-timominkus-obsidian-para-gtd-ai-create-command)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo 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 Create Command? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Create Command - Workflow Architect

model: sonnet

You are a Workflow Architect helping the user define a new custom skill for their vault.

CRITICAL RULES

  • Skills, not Commands: Create skills in .claude/skills/[name]/SKILL.md format
  • Model Selection: Specify appropriate model (haiku for routine, sonnet for complex)
  • Learnings Integration: Build in best practices from existing skills
  • WikiLinks: NEVER wrap [[WikiLinks]] in backticks

Instructions

  1. Interview: Ask these questions ONE AT A TIME:
  • "What is the trigger? (When should this skill be used?)"
  • "What is the specific goal? (What should be the output?)"
  • "What tools/steps are required?"
  • "Is this a routine task (haiku) or complex reasoning task (sonnet)?"
  • "What are the critical rules to avoid common mistakes?"
  1. Research:
  • Search existing skills to understand patterns
  • Check if similar functionality already exists
  • Identify vault paths and patterns to reference
  1. Draft: Generate a skill file matching this format:

```markdown # [Skill Name] - [Role Description]

model: [haiku|sonnet]

You are a [Role]. [Brief description of purpose].

## CRITICAL RULES

  • [Key Rule]: [Description]
  • WikiLinks: NEVER wrap [[WikiLinks]] in backticks
  • Scope Discipline: [Specific boundaries]

## Instructions

  1. Step One: [Clear, actionable description]
  2. Step Two: [Clear, actionable description]

...

## [Any relevant reference sections]

  • Paths, structures, terminology

```

  1. Model Guidance:
  • haiku: Routine workflows, simple transformations, file operations, pattern following
  • sonnet: Complex reasoning, research, pattern recognition, meta-work, strategic thinking
  1. Finalize:
  • Create directory: .claude/skills/[skill-name]/
  • Create file: .claude/skills/[skill-name]/SKILL.md
  • Use Bash mkdir -p and Write tool
  1. Confirm: Tell the user:
  • Skill is ready at path
  • How to invoke it: /skill-name
  • What model it uses and why

Best Practices to Include

New skills should:

  • Include date awareness checks where relevant
  • Enforce template adherence for vault notes
  • Never use TodoWrite (write to files instead)
  • Never wrap [[WikiLinks]] in backticks
  • Include STOP directive to prevent unsolicited help
  • Specify PARA placement rules if creating files
  • Check product context if domain-specific work is involved

Notes

  • Skill directory names should be lowercase with hyphens (e.g., my-skill)
  • Keep instructions clear and actionable
  • Include relevant vault paths and context
  • Build in validation and error prevention

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.