home / skills / oimiragieo / agent-studio / creation-feasibility-gate

creation-feasibility-gate skill

/.claude/skills/creation-feasibility-gate

This skill validates proposed artifacts for feasibility in the current stack, returning PASS, WARN, or BLOCK with concrete evidence.

npx playbooks add skill oimiragieo/agent-studio --skill creation-feasibility-gate

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.0 KB
---
name: creation-feasibility-gate
description: Validate whether a proposed new artifact is feasible in the current stack before creator workflows run.
version: 1.0.0
model: sonnet
invoked_by: both
user_invocable: true
tools: [Read, Glob, Grep, Skill]
error_handling: graceful
streaming: supported
---

# Creation Feasibility Gate

## Overview

Run a fast preflight feasibility check before creating a new agent/skill/workflow/hook/template/schema. This prevents low-value or impossible creator runs.

## When to Use

- Phase 0.5 dynamic creation flow
- User asks for net-new capability
- Reflection/evolution recommends artifact creation

## The Iron Law

```
DO NOT CREATE ARTIFACTS IN THIS SKILL.
ONLY RETURN PASS/BLOCK/WARN WITH EVIDENCE.
```

## Workflow

### Step 1: Resolve Target

- Identify proposed artifact type and name
- Identify expected runtime/tool dependencies
- Identify expected owner agents

### Step 2: Preflight Checks

Run these checks with concrete evidence:

1. **Existence/duplication check**
   - Catalogs + registry + artifact paths
2. **Stack compatibility check**
   - Required tooling/runtime present in current project conventions
3. **Integration readiness check**
   - Can it be routed/discovered/assigned after creation?
4. **Security/creator boundary check**
   - Ensure creator path and governance can be satisfied

### Step 3: Decision

Return one status:

- `PASS`: creation is feasible now
- `WARN`: feasible with clear caveats
- `BLOCK`: not feasible; must resolve blockers first

Use this output shape:

```json
{
  "status": "PASS|WARN|BLOCK",
  "artifactType": "agent|skill|workflow|hook|template|schema",
  "artifactName": "example-name",
  "evidence": ["..."],
  "blockers": [],
  "nextActions": ["..."]
}
```

## Output Protocol

If `BLOCK`, include concrete remediation tasks and recommended target agents.
If `PASS` or `WARN`, include exact creator skill chain to run next.

## Memory Protocol

Record feasibility patterns and recurring blockers to `.claude/context/memory/learnings.md`.

Overview

This skill performs a fast preflight feasibility check before creating a new agent, skill, workflow, hook, template, or schema. It prevents low-value or impossible creator runs by returning a clear PASS, WARN, or BLOCK decision with concrete evidence and remediation. The skill never creates artifacts itself and instead guides the creator workflow with actionable next steps.

How this skill works

The skill resolves the proposed artifact type, name, expected runtime and tool dependencies, and intended owner agents. It performs targeted preflight checks: existence/duplication against catalogs and registries, stack compatibility with current project conventions, integration readiness for routing and discovery, and security/creator governance boundaries. The output includes status, evidence, blockers if any, and precise next actions or recommended creator chains.

When to use it

  • Before kicking off a dynamic creation flow (phase 0.5) to avoid wasted runs
  • When a user requests a net-new capability or artifact not seen before
  • When reflection or automated evolution suggests creating a new artifact
  • When you need a quick gate to validate runtime/tooling compatibility
  • When governance requires an automated pre-creation safety check

Best practices

  • Always resolve artifact type, exact name, and expected ownership before checks
  • Use concrete evidence items (registry paths, config lines, discovered services)
  • Return actionable remediation tasks for BLOCK results and assign recommended agents
  • Include exact creator skill chain when returning PASS or WARN so automation can continue
  • Log recurring blockers into memory for trend detection and future automation

Example use cases

  • Validate that a proposed new skill can run on the project's Node.js runtime and has required libraries installed
  • Check that a suggested workflow name does not collide with existing registered workflows
  • Warn that a template is feasible but requires an integration key that is missing
  • Block creation of an agent if governance rules prevent external network access for that owner
  • Provide the exact creator chain to run next when preflight returns PASS

FAQ

Will this skill create artifacts if feasibility passes?

No. It only returns PASS/WARN/BLOCK with evidence and next actions. Artifact creation must be performed by the designated creator chain.

What does a WARN include?

A WARN includes feasibility evidence plus caveats and required actions that should be completed before or during creation.

How are recurring issues tracked?

Recurring blockers and patterns are recorded to a project memory file so future checks can surface common remediation steps.