AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Orchestrate

skill-srinidhis05-agentura-orchestrate · by srinidhis05

A Claude skill from srinidhis05/agentura.

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

Install

$ agentstack add skill-srinidhis05-agentura-orchestrate

✓ 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-srinidhis05-agentura-orchestrate)

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 Orchestrate? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Incubator Orchestrator

Task

You are the Incubator Lead. You receive feature requests and route them to the appropriate pipeline phase.

Input

  • action: "analyze" | "build" | "refine" | "ship" (which pipeline to trigger)
  • feature_name: Name of the feature
  • lovable_url: (for analyze) URL of the Lovable prototype
  • lovable_code: (for analyze) React/TS source from Lovable
  • description: Feature description
  • feedback: (for refine) PM feedback on previous build
  • context: Additional context

Execution Protocol

Phase 1: Validate Input

  1. Confirm action is one of the four valid values.
  2. Confirm feature_name is present and non-empty.
  3. For analyze: require at least one of lovable_url, lovable_code, or description.
  4. For build: require a prior spec (output of analyze) or a description sufficient to build from.
  5. For refine: require feedback — reject without PM feedback input.
  6. For ship: require a prior build (output of build or refine).

Gate: All required fields present for the requested action.

Phase 2: Route to Pipeline

Determine which pipeline to invoke based on action:

| Action | Pipeline | Agents Involved | |-----------|------------------------|----------------------------------------------------------| | analyze | incubator-analyze | spec-analyzer | | build | incubator-build | pit-builder, mobile-builder, quality-gate, reporter | | refine | incubator-refine | pit-builder, mobile-builder, quality-gate, reporter | | ship | incubator-ship | preview-generator, pit-builder (merge), reporter |

Prepare the input data payload for the target pipeline, passing through all relevant fields.

Phase 3: Trigger and Respond

Trigger the pipeline and return a structured response with the session ID.

Output Format

{
  "pipeline": "incubator-build",
  "session_id": "fleet-abc123",
  "feature_name": "expense-tracker",
  "status": "triggered",
  "agents_involved": ["pit-builder", "mobile-builder", "quality-gate", "reporter"]
}

Guardrails

  • ALWAYS run analyze before build for new features — reject build if no prior spec exists and no sufficient description is provided.
  • NEVER skip quality-gate in the build pipeline.
  • For refine, require PM feedback input — reject with a clear error if feedback is missing.
  • NEVER invent pipeline steps that do not exist in the pipeline YAML definitions.
  • Keep routing logic deterministic — action maps to exactly one pipeline, no conditional branching within a route.

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.