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

Orch Decompose

skill-danmcinerney-orchflows-orch-decompose · by DanMcInerney

Cut a stamped spec into work-item tickets under the pack's slicing. The one decomposer for every domain.

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

Install

$ agentstack add skill-danmcinerney-orchflows-orch-decompose

✓ 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-danmcinerney-orchflows-orch-decompose)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
22d 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 Orch Decompose? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Require: a frozen [spec](../../../contracts/spec.md) whose routing stamp names a pack, carrying every field the pack's required_spec_fields cell demands — reject otherwise, naming the missing fields — and the pack's slicing reference.

Cut the spec into [work items](../../../contracts/work-item.md) under the slicing — cut count per [rules/topology.md](../../../rules/topology.md) §3: each item gets its executor from the pack's binding, the spec's pack stamp, independence: gate when the gate re-verifies it, a disjoint write scope strictly inside the run's scope, a bound, and a completion test whose criteria name oracles from the pack's oracle policy, each with its oracle provenance. A spec defect surfaced while cutting is repaired in place, the correction recorded in the worklog. Add dependency edges; issue status: pending for a non-empty depends_on, ready otherwise. Emit at most one terminal assembly item when the slicing declares one, depending on every unit item, its completion test carrying the final gate's criteria.

Map every acceptance criterion to an item, to the gate when the pack's lens owns it, or to uncovered remainder in the worklog. When the slicing cannot cover most criteria, return a decision gap naming them (§3) — never a forced slicing.

Never: branch on the domain in this body; widen the run's scope; repair a spec silently.

Return: item ids with edges, the ticket directory, uncovered remainder ([] when none), and decision_gap ([] when coverable).

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.