orca-orchestration SKILL.md skillA

orca-orchestration from upex-galaxy/agentic-qa-boilerplate is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add upex-galaxy/agentic-qa-boilerplate/orca-orchestration@git:20261029.d86b84c

Pins git:20261029.d86b84c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
upex-galaxy/agentic-qa-boilerplate
Path
.agents/skills/orca-orchestration/SKILL.md
Versions recorded
21
Latest version
git:20261029.d86b84c, committed Oct 29, 2026
First version recorded
Sep 17, 2026
Size
46,180 bytes
Repository stars
26
License
MIT

Multi-session agent orchestration for this repo: one conductor session coordinating a fleet of persistent worker sessions (one per story, per module, per failure cluster) through the Orca runtime, plus the non-Orca fallback where the same launch lines are pasted by hand. Owns the HOW of fleet work — terminals, Runs, Tasks, dispatch, briefs, claims, board cards, liveness, cleanup — while each workflow skill keeps owning the WHAT. Use when the user wants to: orchestrate or parallelize work…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Orca Orchestration — One Conductor, a Fleet of Sessions

This skill is the transport layer for work that does not fit in one session. A **conductor** talks to the owner and coordinates **workers**; each worker is a persistent agent session that owns a scope from start to finish, reports through a mailbox, and can be interrupted, questioned and resumed. The **fleet** is all workers of one **Run**.

It is **optional by construction**. Everything here has a path that works with no runtime at all: the same launch lines, pasted into terminals by a human, and the same tokens and artifacts the workflow skills already write. What the runtime buys is the step a human would otherwise do with their hands, plus a mailbox instead of screen-scraping.

**Read full SKILL.md when**: starting a fleet cold, arbitrating a claim, choosing a topology, recovering a Run from a previous session, or writing an unattended automation.

---

## When to use

- The user asks to parallelize, orchestrate, or run "one session per story / module / failure cluster".
- The user wants to talk to, steer, interrupt, question or close a session that is already running.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add upex-galaxy/agentic-qa-boilerplate/orca-orchestration@sha256:909cde6ac2efea33

The line at the top of this page pins the label git:20261029.d86b84c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_q6syloaabl6rbzhy.svg)](https://markdownregistry.com/a/art_q6syloaabl6rbzhy)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 21 versions of this file, between Sep 17, 2026 and Oct 29, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261029.d86b84c latest2026-10-29 d86b84c 46,180 BA view · diff
git:20261025.d38f1af2026-10-25 d38f1af 41,824 BA view · diff
git:20261025.b77cfee2026-10-25 b77cfee 41,705 BA view · diff
git:20261025.bd154ed2026-10-25 bd154ed 41,613 BA view · diff
git:20261022.96b48282026-10-22 96b4828 41,231 BA view · diff
git:20261011.fa9e7942026-10-11 fa9e794 40,839 BA view · diff
git:20261005.ba781fa2026-10-05 ba781fa 40,697 BA view · diff
git:20261005.1bb355b2026-10-05 1bb355b 40,604 BA view · diff
git:20261004.e175f682026-10-04 e175f68 40,657 BA view · diff
git:20261003.661cb602026-10-03 661cb60 41,132 BA view · diff
git:20260925.1ca9e642026-09-25 1ca9e64 39,964 BA view · diff
git:20260925.612ba3a2026-09-25 612ba3a 39,908 BA view · diff
git:20260925.9e4f7672026-09-25 9e4f767 40,125 BA view · diff
git:20260924.c5832372026-09-24 c583237 40,069 BA view · diff
git:20260923.27a7dc02026-09-23 27a7dc0 39,709 BA view · diff
git:20260922.1275d8d2026-09-22 1275d8d 39,682 BA view · diff
git:20260921.d3a88da2026-09-21 d3a88da 36,570 BA view · diff
git:20260918.d340d892026-09-18 d340d89 31,838 BA view · diff
git:20260918.61d0abf2026-09-18 61d0abf 31,614 BA view · diff
git:20260918.c6f9c1b2026-09-18 c6f9c1b 31,310 BA view · diff
git:20260917.b59126b2026-09-17 b59126b 27,119 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (46180 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

upex-galaxy/agentic-qa-boilerplate · 26 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_q6syloaabl6rbzhy
GET https://markdownregistry.com/api/v1/resolve?ref=upex-galaxy/agentic-qa-boilerplate/orca-orchestration
GET https://markdownregistry.com/api/v1/blob/909cde6ac2efea33ecd774f5cda385e28c5ac133e90f4b23df0c7a7e38065c4c

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from upex-galaxy/agentic-qa-boilerplate

acli SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/acli/SKILL.md · Atlassian CLI (official `acli` binary) for Jira Cloud, Confluence Cloud, and org admin tasks from the terminal. Use…
git:20261104.88a8bdc · audit A · 26 stars
agentic-qa-core SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/agentic-qa-core/SKILL.md · Foundation skill that hosts shared references cited by other workflow skills (briefing template, dispatch patterns…
git:20261104.88a8bdc · audit A · 26 stars
agentic-qa-onboard SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/agentic-qa-onboard/SKILL.md · Walks new users through this repo's QA flow — Playwright + KATA + Allure + Xray stack, Jira QA state machine (statuses…
git:20261106.21afc18 · audit B · 26 stars
bug-screenshot-annotation SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/bug-screenshot-annotation/SKILL.md · Turns a raw bug screenshot into a QA-style annotated evidence image — circles/ovals around the broken region, arrows…
git:20261104.10059d0 · audit B · 26 stars
business-api-context SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/business-api-context/SKILL.md · What the API of the system under test MEANS to the business: every endpoint group, who calls it and why, what it…
git:20261104.10059d0 · audit A · 26 stars
business-data-context SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/business-data-context/SKILL.md · What the system under test IS at the data level: business entities and why they exist, their relationships, state…
git:20261104.10059d0 · audit A · 26 stars
business-domain-context SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/business-domain-context/SKILL.md · The vocabulary and the business of the system under test: what the product is for, who pays and why, and what every…
git:20261104.10059d0 · audit A · 26 stars
business-e2e-context SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/business-e2e-context/SKILL.md · How people actually use the system under test end to end: the personas, the user journeys first (entry point, steps…
git:20261104.10059d0 · audit A · 26 stars
evidence-artifact SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/evidence-artifact/SKILL.md · Turns a ticket's test evidence into ONE private claude.ai page (an Artifact) that a developer or PM can open and read…
git:20261104.10059d0 · audit A · 26 stars
exploratory-testing SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/exploratory-testing/SKILL.md · Ticket-free exploratory testing of a critical flow, a module or the whole product, across UI, API and DB together, in…
git:20261104.10059d0 · audit A · 26 stars
framework-development SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/framework-development/SKILL.md · Framework evolution mode — evolves the QA boilerplate itself (KATA, fixtures, cli/, scripts/, api/schemas/ pipeline…
git:20261104.10059d0 · audit A · 26 stars
git-flow-master SKILL.md skill
upex-galaxy/agentic-qa-boilerplate · .agents/skills/git-flow-master/SKILL.md · End-to-end Git operator for any branching strategy. Auto-detects the project's strategy (solo-main, main+integration…
git:20261102.1ff1dab · audit A · 26 stars

Every file in upex-galaxy/agentic-qa-boilerplate

Browse by kind, by grade A, or by owner.