CONCEPT Cited by 2 sources
Agent orchestration skill¶
Definition¶
A skill (in the Rovo-Dev / Claude-Code sense of an addressable bundle of agent-facing instructions) that encodes a multi-step workflow, not a single narrow tool binding. The skill tells the agent how to work on a particular codebase end-to-end — the golden-path loops, the sequencing of tools, the verification checkpoints.
Atlassian's Rovo Dev / Fireworks post is the canonical articulation:
"We've built a meta-workflow / orchestration skill for Fireworks development. It doesn't do one narrow technical thing, instead it gives the agent a set of 'golden path' loops for how to work on Fireworks changes end-to-end." (Source: sources/2026-04-24-atlassian-rovo-dev-driven-development)
Two kinds of skills¶
| Narrow / tool-binding skill | Orchestration / meta-workflow skill |
|---|---|
| One domain or one action | End-to-end workflow across domains |
| E.g. "how to use our CLI", "how to write a Raft test", "how to make a PR" | E.g. "how to work on Fireworks changes end-to-end" |
| Answers what does this tool do | Answers which tools in which order for this change shape |
| Single invocation | Multi-step loop with checkpoints |
The Fireworks post names the first kind ("Skills for PRs, using CLI, specific domains like Raft, gRPC") as the conventional skill and introduces the orchestration variant as the higher- leverage form for sustained work on a codebase.
Why orchestration skills matter¶
A coding agent's context budget is finite. For a complex codebase with many tools, many conventions, and a non-obvious golden-path sequence, the agent either:
- Re-discovers the sequence every task — expensive, error- prone, and dependent on the agent's ability to piece together scattered README files.
- Loads a pre-compiled orchestration skill — the sequence, conventions, and common traps are encoded once, loaded as context when the agent needs them, and maintained as the codebase evolves.
This is the procedural-knowledge analogue of a README — but structured for agent consumption rather than human onboarding. The Fireworks team reports the form factor works: "we've built lots of skills" and specifically "a skill that automates deploying, operating, and tearing down isolated Fireworks dev shards on the shared AWS scms Kubernetes cluster" — a second orchestration skill, for the dev-shard management sub-workflow.
What goes in an orchestration skill¶
Inferable from the Fireworks description:
- Entry points — the workflows this skill covers ("raise a PR", "fix a failing test", "deploy to a dev shard").
- Tool sequences — which tools to invoke in which order for each entry point.
- Verification checkpoints — when to pause and check (run tests, check CI, read pipeline output).
- Common traps / exclusions — things the agent should not do on this codebase ("don't skip the Helm validation step", "don't merge without running e2e").
- Escape hatches — when to hand back to the human.
This is the same shape as a human team runbook, re-targeted at an LLM agent consumer.
Not the same as¶
- A system prompt. The system prompt is always on. Skills are addressable — the agent loads them on demand. Maintaining a skill does not inflate every conversation.
- A tool schema. A tool schema describes how to call a tool. An orchestration skill describes which tools to call in which order for a workflow.
- A spec. A spec describes what the system does. A skill describes how the agent works on the system.
Per-codebase variability and skill-fallback chains¶
Atlassian's 2026-06-01 KTLO-automation post extends the orchestration-skill concept along a new axis: per-codebase variability across thousands of repositories.
"Atlassian hosts thousands of repositories owned by hundreds of teams, each with their own codebases and conventions so a 'one-size-fits-all' doesn't work. We've encoded our cleanup experience into repository-specific agent skills, and the system prompt gives each agent a clear fallback path: (1) repository's existing cleanup procedure → (2) flag the repo as needing a dedicated skill + provide owner instructions → (3) generic cleanup skill that works across most codebases." (Source: sources/2026-06-01-atlassian-how-we-cut-up-to-80-of-engineering-chores-using-ai-agents-in)
Two new structural moves on top of the meta-workflow framing:
- Repository-specific skills — the orchestration skill is scoped to one codebase, encoding its conventions / linters / flag wrapper APIs / test-cleanup discipline. Many such skills exist in parallel; the agent picks the one matching the repo it's working on.
- Skill-fallback chain — when the repo-specific skill is absent, the agent's "no skill exists" failure mode is converted into operational signal that prompts the team to author one (tier 2), with a generic fallback (tier 3) producing a working draft PR even without a repo-specific skill. Canonicalised as patterns/agent-skill-with-fallback-chain.
The fallback-chain mechanic also generalises to other selector axes — Atlassian's flaky-test workflow uses per-test-category specialist skills with the same classify-then-dispatch shape (patterns/test-category-classifier-then-specialist-skill).
Two axes of skill specialisation¶
The wiki now names two distinct selector axes for orchestration skills:
| Selector axis | Skill shape | Canonical instance |
|---|---|---|
| Per-codebase | One orchestration skill per repository | Atlassian KTLO cleanup; Fireworks dev-shard |
| Per-failure-category | One specialist skill per failure type | Atlassian flaky-test (unit / integration / visual) |
The two axes can compose: a flaky-test agent can classify on test-category, then within that, fall back from repo-specific specialist skill → flag-for-creation → generic specialist skill.
Seen in¶
- sources/2026-04-24-atlassian-rovo-dev-driven-development — canonical articulation; Fireworks team built a meta-workflow skill for end-to-end development, plus a dev-shard deploy / operate / teardown orchestration skill.
- sources/2026-06-01-atlassian-how-we-cut-up-to-80-of-engineering-chores-using-ai-agents-in — extends the concept with the per-codebase-variability axis and the three-tier skill-fallback chain (patterns/agent-skill-with-fallback-chain); also names the per-test-category dispatch (patterns/test-category-classifier-then-specialist-skill). KTLO-axis instance of orchestration skills (vs. the greenfield-axis Fireworks instance).
Related¶
- concepts/agentic-development-loop
- concepts/work-item-as-agent-prompt — the substrate skills are loaded in response to.
- concepts/agent-as-first-pass-investigator — the operational model the skill executes inside.
- concepts/ktlo-engineering-chores — the work category per-codebase skills are most often authored for.
- patterns/agent-orchestration-meta-skill — Fireworks greenfield-dev variant.
- patterns/agent-skill-with-fallback-chain — KTLO-axis per-codebase fallback chain.
- patterns/test-category-classifier-then-specialist-skill — per-failure-category dispatch.
- patterns/jira-status-transition-triggers-agent-workflow — the trigger that loads the right skill.
- patterns/mcp-tools-plus-skills-unified-platform
- patterns/migration-as-agent-skill
- systems/rovo-dev
- systems/atlassian-fireworks
- systems/jira