Skills are capability. The graph is timing. Your agent knows how to do everything. It just doesn't know when.
AI agents can use skills. What the agent does not know is when. It does not know that a story moving to review is the moment to run the certification skill — that the build is done and it is time to check the work against the spec. That timing lives in your head, and you supply it via prompt, the same way you supply every other unwritten thing.
DecisionGraph can trigger them at the right moment. Configure statuses to /review code after every story is built, and /certify-story when its time to run a QA gate. They are static capabilities you can use out of the box – or create your own.
The unwritten-spec problem and the unwritten-timing problem are the same problem. Both are things the agent is waiting for you to know first. Let DecisionGraph handle the timing, and you can let your agent handle the rest.
Your agent knows how to do everything.
It just doesn't know when.
A story in DecisionGraph moves through a lifecycle: backlog → in development → review → done. Each transition is a moment. The graph knows what moment it is.
Atlassian gives you automation rules. Someone writes a trigger: “when an issue moves to Review, notify the QA team.” That rule is a maintained artifact — it was written by a human, it lives somewhere in the config, and it drifts the moment process changes. The rule describes what should happen. It does not derive it.
The axis is the same one that runs through everything here: reported truth vs. derived truth. An automation rule reports that orchestration is happening. A status transition derives it.
Status transitions are not just state changes. They are declared moments in a lifecycle. DecisionGraph's model treats each transition as an occasion with a known context: the story's spec, its acceptance criteria, its lineage back to the feature it serves.
A skill loaded into Claude Code does not expire. It runs the same way every time. What changes is when to call it — and “when” is what the lifecycle knows. The graph is not smarter than the skill. It just knows when.
When certification runs on review, it does not have to ask for the spec. The spec is lodged to the function. The acceptance criteria are on the story. The lineage is the graph. The skill arrives already briefed — not because anyone assembled a prompt, but because the work was connected when it was done.
The graph is timing
Every status transition is a downbeat. Every skill invocation lands at the right moment. Every context is already attached. The agent has always known how. Now it knows when.
Learn how DecisionGraph turns your artifacts into assets.
See the whole loop — spec, decompose, build, verify — start to finish.
Watch → /spec-to-codeLet the agent rough out the work so your time goes to the details that matter most.
Read → /apprenticeHere's the half that's missing — and why the agent needs both.
Read → /visualThe prompt-stream spec dies with the session. The written spec keeps working after ship.
Read → /durable