> ## Documentation Index
> Fetch the complete documentation index at: https://docs.builddown.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# BuildDown skills

> A suite of Claude Code skills for planning, sequencing, landing, and verifying work driven through an AI coding agent.

<Warning>
  **Experimental version.**

  This is the latest in-development version of AI-Implement. Features may change without notice and behavior is not guaranteed. Switch to the [latest stable version here](/introduction).
</Warning>

Running a ticket-to-pull-request pipeline surfaces four recurring questions. Each has a skill that answers it:

* I have a design or an objective — how do I turn it into well-scoped tickets the agent can finish in one pass? **→** **`bd-build-up`** or **`bd-mega-build-up`** when the design should be pressure-tested first
* I have a stack of planned tickets — what order should they go out in, and which will fail without more context? **→** **`bd-summit-push`**
* I have a pile of open pull requests from the agent — which merge, which need another pass, and which are blocked? **→** **`bd-build-down`** or **`bd-super-build-down`** for many at once
* Did the preview actually work, or did the agent just make the diff look right? **→** **`bd-smoke-jumper`**

These skills run inside your own Claude Code session while you plan and review. They're separate from the AI-Implement orchestrator, which is what later picks up a marked issue and opens the pull request.

<Note>
  The remaining two skills sit outside that sequence:

  * `bd-project-setup` runs once to wire a project to its tools
  * `bd-belay-on` formalizes handing a question to a different tool at any point along the way
</Note>

## How the skills fit together

```mermaid theme={null}
graph TD
    setup(["bd-project-setup<br/>run once per project"])
    up["bd-build-up<br/>plan the work"]
    mega["bd-mega-build-up<br/>plan, grilled harder"]
    push["bd-summit-push<br/>sequence and harden"]
    agent(["your coding agent<br/>opens pull requests"])
    down["bd-build-down<br/>drive to merge"]
    sdown["bd-super-build-down<br/>drive to merge, at volume"]
    smoke["bd-smoke-jumper<br/>verify the preview"]

    setup --> up
    setup --> mega
    up --> push
    mega --> push
    push ==> agent
    agent ==> down
    agent ==> sdown
    down --> smoke
    sdown --> smoke

    classDef external stroke-width:3px
    class agent,setup external
```

## What ties them together

The skills share one autonomy model, so a skill either acts or asks for the same reasons throughout.

They also read the same recorded project bindings rather than each asking you where your issues live — which is what `bd-project-setup` exists to write.

They assume a common setup: a connected issue tracker, a connected GitHub account, browser automation for preview testing, and a coding agent that responds to pull request comments.

Six of the eight understand feature-branch grouping. When a parent issue and its children are marked together, they treat the tree as one unit that rolls up to a single reviewable pull request rather than as unrelated issues.

## Available skills

| Skill                 | What it does                                                                                                                               |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| `bd-project-setup`    | Wires a project to its tools once — creates the tracker connection, authorizes it, and **records the settings every other skill reads**.   |
| `bd-build-up`         | Turns an objective or design into a **sequenced, dependency-aware set of tracker issues**, shown for your review before anything is filed. |
| `bd-mega-build-up`    | A deeper `bd-build-up` for larger work — pressure-tests the design first, then files issues alongside attached design and plan documents.  |
| `bd-summit-push`      | Optimizes a set of planned issues — their order, dependencies, and wording — for the best chance of one-shot success through the pipeline. |
| `bd-build-down`       | Drives open pull requests to merge: reviews each against its gap analysis, resolves what's missing, and lands the ones that are ready.     |
| `bd-super-build-down` | A faster, hands-off `bd-build-down` for many pull requests at once or unattended runs.                                                     |
| `bd-smoke-jumper`     | Smoke-tests a pull request's preview deploy, posts a verdict, and files issues for anything that fails.                                    |
| `bd-belay-on`         | Coordinates handing a task off to another tool and folding the results back in cleanly.                                                    |

**Tracker support varies by skill.** `bd-build-down` and `bd-mega-build-up` carry dedicated Jira handling alongside Linear.

`bd-build-up`, `bd-summit-push`, and `bd-super-build-down` describe Jira behavior projected from their Linear behavior rather than fully adapted to it, so **Linear assumptions may show through on Jira projects**.

<Note>
  `bd-project-setup` binds either tracker, and the remaining skills don't depend on one.
</Note>

## Next step

<Card title="Install the skills" icon="download" href="/latest/skills/installation">
  Add the plugin to Claude Code and choose a release channel.
</Card>